{ "name": "AlpineDataWorks \u2014 Intelligence Catalog", "version": "2026-07-19", "generated": "2026-07-19", "schema": "https://alpinedataworks.com/iom.schema.json", "count": 308, "products": [ { "id": "ADW-001", "name": "Crypto Market Sentiment & Volatility Index", "domain": "Market/Crypto", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-001", "mcp_tool": "adw.adw_001", "sample": "https://alpinedataworks.com/showcase/adw-001", "description": "The current sentiment and volatility regime of the crypto market, scored 0-100.", "agent_question": "What is the current sentiment & volatility regime for crypto?", "history_start": "2018-02-01", "history_years": 8.4, "product_class": "time-series", "tier": "Gold", "refresh": "hourly", "source_apis": [ "Alternative.me", "CoinGecko", "Coinbase", "OKX" ], "mcp_description": "Returns a 0-100 crypto sentiment and volatility regime index (0.4 sentiment + 0.3 volume momentum + 0.3 volatility adjustment from Alternative.me, CoinGecko, Coinbase, OKX; hourly, history to 2018) with composite_score, sentiment_component, volatility_component, liquidity_depth. Call when the user asks about crypto market sentiment, fear and greed, Bitcoin volatility, risk regimes, or market mood, or when timing portfolio rebalancing, defensive hedging, or crypto entry/exit decisions." }, { "id": "ADW-002", "name": "US Macro Economic Health Score", "domain": "Financial/Macro", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-002", "mcp_tool": "adw.adw_002", "sample": "https://alpinedataworks.com/showcase/adw-002", "description": "The overall health of the US macro economy, scored 0-100 from key indicators.", "agent_question": "How healthy is the US macro economy right now?", "history_start": "1960-12-01", "history_years": 65.6, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED", "BLS", "BEA" ], "mcp_description": "Returns a 0-100 US macro economic health score (Z-scored CPI inflation, unemployment, and GDP growth from FRED/BLS/BEA, monthly history to 1960) with inflation_pressure, labor_market_status, and growth_momentum sub-fields. Call when the user asks about US economic health, recession risk, macro conditions, inflation, jobs, or the business cycle, or when timing portfolio shifts (bond duration, TIPS allocation) around monthly macro data releases." }, { "id": "ADW-003", "name": "DeFi Protocol TVL & Yield Driver", "domain": "Market/Crypto", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-003", "mcp_tool": "adw.adw_003", "sample": "https://alpinedataworks.com/showcase/adw-003", "description": "The drivers behind changes in a DeFi protocol's total value locked and yields.", "agent_question": "Why is TVL in this DeFi protocol changing?", "history_start": "2018-03-14", "history_years": 8.3, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "DeFiLlama", "Etherscan" ], "mcp_description": "Returns a 0-100 DeFi protocol TVL-driver score (daily DeFiLlama + Etherscan data; TVL/APY divergence logic decomposed by asset type, history to 2018) with primary_driver_label, tvl_delta_usd, apy_trend, and asset_composition. Call when the user asks why a protocol's TVL, total value locked, liquidity, or yield/APY is changing, or when timing treasury reallocations before yield-driven inflows flip to composition-shift outflows and withdrawal cascades." }, { "id": "ADW-004", "name": "US Bank Stability & Branch Coverage Index", "domain": "Financial", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-004", "mcp_tool": "adw.adw_004", "sample": "https://alpinedataworks.com/showcase/adw-004", "description": "The stability and branch coverage of the US banking system, scored 0-100.", "agent_question": "What is the stability & coverage of US banking?", "history_start": "1976-12-01", "history_years": 49.6, "product_class": "time-series", "tier": "Gold", "refresh": "quarterly", "source_apis": [ "FDIC BankFind", "FRED" ], "mcp_description": "Returns a 0-100 US bank stability and branch coverage index (FDIC BankFind + FRED; branch density and deposit growth scaled by bank failure rate; quarterly since 1976) with stability_index, branch_density_score, and failure_risk_indicator. Call when the user asks about banking system health, bank failures, branch density, deposit growth, or regional banking access, or when timing credit-risk premiums for geographically concentrated SMB loan underwriting." }, { "id": "ADW-005", "name": "Global Real Estate Affordability Score", "domain": "Retail/Location", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-005", "mcp_tool": "adw.adw_005", "sample": "https://alpinedataworks.com/showcase/adw-005", "description": "Real estate affordability relative to income across global markets, scored 0-100.", "agent_question": "How affordable is real estate vs income?", "history_start": "1963-03-31", "history_years": 63.3, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED housing", "World Bank" ], "mcp_description": "Returns a 0-100 global real estate affordability score (higher = more affordable; normalized price-to-income and rent-to-income from FRED housing and World Bank data, monthly since 1963) with affordability_score, price_to_income_ratio, rent_to_income_ratio. Call when the user asks about housing affordability, home prices vs income, rent burden, or housing market valuation, or when timing real estate acquisitions, multifamily underwriting, or rental-demand investment screens." }, { "id": "ADW-006", "name": "Energy Grid Carbon Intensity Summary", "domain": "Energy", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-006", "mcp_tool": "adw.adw_006", "sample": "https://alpinedataworks.com/showcase/adw-006", "description": "The carbon intensity and renewable share of energy-grid generation, tracked over time.", "agent_question": "Current carbon intensity & renewable share?", "history_start": "1973-01-31", "history_years": 53.4, "product_class": "time-series", "tier": "Gold", "refresh": "hourly", "source_apis": [ "EIA Open Data", "Electricity Maps" ], "mcp_description": "Returns a 0-100 renewable-share and grid carbon intensity summary (weighted 24h avg CO2, EIA + Electricity Maps, hourly, history since 1973) with avg_co2_intensity, renewable_share_pct, grid_load_status, and greenness_flag (renewables >50%). Call when the user asks about carbon intensity, grid emissions, renewable share, clean energy, or electricity greenness, or when timing carbon-aware scheduling of compute, ML training, or batch workloads for Scope 2 reporting." }, { "id": "ADW-007", "name": "News Sentiment & Trend Velocity Index", "domain": "Market/News", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-007", "mcp_tool": "adw.adw_007", "sample": "https://alpinedataworks.com/showcase/adw-007", "description": "The current sentiment and trend velocity of global news coverage, scored 0-100.", "agent_question": "Current global news sentiment & velocity?", "history_start": "2015-02-19", "history_years": 11.4, "product_class": "time-series", "tier": "Gold", "refresh": "hourly", "source_apis": [ "GDELT", "RSS", "CoinDesk Data" ], "mcp_description": "Returns a 0-100 global news sentiment and trend velocity index (hourly GDELT, RSS, and CoinDesk tone plus story-volume acceleration, weighted 0.6 Tone + 0.4 Velocity, history to 2015) with sentiment_index, news_velocity, tone_score, and source_diversity_score. Call when the user asks about news sentiment, media tone, news-flow spikes, breaking-news momentum, or headline risk, or when timing risk-off hedges, market-making spread widening, or event-driven volatility alerts." }, { "id": "ADW-008", "name": "AI/Software Ecosystem Health Driver", "domain": "Tech/Cloud", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-008", "mcp_tool": "adw.adw_008", "sample": "https://alpinedataworks.com/showcase/adw-008", "description": "The health of the AI/software ecosystem, separating organic growth from hype in developer activity.", "agent_question": "Organic growth or hype in AI/software?", "history_start": "1993-12-01", "history_years": 32.6, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "GitHub REST API (keyless)" ], "mcp_description": "Returns a 0-100 AI/software ecosystem health score (daily, reproducible from keyless GitHub REST data: 10-repo AI/ML basket, 0.6 stars-mindshare + 0.4 issue/star engagement) with health_score, primary_driver_label, organic_vs_hype, and basket_total_stars. Call when the user asks whether AI open-source momentum is organic growth or hype, about developer mindshare or ecosystem sentiment, or when timing AI investment-thesis reassessments, venture portfolio reviews, or tech-stack bets." }, { "id": "ADW-009", "name": "Supply Chain & Logistics Continuity Score", "domain": "Logistics", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-009", "mcp_tool": "adw.adw_009", "sample": "https://alpinedataworks.com/showcase/adw-009", "description": "The stress level and continuity of global supply chains and logistics, scored 0-100.", "agent_question": "How stressed are global supply chains?", "history_start": "1975-12-01", "history_years": 50.6, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "Freightos FBX", "Drewry WCI", "NY Fed GSCPI" ], "mcp_description": "Returns a 0-100 global supply chain continuity score (low = acute stress; normalized Freightos FBX and Drewry WCI freight indices plus NY Fed GSCPI z-score, weekly since 1975) with continuity_score, freight_trend, and confidence. Call when the user asks about supply chain stress, container shipping costs, ocean freight rates, logistics disruption, or port congestion, or when timing import purchase orders, safety-stock buffers, or expediting alternate suppliers." }, { "id": "ADW-010", "name": "Public Data Source Quality & Freshness Index", "domain": "Source-Quality", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-010", "mcp_tool": "adw.adw_010", "sample": "https://alpinedataworks.com/showcase/adw-010", "description": "The freshness, completeness, and quality of public data sources, scored 0-100.", "agent_question": "How fresh & complete is this source?", "history_start": "1975-12-01", "history_years": 50.6, "product_class": "time-series", "tier": "Platinum", "refresh": "daily", "source_apis": [ "data.gov", "FRED", "SEC EDGAR", "World Bank" ], "mcp_description": "Returns a 0-100 source quality and freshness index (0.5 freshness + 0.3 completeness + 0.2 stability, computed daily across data.gov, FRED, SEC EDGAR, World Bank) with quality_index, freshness_hours, completeness_pct, stability_score. Call when the user asks about data freshness, staleness, completeness, or source reliability, or when timing downstream pipeline refreshes so stale or degraded upstream data pauses jobs instead of propagating into scored outputs." }, { "id": "ADW-015", "name": "Consumer-Credit Stress Index", "domain": "Consumer/Credit", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-015", "mcp_tool": "adw.adw_015", "sample": "https://alpinedataworks.com/showcase/adw-015", "description": "Composite z-score of credit-card delinquency rate and revolving credit growth. High score = elevated consumer-credit stress.", "agent_question": "How stressed is US consumer credit right now \u2014 rising delinquencies or credit binging?", "history_start": "1992-06-30", "history_years": 34.0, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (DRCCLACBS, REVOLSL)" ], "mcp_description": "Returns a monthly 0-100 US consumer-credit stress score (FRED card delinquency rate + revolving credit YoY, z-scored vs trailing 36 months; 50=neutral, higher=stress; since 1992) with trend, confidence, stress_level, top_drivers, delinquency_rate_pct, revolving_credit_yoy_pct. Call when the user asks about consumer credit stress, card delinquencies, revolving debt, credit binging, or household borrowing, or when timing underwriting tightening, collections pre-staging, or credit-risk alerts." }, { "id": "ADW-101", "name": "Entropy-Weighted CUSUM (EWC)", "domain": "Markets/Vol", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-101", "mcp_tool": "adw.adw_101", "sample": "https://alpinedataworks.com/showcase/adw-101", "description": "An entropy-weighted CUSUM signal of imminent volatility regime shifts, for position sizing and hedge timing.", "agent_question": "Enables traders to anticipate imminent volatility regime shifts to optimize position sizing and hedge timing before market instability occurs.", "history_start": "2016-09-21", "history_years": 9.8, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Stooq daily OHLCV (SPY, keyless)" ], "mcp_description": "Returns a 0-100 volatility regime-shift early-warning score for US equities (daily SPY log-returns, 60-day rolling z-score, CUSUM change-point detection, Shannon entropy weighting; 9+ years history) with trend, confidence, top_drivers, ewc_raw, and cusum_statistic. Call when the user asks about market volatility, regime change, S&P 500 instability, turbulence, or vol spikes, or when timing position sizing, hedge adjustments, or options/straddle exposure ahead of market instability." }, { "id": "ADW-102", "name": "Tail Probability Shift (TPS)", "domain": "Markets/Vol", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-102", "mcp_tool": "adw.adw_102", "sample": "https://alpinedataworks.com/showcase/adw-102", "description": "Early-stage shifts in fat-tail probability of market returns, flagging rising drawdown risk before stress events.", "agent_question": "Enables traders to detect early-stage increases in fat-tail risk to prevent catastrophic drawdowns during market stress events.", "history_start": "2017-06-28", "history_years": 9.0, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Stooq daily OHLCV (SPY, keyless)" ], "mcp_description": "Returns a 0-100 fat-tail risk escalation score for US equities (shift in S&P 500/SPY's 20-day tail-exceedance rate beyond 1.5\u03c3 vs its 252-day baseline, sigmoid-scaled, refreshed daily) with score, trend, confidence, top_drivers, tail_prob_shift, tail_prob_recent, tail_prob_baseline. Call when the user asks about tail risk, fat tails, crash probability, extreme moves, volatility regime shifts, or drawdown risk, or when timing de-risking, hedging, or gross-exposure cuts ahead of market stress." }, { "id": "ADW-103", "name": "Phase-Slope", "domain": "Markets/Vol", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-103", "mcp_tool": "adw.adw_103", "sample": "https://alpinedataworks.com/showcase/adw-103", "description": "The slope of the volatility cycle phase, flagging cyclical regime shifts ahead of standard volatility metrics.", "agent_question": "Identify cyclical volatility regime shifts to time entries and exits with higher predictive accuracy than standard volatility metrics.", "history_start": "2016-08-08", "history_years": 9.9, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Stooq daily OHLCV (SPY, keyless)" ], "mcp_description": "Returns a daily 0-100 volatility regime-shift score (10-day OLS slope of SPY 20-day realized volatility, percentile-ranked against a 252-day history) with trend, confidence, top_drivers, realized_vol_20d_ann, and vol_slope_10d. Call when the user asks about volatility regimes, vol expansion or compression, whether market volatility is rising or falling, or SPY realized vol trend, or when timing entries, exits, hedges, or long/short-gamma options positioning." }, { "id": "ADW-104", "name": "Price-Range Ratio", "domain": "Markets/Vol", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-104", "mcp_tool": "adw.adw_104", "sample": "https://alpinedataworks.com/showcase/adw-104", "description": "The ratio of recent price ranges, flagging assets with expanding volatility ahead of potential breakouts.", "agent_question": "Helps traders identify assets with expanding volatility ranges to anticipate breakout opportunities and optimize entry timing.", "history_start": "2016-07-19", "history_years": 10.0, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Stooq daily OHLCV (SPY, keyless)" ], "mcp_description": "Returns a 0-100 volatility-range expansion score for US equities (SPY daily OHLCV via Stooq; ATR-14 vs ATR-252 baseline, percentile-ranked over 10 years; ratio >1 = expanding) with score, trend, confidence, top_drivers, atr_14d, atr_252d_baseline, price_range_ratio. Call when the user asks about volatility expansion, widening trading ranges, ATR, or breakout setups, or when timing momentum entries, breakout alerts, or market-making spread widening for intraday range risk." }, { "id": "ADW-105", "name": "Local Tail Variance Ratio (LTVR)", "domain": "Markets/Vol", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-105", "mcp_tool": "adw.adw_105", "sample": "https://alpinedataworks.com/showcase/adw-105", "description": "The local tail variance ratio, measuring accelerating volatility regimes for entry timing and hedging.", "agent_question": "Enables traders to identify accelerating volatility regimes for timing entries or hedging based on statistically validated predictive power.", "history_start": "2016-09-21", "history_years": 9.8, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Stooq daily OHLCV (SPY, keyless)" ], "mcp_description": "Returns a 0-100 volatility-regime score for SPY (percentile-ranked 60-day rolling tail-variance ratio \u2014 share of variance from extreme 20th/80th-percentile daily moves; Stooq OHLCV, daily since 2016) with trend, confidence, top_drivers, ltvr_raw, and realized_vol_20d_ann. Call when the user asks about volatility regimes, tail risk, market turbulence, vol spikes, or S&P 500 risk, or when timing protective hedges, put spreads, or trade entries before realized volatility accelerates." }, { "id": "ADW-106", "name": "Tail Mean Difference (TMD)", "domain": "Markets/Return", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-106", "mcp_tool": "adw.adw_106", "sample": "https://alpinedataworks.com/showcase/adw-106", "description": "The difference between upper- and lower-tail mean returns, capturing asymmetric return distributions that linear factors miss.", "agent_question": "Capture non-linear return dynamics by measuring the difference between tail means to identify assets with asymmetric return distributions that linear factors miss.", "history_start": "2016-09-21", "history_years": 9.8, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Stooq daily OHLCV (SPY, keyless)" ], "mcp_description": "Returns a daily 0-100 return-asymmetry score for US equities (SPY 60-day returns; 90th-percentile upper-tail mean minus 10th-percentile lower-tail mean; 50=symmetric, >50=upside skew) with trend, confidence, top_drivers, tmd_raw, and upper/lower tail means. Call when the user asks about return skewness, tail risk asymmetry, fat tails, or non-linear return dynamics, or when timing factor rotations between momentum/growth and defensive low-volatility tilts." }, { "id": "ADW-016", "name": "Promo-Elasticity Gap", "domain": "Retail/Marketing", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-016", "mcp_tool": "adw.adw_016", "sample": "https://alpinedataworks.com/showcase/adw-016", "description": "The gap between promotional spend and price elasticity by retail category, flagging underperforming trade investments.", "agent_question": "Identify underperforming promotional investments to reallocate trade spend toward high-elasticity categories for maximum revenue lift.", "history_start": "1962-12-01", "history_years": 63.6, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Internal POS transaction logs", "promotional calendar data", "and competitor pricing feeds from public web scraping or free market reports." ], "mcp_description": "Returns a 0-100 promo-elasticity gap score by retail category (realized promotional ROI versus the elasticity-implied maximum, computed daily from POS volume, discount depth, promo calendars, and competitor pricing) with score, trend, confidence, and top_drivers. Call when the user asks about promotion effectiveness, trade-spend ROI, discount depth, or price elasticity, or when timing trade-budget reallocation and promo-calendar decisions." }, { "id": "ADW-017", "name": "Shopper-Impact / Discretionary Squeeze", "domain": "Consumer/Macro", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-017", "mcp_tool": "adw.adw_017", "sample": "https://alpinedataworks.com/showcase/adw-017", "description": "The financial pressure on consumers' discretionary spending, scored 0-100 for timing promotions and assortment decisions.", "agent_question": "Enables retailers and brands to time promotions and optimize assortment by quantifying the financial pressure on consumers' discretionary spending.", "history_start": "2010-02-01", "history_years": 16.4, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (CPILFESL, CES0500000003)" ], "mcp_description": "Returns a 0-100 monthly consumer discretionary-squeeze score (YoY Core CPI vs. wage growth divergence, FRED, z-scored vs 36-month window; 50=neutral, higher=squeeze rising) with squeeze_level, trend, real_wage_gap_pct, core_cpi_yoy_pct, wage_growth_yoy_pct. Call when the user asks about consumer spending pressure, inflation outpacing wages, real wages, purchasing power, or cost-of-living squeeze, or when timing retail promotions, promo depth, value messaging, or assortment decisions." }, { "id": "ADW-018", "name": "Demographic Affinity / Site-Selection", "domain": "Retail/Location", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-018", "mcp_tool": "adw.adw_018", "sample": "https://alpinedataworks.com/showcase/adw-018", "description": "Demographic affinity between store concepts and local population characteristics, scored for retail site selection by zip code.", "agent_question": "Identify high-potential zip codes for new retail locations by matching store concepts to local population characteristics.", "history_start": "1987-12-31", "history_years": 38.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "US Census Bureau (ACS)", "Bureau of Economic Analysis" ], "mcp_description": "Returns a 0-100 demographic-affinity score for retail site selection by US zip code (Census ACS income, age, and household-size data blended with proprietary spending-propensity weights; daily refresh, history to 1987) with score, trend, confidence, and top_drivers. Call when the user asks about where to open a store, zip-code site screening, or trade-area demographic fit, or when timing lease commitments, market entry, or new-store openings." }, { "id": "ADW-019", "name": "Supply-Chain Disruption Cost", "domain": "Logistics", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-019", "mcp_tool": "adw.adw_019", "sample": "https://alpinedataworks.com/showcase/adw-019", "description": "The quantified financial cost of supply-chain disruptions, informing hedge-now versus wait decisions on inventory.", "agent_question": "Quantify the financial impact of supply-chain disruptions to determine whether immediate inventory hedging or strategic waiting yields the lower total cost.", "history_start": "1916-12-01", "history_years": 109.6, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Public trade statistics", "global shipping index reports", "and commodity price feeds." ], "mcp_description": "Returns a 0-100 supply-chain disruption cost index (stochastic optimization over lead-time volatility, demand variance, and holding costs from trade statistics, shipping indices, and commodity price feeds) with score, trend, confidence, and top_drivers. Call when the user asks about supply-chain disruption, stockout risk, or freight cost pressure, or when timing a hedge-now versus wait inventory decision." }, { "id": "ADW-020", "name": "Supply-Chain Early Warning", "domain": "Logistics", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-020", "mcp_tool": "adw.adw_020", "sample": "https://alpinedataworks.com/showcase/adw-020", "description": "Early-warning signals of geopolitical and operational supply-chain disruptions before they hit inventory levels.", "agent_question": "Enable logistics managers to proactively diversify suppliers by identifying geopolitical or operational disruptions before they impact inventory levels.", "history_start": "1998-01-31", "history_years": 28.4, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "GDELT Project (Global Database of Events", "Language", "and Tone)" ], "mcp_description": "Returns a 0-100 supply-chain disruption-risk score (NLP over GDELT-derived news sentiment and official trade alerts, entity-specific risk events weighted into a disruption probability, daily since 1998) with score, trend, confidence, and top_drivers. Call when the user asks about supply-chain risk, supplier or trade-lane disruption, geopolitical logistics exposure, or port stability, or when timing supplier diversification, safety-stock increases, or purchase-order pull-forwards." }, { "id": "ADW-021", "name": "Healthcare Staffing Shortage", "domain": "Health", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-021", "mcp_tool": "adw.adw_021", "sample": "https://alpinedataworks.com/showcase/adw-021", "description": "The severity of nursing-staff shortages, tracked to flag staffing gaps before they impact patient care and costs.", "agent_question": "Enable healthcare administrators to proactively recruit and deploy nursing staff before critical staffing shortages impact patient care and operational costs.", "history_start": "1948-06-30", "history_years": 78.0, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "CDC National Hospital Discharge Survey", "Bureau of Labor Statistics (BLS) healthcare employment data", "hospital public charge volume reports." ], "mcp_description": "Returns a 0-100 nursing-staff shortage risk score (daily time-series forecast blending real-time hospital admission rates, seasonal patterns since 1948, and BLS local healthcare employment) with score, trend, confidence, and top_drivers. Call when the user asks about hospital staffing gaps, nurse shortages, or healthcare labor-market tightness, or when timing travel-nurse contracts, float-pool deployment, or nurse recruiting spend." }, { "id": "ADW-023", "name": "Energy-Cost Volatility", "domain": "Energy", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-023", "mcp_tool": "adw.adw_023", "sample": "https://alpinedataworks.com/showcase/adw-023", "description": "The volatility of energy costs facing corporate buyers, quantifying price risk in operational budgets.", "agent_question": "Enables corporate buyers to quantify price risk and justify locking in long-term energy contracts to stabilize operational budgets.", "history_start": "1989-12-29", "history_years": 36.5, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (DCOILWTICO, CPIENGSL)" ], "mcp_description": "Returns a 0-100 energy-cost volatility index (30-day WTI log-return stdev 70% + 3-month Energy CPI stdev 30%, normalized vs 5-year history; FRED, monthly since 1989) with score, trend, confidence, top_drivers, volatility_level, latest WTI price and 30-day change. Call when the user asks about energy price risk, oil/fuel cost swings, or hedging energy exposure, or when timing long-term energy contract locks, WTI futures hedges, fixed-price utility agreements, or procurement budgets." }, { "id": "ADW-024", "name": "Aspiration Premium Index", "domain": "Consumer/Brand", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-024", "mcp_tool": "adw.adw_024", "sample": "https://alpinedataworks.com/showcase/adw-024", "description": "The share of a brand's pricing power driven by aspiration versus functional utility, flagging pricing fragility.", "agent_question": "Enables brands to distinguish whether their pricing power stems from emotional aspiration or functional utility to identify and mitigate pricing fragility.", "history_start": "1960-12-01", "history_years": 65.6, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (CPIAPPSL, CPILFESL)" ], "mcp_description": "Returns a 0-100 consumer aspiration-premium index (apparel CPI YoY minus core CPI YoY, z-scored vs 5yr history; FRED, monthly since 1960) with score, trend, confidence, top_drivers, and aspiration_spread_pct. Call when the user asks about brand pricing power, emotional-aspiration vs functional-utility demand, apparel inflation, or premium pricing fragility, or when timing price increases, markdowns, or competitive price-sensitivity tests." }, { "id": "ADW-026", "name": "Gas Perception-Gap", "domain": "Consumer/Behavioral", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-026", "mcp_tool": "adw.adw_026", "sample": "https://alpinedataworks.com/showcase/adw-026", "description": "The divergence between actual gasoline price moves and consumer sentiment, flagging political risk and demand destruction.", "agent_question": "Quantifies divergence between actual gasoline price moves and consumer sentiment to flag political risk and demand-destruction scenarios.", "history_start": "1982-10-01", "history_years": 43.8, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (CUSR0000SETB01, UMCSENT)" ], "mcp_description": "Returns a 0-100 gas perception-gap score (MoM gasoline CPI vs UMich consumer sentiment, divergence z-scored vs 36-month history; 100=aligned, 0=extreme gap) with trend, confidence, alignment_label, and signed divergence_z_score. Call when the user asks about gas prices vs consumer mood, pump-price sentiment, fuel-cost inflation perception, or gasoline political risk, or when timing demand-destruction warnings, fuel-sensitive retail/CPG forecasts, or consumer-overreaction vs demand-loss calls." }, { "id": "ADW-027", "name": "Sunlight-Deficit Wellbeing", "domain": "Health/Climate", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-027", "mcp_tool": "adw.adw_027", "sample": "https://alpinedataworks.com/showcase/adw-027", "description": "The wellbeing impact of seasonal sunlight deprivation by region, tracked for mental-health and telehealth planning.", "agent_question": "Enables employers and insurers to proactively deploy mental health interventions and telehealth resources to employees in regions experiencing seasonal light deprivation.", "history_start": "1966-11-01", "history_years": 59.7, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "National Solar Radiation Database (NSRDB)", "NOAA Climate Data", "and public health statistics." ], "mcp_description": "Returns a 0-100 regional sunlight-deficit wellbeing risk score (NSRDB solar irradiance and NOAA daylight duration mapped against historical mental-health utilization; daily, history to 1966) with score, trend, confidence, and top_drivers. Call when the user asks about seasonal affective risk, winter light deprivation, or regional mental-health demand, or when timing employer wellness campaigns, EAP outreach, or telehealth staffing by region." }, { "id": "ADW-028", "name": "Brand Sentiment->Volume Gap", "domain": "Marketing", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-028", "mcp_tool": "adw.adw_028", "sample": "https://alpinedataworks.com/showcase/adw-028", "description": "The gap between brand sentiment engagement and sales volume, isolating high-engagement, low-conversion campaigns.", "agent_question": "Identify marketing inefficiencies by isolating high-engagement, low-conversion campaigns to optimize ad spend allocation.", "history_start": "1995-12-01", "history_years": 30.6, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (RSAFS, UMCSENT)" ], "mcp_description": "Returns a 0-100 monthly brand sentiment-to-sales-volume gap score (UMich consumer sentiment MoM vs FRED retail sales MoM, percentile-ranked over 36 months) with gap_type (hype-trap vs undervalued-utility), trend, confidence, and top_drivers. Call when the user asks about marketing efficiency, high-engagement low-conversion campaigns, consumer hype vs actual spending, or brand buzz outpacing sales, or when timing shifts between upper-funnel awareness and performance ad spend." }, { "id": "ADW-029", "name": "Labor-Adjacent Capacity", "domain": "Workforce", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-029", "mcp_tool": "adw.adw_029", "sample": "https://alpinedataworks.com/showcase/adw-029", "description": "The supply of contractor and external labor capacity available to absorb upcoming quarterly demand.", "agent_question": "Enables enterprises to make data-driven decisions on whether to expand headcount or engage external contractors for upcoming quarterly demand.", "history_start": "1993-12-01", "history_years": 32.6, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Bureau of Labor Statistics", "LinkedIn Economic Graph", "Glassdoor", "and internal HRIS transaction logs." ], "mcp_description": "Returns a 0-100 labor-adjacent capacity score (daily cost-differential between permanent hiring and contingent staffing, from BLS data, LinkedIn Economic Graph, Glassdoor wage indices, and internal HRIS hiring velocity and utilization) with trend, confidence, and top_drivers. Call when the user asks about contractor availability, hire-vs-contract tradeoffs, or staffing costs, or when timing headcount expansion versus contingent staffing for upcoming quarterly demand." }, { "id": "ADW-030", "name": "Climate Adaptation Capex", "domain": "Climate/Risk", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-030", "mcp_tool": "adw.adw_030", "sample": "https://alpinedataworks.com/showcase/adw-030", "description": "Quantified physical climate-risk exposure, tracked to prioritize climate-adaptation capital expenditure.", "agent_question": "Enable organizations to prioritize and allocate capital expenditure for climate resilience projects based on quantified physical risk exposure.", "history_start": "1985-12-31", "history_years": 40.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "NOAA National Centers for Environmental Information", "USGS Flood Hazard Mapper", "World Bank Climate Change Knowledge Portal" ], "mcp_description": "Returns a 0-100 climate-adaptation capex priority score (geospatial flood, wildfire, and heat hazard data from NOAA NCEI, USGS, and the World Bank, combined with asset location and value into a risk-adjusted ROI per intervention) with score, trend, confidence, and top_drivers. Call when the user asks about physical climate risk, facility resilience, flood or heat exposure, or adaptation ROI, or when timing capital allocation across climate-resilience projects." }, { "id": "ADW-031", "name": "Digital Infrastructure Load", "domain": "Tech/Infra", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-031", "mcp_tool": "adw.adw_031", "sample": "https://alpinedataworks.com/showcase/adw-031", "description": "The load on digital infrastructure, tracking demand against capacity to flag outage risk at peaks.", "agent_question": "Enables IT leaders to forecast infrastructure capacity needs and prevent service outages during peak demand periods.", "history_start": "2004-11-01", "history_years": 21.7, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (PCU518210518210, IPG2211S)" ], "mcp_description": "Returns a 0-100 digital infrastructure load index (monthly FRED series; YoY z-scores: electricity generation 60% + data-processing PPI 40%; >70=high stress) with score, trend, load_level, composite_z_score, and driver YoY rates. Call when the user asks about data center demand, cloud capacity strain, compute cost pressure, or infrastructure buildout, or when timing capacity expansion, reserved-instance purchases, or auto-scaling budgets to prevent outages during peak demand." }, { "id": "ADW-046", "name": "Corporate Credit-Spread Stress Index", "domain": "Financial/Credit", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-046", "mcp_tool": "adw.adw_046", "sample": "https://alpinedataworks.com/showcase/adw-046", "description": "Composite z-score of IG (BAA10Y) and HY (BAMLH0A0HYM2) spreads. High score = wide spreads, elevated credit stress.", "agent_question": "Are corporate credit spreads signaling elevated default risk right now?", "history_start": "1953-06-30", "history_years": 73.0, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (BAA10Y, BAMLH0A0HYM2)" ], "mcp_description": "Returns a 0-100 corporate credit-spread stress score (Baa spread and high-yield OAS from FRED, equal-weight z-scores vs a trailing 130-observation window, 50=neutral, monthly since 1953) with trend, confidence, top_drivers, spread_stress_label, baa_spread_pct, hy_oas_bp, and composite_z. Call when the user asks about credit spreads, corporate default risk, high-yield stress, or bond market risk, or when timing high-yield allocation cuts, credit de-risking, or fixed-income hedging." }, { "id": "ADW-053", "name": "Inflation-Expectations Gap Index", "domain": "Financial/Macro", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-053", "mcp_tool": "adw.adw_053", "sample": "https://alpinedataworks.com/showcase/adw-053", "description": "Divergence between 10-year breakeven inflation (T10YIE) and realized core CPI YoY. High score = expectations well above realized (overheating bias).", "agent_question": "Are market inflation expectations running above or below realized core CPI?", "history_start": "2006-12-29", "history_years": 19.5, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (T10YIE, CPILFESL)" ], "mcp_description": "Returns a 0-100 inflation-expectations gap score (10-year breakeven T10YIE minus realized core CPI YoY, FRED, z-scored vs trailing 36-month divergence; >50 = expectations above realized) with trend, confidence, gap_label, breakeven_inflation_pct, core_cpi_yoy_pct, divergence_pct, divergence_z. Call when the user asks about market inflation expectations vs realized CPI, breakevens, TIPS, or Fed credibility, or when timing TIPS-vs-nominal Treasury rebalancing or inflation-hedge positioning." }, { "id": "ADW-054", "name": "Yield-Curve Inversion Signal", "domain": "Financial/Rates", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-054", "mcp_tool": "adw.adw_054", "sample": "https://alpinedataworks.com/showcase/adw-054", "description": "Composite inversion depth score from T10Y2Y and T10Y3M spreads. High score = deep inversion historically associated with recession risk.", "agent_question": "How deep is the current yield-curve inversion and is it deepening?", "history_start": "1980-05-30", "history_years": 46.1, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (T10Y2Y, T10Y3M)" ], "mcp_description": "Returns a 0-100 yield-curve inversion signal (FRED T10Y2Y and T10Y3M spreads negated, z-scored vs a 130-obs trailing window since 1980; 50=neutral, >50=more inverted than historical average) with trend, confidence, inversion_depth_label, raw spreads, and composite_z. Call when the user asks about yield-curve inversion, 10y-2y or 10y-3m Treasury spreads, curve flattening/steepening, or recession risk, or when timing credit de-risking, duration, or cash-allocation decisions." }, { "id": "ADW-055", "name": "Dollar-Strength Index", "domain": "Financial/FX", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-055", "mcp_tool": "adw.adw_055", "sample": "https://alpinedataworks.com/showcase/adw-055", "description": "Level + momentum z-score of the broad trade-weighted USD index (DTWEXBGS). High score = strong/strengthening USD.", "agent_question": "Is the US dollar strengthening or weakening vs its historical range?", "history_start": "2009-12-31", "history_years": 16.5, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (DTWEXBGS)" ], "mcp_description": "Returns a 0-100 US dollar strength score (composite z of FRED broad trade-weighted index DTWEXBGS: level 60%, 30-day momentum 40%; 50=neutral, higher=stronger; monthly, 16.5yr history) with trend, confidence, top drivers, strength_label, latest index, 30-day momentum %, and composite z. Call when the user asks whether the dollar is strengthening or weakening, about USD/FX/exchange-rate/currency moves, or when timing FX hedges, hedge tenors on foreign payables, or import/export pricing." }, { "id": "ADW-056", "name": "Consumer Savings-Rate Stress Index", "domain": "Consumer/Macro", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-056", "mcp_tool": "adw.adw_056", "sample": "https://alpinedataworks.com/showcase/adw-056", "description": "Inverted z-score of the personal saving rate (PSAVERT). High score = low/falling saving = elevated spending fragility and default risk.", "agent_question": "Are US consumers running down savings at an alarming rate?", "history_start": "1962-12-01", "history_years": 63.6, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (PSAVERT)" ], "mcp_description": "Returns a 0-100 US consumer savings-rate stress index (FRED PSAVERT personal saving rate, inverted and z-scored vs a trailing 36-month window; >50 = below-average saving, monthly since 1962) with score, trend, confidence, saving_rate_pct, 3-month change, and top drivers. Call when the user asks about consumer savings drawdown, household financial cushion, spending sustainability, or recession stress, or when timing consumer-credit underwriting, lending limits, or debt-to-income cutoffs." }, { "id": "ADW-032", "name": "Regulatory Compliance Risk", "domain": "Compliance", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-032", "mcp_tool": "adw.adw_032", "sample": "https://alpinedataworks.com/showcase/adw-032", "description": "Regulatory compliance risk exposure across jurisdictions, scored to flag rising fine and disruption risk.", "agent_question": "Enables organizations to proactively identify and mitigate regulatory exposure across multiple jurisdictions to avoid fines and operational disruptions.", "history_start": "1997-11-28", "history_years": 28.6, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Official gazettes", "regulatory agency publications", "and public enforcement databases (e.g.", "SEC" ], "mcp_description": "Returns a 0-100 regulatory compliance risk score by jurisdiction and domain area (NLP over official gazettes, agency publications, and public enforcement databases, weighted by violation frequency and severity) with score, trend, confidence, and top_drivers. Call when the user asks about regulatory exposure, enforcement risk, fines, or compliance posture in a market, or when timing market entry, vendor onboarding, or compliance-budget decisions. Daily refresh; history to 1997." }, { "id": "ADW-033", "name": "Supply Chain Diversification", "domain": "Logistics", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-033", "mcp_tool": "adw.adw_033", "sample": "https://alpinedataworks.com/showcase/adw-033", "description": "Supply-chain concentration risk across suppliers, regions, and transport modes, scored to guide diversification.", "agent_question": "Enable logistics buyers to quantify and mitigate concentration risk by identifying over-reliance on specific suppliers, regions, or transport modes.", "history_start": "1996-12-01", "history_years": 29.6, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "ImportGenius", "Panjiva", "UN Comtrade", "World Bank Logistics Performance Index" ], "mcp_description": "Returns a 0-100 supply-chain diversification score (HHI concentration across supplier spend, sourcing regions, and transport modes; ImportGenius, Panjiva, UN Comtrade, World Bank LPI) with trend, confidence, and top_drivers. Call when the user asks about supplier concentration, single-source risk, regional exposure, or transport-mode dependence, or when timing dual-sourcing, nearshoring, or carrier-diversification decisions. Daily refresh; history to 1996." }, { "id": "ADW-201", "name": "Port-Congestion Lead Time", "domain": "Logistics", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-201", "mcp_tool": "adw.adw_201", "sample": "https://alpinedataworks.com/showcase/adw-201", "description": "Port-congestion-driven lead-time extension, tracked so shippers can size inventory buffers against delays.", "agent_question": "Enable shippers to determine if current inventory buffers are sufficient to absorb port delays, preventing stockouts or excess holding costs.", "history_start": "1922-12-01", "history_years": 103.6, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Port authority AIS data", "terminal operator public dashboards", "and global shipping line schedules." ], "mcp_description": "Returns a 0-100 port-congestion lead-time variance score (daily probabilistic delay distribution built from port-authority AIS vessel arrivals, terminal dwell times, and crane-productivity metrics) with trend, confidence, and top_drivers. Call when the user asks about port congestion, shipping delays, container lead times, or inventory buffer adequacy, or when timing safety-stock changes, expedited-freight bookings, or purchase-order pull-forwards." }, { "id": "ADW-202", "name": "SMB Credit-Default Proxy", "domain": "Finance", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-202", "mcp_tool": "adw.adw_202", "sample": "https://alpinedataworks.com/showcase/adw-202", "description": "A credit-default risk proxy for small and mid-sized businesses that lack public financials or credit-bureau histories.", "agent_question": "Enable lenders and suppliers to assess credit default risk for small and medium-sized businesses that lack public financial disclosures or credit bureau histories.", "history_start": "1950-12-01", "history_years": 75.6, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Public court records", "utility payment registries", "business registration databases", "and open-source financial news feeds." ], "mcp_description": "Returns a 0-100 credit-default risk proxy for SMBs that lack public financials or credit-bureau histories (logistic regression over utility payment records, court filings, business registrations, and bank-transaction aggregates; daily refresh) with score, trend, confidence, and top_drivers. Call when the user asks about SMB creditworthiness, counterparty or supplier default risk, or thin-file borrowers, or when timing net-terms approvals, credit-line reviews, or a move to prepayment." }, { "id": "ADW-204", "name": "Shelf-Share Velocity", "domain": "Retail/Logistics", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-204", "mcp_tool": "adw.adw_204", "sample": "https://alpinedataworks.com/showcase/adw-204", "description": "The velocity of shelf-share gains and losses, benchmarking product distribution efficiency against market leaders.", "agent_question": "Enable retailers and CPG brands to benchmark their product distribution efficiency against market leaders to identify untapped shelf-space opportunities.", "history_start": "1995-12-01", "history_years": 30.6, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "NielsenIQ", "IRI", "or Statista retail sales data" ], "mcp_description": "Returns a 0-100 shelf-share velocity score benchmarking distribution efficiency against category leaders (POS volumes and inventory turnover by SKU and store, normalized to category sales; NielsenIQ/IRI data, daily, history to 1995) with score, trend, confidence, and top_drivers. Call when the user asks about shelf share, distribution velocity, or SKU benchmarking, or when timing planogram resets, trade-promotion spend, or delist decisions." }, { "id": "ADW-205", "name": "3-Ps Mix Index", "domain": "Marketing", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-205", "mcp_tool": "adw.adw_205", "sample": "https://alpinedataworks.com/showcase/adw-205", "description": "The combined product, price, and promotion mix performance by consumer segment, scored for sales lift.", "agent_question": "Enables marketers to identify the optimal product, price, and promotional mix for specific consumer segments to maximize sales lift and market share.", "history_start": "1962-12-01", "history_years": 63.6, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "NielsenIQ/IRI retail scanner data", "consumer panel data", "and public demographic census data." ], "mcp_description": "Returns a 0-100 marketing-mix optimization score by consumer segment (composite of sales volume, price elasticity, and promotion frequency from NielsenIQ/IRI scanner and panel data, daily, history to 1962) with score, trend, confidence, and top_drivers. Call when the user asks about product-price-promotion mix, segment targeting, promo effectiveness, or sales lift, or when timing trade-promotion budgets or price changes." }, { "id": "ADW-037", "name": "Wage-Price Spiral Risk", "domain": "Labor/Macro", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-037", "mcp_tool": "adw.adw_037", "sample": "https://alpinedataworks.com/showcase/adw-037", "description": "Quantifies the self-reinforcing cycle between wage growth and core inflation. High scores signal rising spiral risk; low scores indicate that wages and prices are diverging or decelerating together.", "agent_question": "How elevated is the feedback loop between wage growth and consumer price inflation right now?", "history_start": "2010-02-01", "history_years": 16.4, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (CES0500000003, CPILFESL)" ], "mcp_description": "Returns a 0-100 wage-price spiral risk score (YoY avg hourly earnings + YoY core CPI, FRED, equal-weight z-scores vs 36-month window; >50 = rising risk, monthly) with trend, wages_yoy_pct, core_cpi_yoy_pct, and wages_z/cpi_z to tell wage-led from CPI-led moves. Call when the user asks about wage-price spirals, wage growth vs inflation, sticky core inflation, or labor-cost pass-through, or when timing rate-hike exposure, bond duration shifts, or nominal-vs-TIPS allocation." }, { "id": "ADW-038", "name": "Freight & Logistics Cost Index", "domain": "Supply Chain/Macro", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-038", "mcp_tool": "adw.adw_038", "sample": "https://alpinedataworks.com/showcase/adw-038", "description": "Composite of truck freight PPI and diesel retail prices to gauge supply-chain cost headwinds. High scores signal elevated logistics costs compressing margins; low scores indicate easing.", "agent_question": "How much pressure are freight and diesel costs placing on supply chains and margins right now?", "history_start": "2007-11-26", "history_years": 18.6, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (PCU484121484121, GASDESW)" ], "mcp_description": "Returns a 0-100 US freight and logistics cost pressure index (truck freight PPI YoY plus diesel 4-week change, weighted z-scores vs a 36-month window; FRED, monthly since 2007) with score, trend, confidence, top_drivers, and component z-scores. Call when the user asks about freight rates, trucking costs, diesel prices, shipping cost inflation, or supply-chain margin pressure, or when timing carrier contract renegotiations, fuel surcharge requests, or margin-risk alerts." }, { "id": "ADW-040", "name": "Healthcare Cost Inflation Index", "domain": "Healthcare/Macro", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-040", "mcp_tool": "adw.adw_040", "sample": "https://alpinedataworks.com/showcase/adw-040", "description": "Measures the spread between medical-care CPI and core CPI. High scores indicate healthcare costs accelerating well above the core basket; low scores suggest healthcare deflation or relative moderation.", "agent_question": "Is healthcare inflation running meaningfully above or below general core inflation right now?", "history_start": "1960-12-01", "history_years": 65.6, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (CPIMEDSL, CPILFESL)" ], "mcp_description": "Returns a 0-100 healthcare cost inflation index (monthly FRED medical CPI vs core CPI year-over-year spread, z-scored over a 36-month window) with score, trend, confidence, medical_cpi_yoy_pct, core_cpi_yoy_pct, healthcare_spread_pct, and top drivers. Call when the user asks about healthcare inflation, medical cost trends, or health costs versus core inflation, or when timing employer health-plan renewals, premium and benefits renegotiation, or healthcare budgeting." }, { "id": "ADW-042", "name": "Auto-Market Affordability Index", "domain": "Auto/Consumer", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-042", "mcp_tool": "adw.adw_042", "sample": "https://alpinedataworks.com/showcase/adw-042", "description": "Combines new-vehicle price inflation with 48-month auto loan rates to gauge consumer affordability. High scores mean vehicles are increasingly unaffordable; low scores signal improving purchasing conditions.", "agent_question": "How affordable is purchasing a new vehicle today relative to recent history?", "history_start": "1983-11-01", "history_years": 42.7, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (CUSR0000SETA01, TERMCBAUTO48NS)" ], "mcp_description": "Returns a 0-100 auto affordability score (New Vehicle CPI YoY + 48-month auto loan rate z-scores, 0.6/0.4 weighted vs 36-month window, FRED monthly since 1983) with trend, confidence, top_drivers, affordability_label, vehicle_price_z, auto_rate_z, and composite_z. Call when the user asks about car affordability, new vehicle prices, auto loan rates, or consumer auto financing costs, or when timing auto lending credit tightening, underwriting thresholds, or vehicle purchase decisions." }, { "id": "ADW-044", "name": "Food-Price Pressure Index", "domain": "Agriculture/Consumer", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-044", "mcp_tool": "adw.adw_044", "sample": "https://alpinedataworks.com/showcase/adw-044", "description": "Combines consumer food CPI with farm-level PPI to capture price pressure propagating from fields to shelves. High scores indicate elevated food inflation; low scores suggest easing.", "agent_question": "How much upward price pressure is the food supply chain exerting on consumers right now?", "history_start": "1950-12-01", "history_years": 75.6, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (CPIUFDSL, WPU012)" ], "mcp_description": "Returns a 0-100 food-price pressure score (FRED Food CPI + Farm Products PPI YoY, 0.6/0.4-weighted z-scores vs a 36-month window; monthly since 1950) with trend, confidence, pressure_level, top_drivers, and component YoY/z fields. Call when the user asks about food inflation, grocery or agricultural commodity prices, farm-cost pass-through, or consumer food-price pressure, or when timing forward contracts, grain-linked procurement, or retail pricing moves." }, { "id": "ADW-045", "name": "Labor-Market Tightness Index", "domain": "Labor/Macro", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-045", "mcp_tool": "adw.adw_045", "sample": "https://alpinedataworks.com/showcase/adw-045", "description": "Tracks the ratio of JOLTS job openings to unemployed workers and z-scores it against a 36-month trailing window. High scores indicate a historically tight labor market; low scores signal slack.", "agent_question": "How tight is the US labor market \u2014 are there meaningfully more job openings than unemployed workers?", "history_start": "2001-02-01", "history_years": 25.4, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (JTSJOL, UNEMPLOY)" ], "mcp_description": "Returns a 0-100 US labor-market tightness score (monthly JOLTS job openings \u00f7 unemployed from FRED, z-scored vs a 36-month window; 50=neutral, higher=tighter) with trend, confidence, tightness_label, openings_to_unemployed_ratio, and raw openings/unemployed counts. Call when the user asks about labor market tightness, worker shortages, hiring difficulty, job openings vs unemployment, or wage pressure, or when timing salary-band reviews, compensation benchmarking, or hiring plans." }, { "id": "ADW-047", "name": "Money-Supply Momentum Index", "domain": "Monetary/Macro", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-047", "mcp_tool": "adw.adw_047", "sample": "https://alpinedataworks.com/showcase/adw-047", "description": "Combines M2 52-week growth with M2 velocity to gauge the monetary impulse to economic activity. High scores signal expansionary money conditions; low scores indicate monetary contraction.", "agent_question": "Is M2 money supply growth above or below its historical trend, and how does velocity amplify or dampen that signal?", "history_start": "1962-12-01", "history_years": 63.6, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (M2SL, M2V)" ], "mcp_description": "Returns a 0-100 money-supply momentum index (FRED M2 YoY growth and M2 velocity z-scores, equal-weight composite vs trailing 36-month window, monthly since 1962) with score, trend, monetary_impulse_label, m2_yoy_pct, m2v_level, component z-scores, and top_drivers. Call when the user asks about M2 money supply growth, liquidity, money velocity, or monetary tightening/easing regimes, or when timing duration positioning or portfolio rebalancing around monetary-policy shifts." }, { "id": "ADW-049", "name": "Productivity Trend Index", "domain": "Labor/Macro", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-049", "mcp_tool": "adw.adw_049", "sample": "https://alpinedataworks.com/showcase/adw-049", "description": "Measures the balance between nonfarm productivity growth and unit labor cost growth. High scores indicate productivity is outrunning costs (margin-positive); low scores signal a cost squeeze or stagflation risk.", "agent_question": "Is nonfarm business productivity outpacing unit labor cost growth \u2014 or is the cost squeeze tightening?", "history_start": "1949-12-31", "history_years": 76.5, "product_class": "time-series", "tier": "Gold", "refresh": "quarterly", "source_apis": [ "FRED (OPHNFB, ULCNFB)" ], "mcp_description": "Returns a 0-100 US productivity-vs-labor-cost index (FRED nonfarm output per hour OPHNFB vs unit labor costs ULCNFB, z-score spread over a 36-quarter window, quarterly since 1949; >50 = productivity leading) with score, trend, confidence, top_drivers, productivity_yoy_pct, ulc_yoy_pct, and z-scores. Call when the user asks about labor productivity, unit labor costs, wage or cost squeeze, or margin pressure, or when timing earnings-growth and margin assumptions in sector models." }, { "id": "ADW-050", "name": "Mortgage-Market Health Index", "domain": "Real Estate/Financial", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-050", "mcp_tool": "adw.adw_050", "sample": "https://alpinedataworks.com/showcase/adw-050", "description": "Combines the 30-year fixed mortgage rate with single-family delinquency rates to measure overall mortgage market health. High scores indicate stress; low scores signal a healthy mortgage market.", "agent_question": "How stressed is the residential mortgage market \u2014 combining rate levels with delinquency trends?", "history_start": "1995-12-29", "history_years": 30.5, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (MORTGAGE30US, DRSFRMACBS)" ], "mcp_description": "Returns a 0-100 mortgage-market stress score (equal-weight z-scores of FRED 30-year mortgage rates and single-family serious delinquencies, monthly since 1995; higher = more stressed) with trend, confidence, health_label, top_drivers, and rate/delinquency percentages. Call when the user asks about mortgage market health, mortgage rates, delinquency trends, or housing credit stress, or when timing LTV/underwriting tightening, origination limits, or real-estate credit exposure." }, { "id": "ADW-052", "name": "Commercial Real-Estate Stress Index", "domain": "Real Estate/Financial", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-052", "mcp_tool": "adw.adw_052", "sample": "https://alpinedataworks.com/showcase/adw-052", "description": "Tracks CRE loan delinquency rates (ex-farm) with a 4-quarter momentum supplement to detect rising credit stress in commercial property markets. High scores signal elevated distress; low scores indicate benign conditions.", "agent_question": "How elevated is stress in the commercial real estate lending market relative to historical norms?", "history_start": "1992-06-30", "history_years": 34.0, "product_class": "time-series", "tier": "Gold", "refresh": "quarterly", "source_apis": [ "FRED (DRCRELEXFACBS)" ], "mcp_description": "Returns a 0-100 commercial real estate lending stress score (FRED bank CRE loan delinquency rate, 70/30 level-plus-momentum z-score blend, quarterly since 1992) with stress_label, trend, confidence, top_drivers, delinquency rate, and momentum/composite z-scores. Call when the user asks about CRE stress, commercial real estate delinquencies, bank credit quality, or property lending risk, or when timing CRE loan-concentration reviews, credit-committee escalations, or exposure decisions." }, { "id": "ADW-067", "name": "Air-Travel Recovery Index", "domain": "Travel/Transport", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-067", "mcp_tool": "adw.adw_067", "sample": "https://alpinedataworks.com/showcase/adw-067", "description": "Measures how far US daily TSA checkpoint throughput has recovered relative to a trailing-year baseline. High score = at or above baseline; low score = well below.", "agent_question": "How recovered is US air travel vs its prior-year baseline?", "history_start": "2019-03-03", "history_years": 7.4, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "TSA Passenger Volumes (tsa.gov, keyless)" ], "mcp_description": "Returns a 0-100 US air-travel recovery index (TSA checkpoint passenger volumes, tsa.gov keyless; 30-day mean vs 365-day baseline, weekly since 2019) with score, trend, confidence, top_drivers, recovery_ratio, current/baseline means, latest daily count. Call when the user asks about air travel demand, TSA throughput, passenger volumes, airport traffic, or travel recovery, or when timing dynamic pricing and promotions for hospitality or airport-adjacent retail." }, { "id": "ADW-034", "name": "Tourism-Demand Pulse", "domain": "Travel/Transport", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-034", "mcp_tool": "adw.adw_034", "sample": "https://alpinedataworks.com/showcase/adw-034", "description": "Captures the absolute throughput level percentile and 30-day momentum percentile of US TSA checkpoint data, providing a dual-lens view of tourism demand. Different angle from ADW-067 (level+momentum vs pure recovery).", "agent_question": "What is the current level and momentum of US tourism demand?", "history_start": "2019-03-03", "history_years": 7.4, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "TSA Passenger Volumes (tsa.gov, keyless)" ], "mcp_description": "Returns a 0-100 US tourism-demand pulse (TSA checkpoint passenger volumes, weekly; blends 30-day throughput level vs 7-year history with 30d-vs-prior-30d momentum) with score, trend, confidence, top_drivers, throughput_level_pct, momentum_30d_pct, and momentum_ratio. Call when the user asks about US travel demand, air passenger traffic, airport throughput, tourism recovery, or hospitality occupancy, or when timing hotel/airline dynamic pricing or discount-inventory decisions." }, { "id": "ADW-076", "name": "Climate-Disaster Cost Trend", "domain": "Climate/Risk", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-076", "mcp_tool": "adw.adw_076", "sample": "https://alpinedataworks.com/showcase/adw-076", "description": "Tracks annual CPI-adjusted US billion-dollar weather and climate disaster costs relative to the 45-year NOAA NCEI historical record. High score = costs in the upper tail; useful for insurance pricing and ESG risk disclosures.", "agent_question": "Are US climate-disaster costs trending above historical norms?", "history_start": "1985-12-31", "history_years": 40.5, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "NOAA NCEI Billion-Dollar Weather & Climate Disasters (ncei.noaa.gov, keyless)" ], "mcp_description": "Returns a 0-100 US climate-disaster cost-trend score (z-score of latest annual billion-dollar-disaster costs vs 1980-present NOAA NCEI history) with trend, confidence, top_drivers, cost z-score, percentile rank, and latest vs trailing-10yr mean cost ($B). Call when the user asks about climate disaster costs, extreme-weather losses, hurricane/wildfire/flood damage, or catastrophe costs vs historical norms, or when timing insurance re-pricing, cat-treaty reviews, or ESG climate-risk escalations." }, { "id": "ADW-071", "name": "Stablecoin-Flow Momentum", "domain": "Market/Crypto", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-071", "mcp_tool": "adw.adw_071", "sample": "https://alpinedataworks.com/showcase/adw-071", "description": "Measures 30-day USD-pegged stablecoin supply change momentum ranked against the full ~8.5yr daily history. High score = strong net inflow into crypto ecosystem; useful for macro-crypto regime detection.", "agent_question": "Is stablecoin capital flowing into or out of crypto?", "history_start": "2018-01-08", "history_years": 8.5, "product_class": "time-series", "tier": "Gold", "refresh": "hourly", "source_apis": [ "DeFiLlama Stablecoin Charts (stablecoins.llama.fi, keyless)" ], "mcp_description": "Returns a 0-100 stablecoin-flow momentum score (30-day change in total stablecoin supply from DeFiLlama, percentile-ranked against 8.5 years of daily history; low = supply contracting, high = expanding; hourly) with trend, confidence, top_drivers, supply in $B, and 30d change %. Call when the user asks about stablecoin inflows/outflows, crypto liquidity, dry powder, or risk-on/risk-off rotation, or when timing DeFi/yield-farming exposure or crypto drawdown risk." }, { "id": "ADW-072", "name": "DeFi-Activity Breadth", "domain": "Market/Crypto", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-072", "mcp_tool": "adw.adw_072", "sample": "https://alpinedataworks.com/showcase/adw-072", "description": "Counts chains with TVL above a $100M meaningful-liquidity floor across the top-20 chains, then ranks that breadth count against the full daily history. High score = broadly distributed DeFi (healthy); low = concentrated.", "agent_question": "How broadly distributed is DeFi liquidity across chains?", "history_start": "2017-10-26", "history_years": 8.7, "product_class": "time-series", "tier": "Gold", "refresh": "hourly", "source_apis": [ "DeFiLlama Chains API (api.llama.fi, keyless)" ], "mcp_description": "Returns a 0-100 DeFi liquidity breadth score (count of top-20 chains with TVL above $100M, DeFiLlama data, percentile-ranked vs 8.7 years of daily history, hourly refresh) with trend, confidence, top drivers, chains-above-floor count, 30-day mean/change, and percentile rank. Call when the user asks about DeFi health, cross-chain TVL distribution, multichain liquidity concentration, or ecosystem breadth, or when timing cross-chain LP deployment versus consolidating to a single chain." }, { "id": "ADW-073", "name": "GitHub-Language Momentum", "domain": "Tech/Software", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-073", "mcp_tool": "adw.adw_073", "sample": "https://alpinedataworks.com/showcase/adw-073", "description": "Aggregates repo-creation count in the past 30 days across TypeScript, Python, Rust, and Go via the GitHub Search API. Forward-accumulating snapshot \u2014 each call yields today's point; build a series by persisting daily. Useful for tech-trend and developer tooling GTM timing.", "agent_question": "How strong is developer momentum in TypeScript, Python, Rust, and Go?", "history_start": "2016-03-31", "history_years": 10.3, "product_class": "time-series", "tier": "Gold", "refresh": "hourly", "source_apis": [ "GitHub Search API (api.github.com, keyless, 10 req/min unauthenticated)" ], "mcp_description": "Returns a 0-100 developer momentum score for TypeScript, Python, Rust, and Go (30-day new-repo creation via GitHub Search API, normalized to a 100k ceiling; hourly, history since 2016) with trend, confidence, top_drivers, per_language breakdown, and total_new_repos_30d. Call when the user asks about programming language popularity, adoption trends, developer ecosystem growth, or open-source activity, or when timing devtools GTM, developer-marketing spend, or language-community sponsorships." }, { "id": "ADW-110", "name": "Crypto Whale-Flow Pressure", "domain": "Market/Crypto", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-110", "mcp_tool": "adw.adw_110", "sample": "https://alpinedataworks.com/showcase/adw-110", "description": "On-chain whale accumulation/distribution + sentiment composite.", "agent_question": "Are large holders accumulating or distributing BTC?", "history_start": "1962-12-01", "history_years": 63.6, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "Glassnode (docs.glassnode.com)" ], "mcp_description": "Returns a 0-100 Bitcoin whale-flow pressure score (weekly composite z-score of large-holder accumulation vs. distribution; above 65 signals accumulation, below 40 distribution) with trend, percentile, top_drivers, confidence, and source_lineage. Call when the user asks about BTC whales, large holders, smart money, on-chain flows, or whether whales are buying or selling, or when timing BTC allocation shifts, crypto rebalancing, or funding-rate position adjustments." }, { "id": "ADW-112", "name": "Metals-Complex Stress", "domain": "Mining/Metals", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-112", "mcp_tool": "adw.adw_112", "sample": "https://alpinedataworks.com/showcase/adw-112", "description": "Gold vol + momentum + gold/silver ratio.", "agent_question": "Is the metals complex calm or stressed?", "history_start": "2006-08-31", "history_years": 19.9, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "FRED (https://fred.stlouisfed.org)" ], "mcp_description": "Returns a 0-100 metals-complex stress score (weekly composite z-score of gold volatility, momentum, and the gold/silver ratio; ~20yr history since 2006) with an IOM carrying top_drivers and source_lineage. Call when the user asks about gold, silver, precious-metals stress, safe-haven conditions, or mining/metals risk, or when timing gold hedge sizing (stress above 70) versus releasing hedges for risk-on allocation (calm below 40)." }, { "id": "ADW-116", "name": "Live Air-Traffic Density", "domain": "Aviation", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-116", "mcp_tool": "adw.adw_116", "sample": "https://alpinedataworks.com/showcase/adw-116", "description": "OpenSky airborne/altitude/US-share composite.", "agent_question": "How dense is live US air traffic?", "history_start": "2003-12-01", "history_years": 22.6, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "OpenSky Network (opensky-network.org/api)" ], "mcp_description": "Returns a 0-100 US live air-traffic density score (composite z-score of OpenSky airborne aircraft count, altitude mix, and US airspace share; weekly, history since 2003) as an IOM with source_lineage and methodology_version for audit trails. Call when the user asks about air traffic volume, flight activity, airspace congestion, aviation demand, or airline travel trends, or when timing demand-shock alerts for airline-sector equity models." }, { "id": "ADW-117", "name": "Travel-Demand Index", "domain": "Tourism", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-117", "mcp_tool": "adw.adw_117", "sample": "https://alpinedataworks.com/showcase/adw-117", "description": "Advisory levels + bulletin severity composite.", "agent_question": "How open/safe is global travel demand?", "history_start": "1973-12-01", "history_years": 52.6, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "EPA (www.epa.gov)" ], "mcp_description": "Returns a 0-100 travel-demand and safety-openness index (weekly composite z-score of State Department advisory levels and bulletin severity, history to 1973) with score, trend, confidence, and auditable source lineage. Call when the user asks about global travel demand, tourism outlook, travel safety, or advisory risk, or when timing hospitality dynamic pricing, forward booking inventory, or upsell campaign decisions." }, { "id": "ADW-041", "name": "Energy-Transition Demand", "domain": "Energy", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-041", "mcp_tool": "adw.adw_041", "sample": "https://alpinedataworks.com/showcase/adw-041", "description": "EIA renewable generation share + momentum.", "agent_question": "How fast is renewable share growing?", "history_start": "1975-01-31", "history_years": 51.4, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "EIA (api.eia.gov/v2)" ], "mcp_description": "Returns a 0-100 energy-transition demand score (weekly composite z-score of EIA renewable-generation share, 51-year history since 1975) with trend, percentile, confidence, and methodology_version. Call when the user asks about renewable share growth, clean energy adoption, solar/wind expansion, or decarbonization momentum, or when timing renewable-tilt ETF rebalances and clean-energy allocation shifts." }, { "id": "ADW-062", "name": "Energy-Inventory Tightness", "domain": "Energy", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-062", "mcp_tool": "adw.adw_062", "sample": "https://alpinedataworks.com/showcase/adw-062", "description": "EIA weekly crude/petroleum stocks z-score.", "agent_question": "How tight are US petroleum stocks?", "history_start": "1950-06-01", "history_years": 76.1, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "EIA (api.eia.gov/v2)" ], "mcp_description": "Returns a 0-100 US petroleum inventory tightness score (composite z-score of EIA weekly petroleum stocks, weekly refresh, history since 1950; 100 = tightest on record) with an IOM field. Call when the user asks about crude oil inventories, petroleum stocks, EIA stock draws or builds, energy supply tightness, or oil market balance, or when timing crude long holds, refinery supply contracts, or inventory-driven trade escalations." }, { "id": "ADW-075", "name": "Renewable-Capacity Growth", "domain": "Energy", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-075", "mcp_tool": "adw.adw_075", "sample": "https://alpinedataworks.com/showcase/adw-075", "description": "EIA renewable YoY momentum.", "agent_question": "How fast is renewable capacity growing?", "history_start": "1975-01-31", "history_years": 51.4, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "EIA (api.eia.gov/v2)" ], "mcp_description": "Returns a 0-100 renewable-capacity growth momentum score (composite z-score of EIA renewable capacity data, weekly, history since 1975) with percentile rank, trend, confidence, source_lineage, and methodology_version. Call when the user asks about renewable capacity growth, clean-energy buildout, solar/wind expansion, or energy transition pace, or when timing renewable infrastructure investment screening and watchlist-to-due-diligence decisions under ESG documentation mandates." }, { "id": "ADW-120", "name": "Community Health Index", "domain": "Health", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-120", "mcp_tool": "adw.adw_120", "sample": "https://alpinedataworks.com/showcase/adw-120", "description": "CDC PLACES chronic-disease composite (100=healthier).", "agent_question": "How healthy is the US population?", "history_start": "1958-12-01", "history_years": 67.6, "product_class": "time-series", "tier": "Gold", "refresh": "annual", "source_apis": [ "CDC PLACES API (https://api.cdc.gov/places)" ], "mcp_description": "Returns a 0-100 US Community Health Index (CDC PLACES chronic-disease composite z-score, 100 = healthier, annual series since 1958) with index values, vintage dates, and methodology_version. Call when the user asks about population health, chronic disease burden, community wellness, or how healthy the US is, or when timing payer market entry, actuarial risk loading, or underwriting decisions." }, { "id": "ADW-121", "name": "Behavioral-Health Stress", "domain": "Health", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-121", "mcp_tool": "adw.adw_121", "sample": "https://alpinedataworks.com/showcase/adw-121", "description": "CDC PLACES mental-distress + depression.", "agent_question": "How strained is US behavioral health?", "history_start": "1951-12-01", "history_years": 74.6, "product_class": "time-series", "tier": "Gold", "refresh": "annual", "source_apis": [ "CDC PLACES (https://places.cdc.gov/api/)" ], "mcp_description": "Returns a 0-100 US behavioral-health stress score (annual composite z-score of CDC PLACES mental-distress and depression prevalence, history to 1951) with value, confidence, and source_lineage fields to separate real signal from small-area estimation noise. Call when the user asks about mental-health strain, depression rates, psychological distress, or EAP demand, or when timing employee-assistance outreach, telehealth benefit promotion, or regional workforce wellbeing interventions." }, { "id": "ADW-122", "name": "Drug-Safety Index", "domain": "Health", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-122", "mcp_tool": "adw.adw_122", "sample": "https://alpinedataworks.com/showcase/adw-122", "description": "openFDA serious-event surge (100=safer).", "agent_question": "Is drug-adverse-event reporting surging?", "history_start": "1996-10-31", "history_years": 29.7, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "openFDA (api.fda.gov)" ], "mcp_description": "Returns a 0-100 weekly Drug-Safety Index (composite z-score of openFDA serious adverse-event reports since 1996; 100 = safer, lower = surging serious events) with score, trend, top_drivers drug categories, and methodology_version for reproducible regulatory data pulls. Call when the user asks about drug adverse events, FAERS surges, medication side effects, drug safety trends, or pharmacovigilance, or when timing safety escalations, recall monitoring, or pharma risk reviews." }, { "id": "ADW-123", "name": "Healthcare-Access Gap", "domain": "Health", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-123", "mcp_tool": "adw.adw_123", "sample": "https://alpinedataworks.com/showcase/adw-123", "description": "BRFSS uninsured+cost-barrier+no-provider.", "agent_question": "How big is the US healthcare-access gap?", "history_start": "2011-12-31", "history_years": 14.5, "product_class": "time-series", "tier": "Gold", "refresh": "annual", "source_apis": [ "CDC BRFSS Data API (https://nccd.cdc.gov/brfss2019api/)" ], "mcp_description": "Returns a 0-100 US healthcare-access gap index (composite z-score of BRFSS uninsured rates, cost-barrier-to-care prevalence, and no-usual-provider rates; annual since 2011) with top_drivers decomposition, source_lineage, and methodology_version. Call when the user asks about healthcare access gaps, uninsured populations, care affordability, provider shortages, or health equity, or when timing Medicaid network development, care-gap closure outreach, or CMS network-adequacy attestations." }, { "id": "ADW-124", "name": "Clinical-Trial Activity", "domain": "Health", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-124", "mcp_tool": "adw.adw_124", "sample": "https://alpinedataworks.com/showcase/adw-124", "description": "ClinicalTrials.gov active volume + phase + momentum.", "agent_question": "How active is the US clinical-trial pipeline?", "history_start": "2000-12-31", "history_years": 25.5, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "ClinicalTrials.gov API (https://clinicaltrials.gov/api/v2/studies)" ], "mcp_description": "Returns a 0-100 US clinical-trial pipeline activity score (composite z-score of ClinicalTrials.gov active trial volume, phase distribution, and registration momentum; weekly since 2000) with top_drivers by trial phase (late-stage Phase 3 vs early Phase 1), percentile, and methodology_version. Call when the user asks about clinical trials, drug development pipelines, biotech or pharma R&D activity, or when timing biotech sector-rotation or investment-screening decisions." }, { "id": "ADW-125", "name": "Infectious-Disease Burden", "domain": "Health", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-125", "mcp_tool": "adw.adw_125", "sample": "https://alpinedataworks.com/showcase/adw-125", "description": "CDC NNDSS multi-disease basket + YoY.", "agent_question": "How heavy is US notifiable-disease burden?", "history_start": "2020-10-31", "history_years": 5.7, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "FEC (api.open.fec.gov/v1)" ], "mcp_description": "Returns a 0-100 US infectious-disease burden score (composite z-score of CDC NNDSS notifiable-disease case counts across a multi-disease basket with year-over-year momentum) with IOM top_drivers, source_lineage, and methodology_version. Call when the user asks about notifiable-disease burden, outbreak surveillance, epidemic risk, or CDC case-count trends, or when timing group-health underwriting, actuarial re-pricing, or seasonal-versus-structural disease signals." }, { "id": "ADW-126", "name": "Federal-Spending Momentum", "domain": "Public/Gov", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-126", "mcp_tool": "adw.adw_126", "sample": "https://alpinedataworks.com/showcase/adw-126", "description": "USAspending award/obligation momentum.", "agent_question": "Is federal spending accelerating?", "history_start": "1949-12-31", "history_years": 76.5, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "USAspending.gov (api.usaspending.gov/api/v2)" ], "mcp_description": "Returns a 0-100 federal-spending momentum score (weekly composite z-score of USAspending award and obligation flows, history to 1949) with score, trend direction, source lineage, and methodology version. Call when the user asks about federal spending acceleration, government outlays, budget momentum, or contract obligations, or when timing govcon business development, teaming outreach, or bid/no-bid decisions." }, { "id": "ADW-127", "name": "Regulatory-Activity Index", "domain": "Public/Gov", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-127", "mcp_tool": "adw.adw_127", "sample": "https://alpinedataworks.com/showcase/adw-127", "description": "Federal Register rule/notice volume + trend.", "agent_question": "How active is federal rulemaking?", "history_start": "1995-06-01", "history_years": 31.1, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "Federal Register API (https://www.federalregister.gov/api/v1)" ], "mcp_description": "Returns a 0-100 federal regulatory-activity index (composite z-score of Federal Register rule/notice volume and trend, weekly, 31-year history) with score, trend, and pinned methodology_version. Call when the user asks about federal rulemaking pace, regulation volume, Federal Register activity, agency rules, or compliance workload, or when timing regulatory-change monitoring, compliance-impact briefs, or alert gating on rising rulemaking." }, { "id": "ADW-128", "name": "Research-Output Momentum", "domain": "Innovation", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-128", "mcp_tool": "adw.adw_128", "sample": "https://alpinedataworks.com/showcase/adw-128", "description": "OpenAlex US publication momentum (patents proxy).", "agent_question": "Is US research output accelerating?", "history_start": "1983-03-31", "history_years": 43.3, "product_class": "time-series", "tier": "Gold", "refresh": "annual", "source_apis": [ "OpenAlex API (api.openalex.org)" ], "mcp_description": "Returns a 0-100 US research-output momentum score (composite z-score of OpenAlex publication trends, a patent-pipeline proxy; annual history to 1983) with the IOM index value; below 50 means output contracting vs. its own history. Call when the user asks about US research acceleration, scientific publications, R&D output, innovation or patent pipeline health, or when timing deep-tech investment screening, pre-seed portfolio weighting, or commercialization bets." }, { "id": "ADW-129", "name": "Seismic-Risk Pulse", "domain": "Geophysical", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-129", "mcp_tool": "adw.adw_129", "sample": "https://alpinedataworks.com/showcase/adw-129", "description": "USGS M4.5+ energy + count + shallow share.", "agent_question": "How seismically active is the world now?", "history_start": "2016-01-08", "history_years": 10.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "USGS (usgs.gov)" ], "mcp_description": "Returns a 0-100 global seismic-activity index (daily composite z-score of USGS M4.5+ earthquake energy, event count, and shallow-focus share; 10.5-year history) with score, percentile, trend, top_drivers, and source_lineage. Call when the user asks about earthquake activity, seismic risk, tremors, or geophysical hazards worldwide, or when timing disruption alerts for ports, pipelines, mines, or insured assets near active epicenters." }, { "id": "ADW-130", "name": "Space-Weather Geomagnetic Risk", "domain": "Geophysical", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-130", "mcp_tool": "adw.adw_130", "sample": "https://alpinedataworks.com/showcase/adw-130", "description": "NOAA SWPC planetary Kp peak/mean/trend.", "agent_question": "How elevated is geomagnetic activity?", "history_start": "2016-07-17", "history_years": 10.0, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "NOAA (data.noaa.gov)" ], "mcp_description": "Returns a 0-100 geomagnetic activity risk score (daily composite z-score of NOAA SWPC planetary Kp peak, mean, and trend; 10-year history) with score, percentile, trend, and methodology_version. Call when the user asks about space weather, geomagnetic storms, Kp index, solar storms, or aurora conditions, or when timing satellite maneuvers, thruster burns, ground-station uplinks, GNSS/GPS accuracy, or HF radio operations." }, { "id": "ADW-131", "name": "Global Stability Index", "domain": "Events", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-131", "mcp_tool": "adw.adw_131", "sample": "https://alpinedataworks.com/showcase/adw-131", "description": "GDELT tone + conflict share (100=stable).", "agent_question": "How stable is the global news climate?", "history_start": "1993-12-31", "history_years": 32.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "GDELT Project (api.gdeltproject.org/api/v2)", "FEC (api.open.fec.gov/v1)" ], "mcp_description": "Returns a 0-100 global stability score for the world news climate (daily composite z-score of GDELT event tone and conflict-event share since 1993; 100 = fully stable) with trend, percentile, top_drivers, and GDELT source lineage. Call when the user asks about geopolitical risk, global instability, conflict escalation, international tensions, unrest, or the news climate, or when timing hedges, risk-off rebalancing, or emerging-market FX exposure decisions." }, { "id": "ADW-132", "name": "US Water Stress (Major Basin)", "domain": "Environment", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-132", "mcp_tool": "adw.adw_132", "sample": "https://alpinedataworks.com/showcase/adw-132", "description": "USGS streamflow vs normal, 10-gauge sample.", "agent_question": "How stressed are major US river basins?", "history_start": "1975-01-02", "history_years": 51.5, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "USGS (usgs.gov)" ], "mcp_description": "Returns a 0-100 US water-stress index for major river basins (weekly USGS streamflow vs. normal across a 10-gauge sample, z-scored composite, history since 1975) with score, trend, percentile, top_drivers gauges, and source_lineage. Call when the user asks about drought, streamflow, river basin conditions, water supply, or irrigation risk, or when timing exposure to water-intensive crops (corn, cotton, rice forward contracts) ahead of USDA crop-progress reports." }, { "id": "ADW-133", "name": "US Air Quality (Major Metro)", "domain": "Environment", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-133", "mcp_tool": "adw.adw_133", "sample": "https://alpinedataworks.com/showcase/adw-133", "description": "Open-Meteo US-AQI, 6-metro sample.", "agent_question": "How bad is air quality in major US metros?", "history_start": "1990-01-01", "history_years": 36.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "FEC (api.open.fec.gov/v1)" ], "mcp_description": "Returns a 0-100 composite air-quality index for major US metros (daily Open-Meteo US-AQI readings across a metro sample, z-scored against history since 1990) with current score, percentile, trend history, and source lineage. Call when the user asks about air pollution, smog, AQI, PM2.5, wildfire smoke, or urban environmental health, or when timing quality-of-life adjustments in real-estate, relocation, or livability-scoring decisions." }, { "id": "ADW-206", "name": "FDIC Deposit-Runoff Velocity", "domain": "Financial/Banking", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-206", "mcp_tool": "adw.adw_206", "sample": "https://alpinedataworks.com/showcase/adw-206", "description": "The velocity of deposit runoff across FDIC-insured banks, flagging early-stage liquidity stress in the sector.", "agent_question": "Is the US banking sector showing early-stage deposit liquidity stress?", "history_start": "1976-12-29", "history_years": 49.5, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FDIC BankFind Suite" ], "mcp_description": "Returns a 0-100 US banking-sector deposit-runoff velocity score (z-score of QoQ uninsured-deposit change over total assets, 20-quarter window, FDIC BankFind Call Report data, monthly) with runoff_velocity_score, stressed_bank_pct, and sector_zscore. Call when the user asks about bank runs, deposit flight or outflows, uninsured deposits, or early-stage bank liquidity stress, or when timing liquidity-scenario refreshes, regional-bank exposure, or risk-desk alerts." }, { "id": "ADW-207", "name": "Treasury Auction Tail Stress Index", "domain": "Financial/Rates", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-207", "mcp_tool": "adw.adw_207", "sample": "https://alpinedataworks.com/showcase/adw-207", "description": "Stress in US Treasury auctions, measuring how well the market is absorbing new debt issuance.", "agent_question": "Is the US Treasury market struggling to absorb new debt issuance?", "history_start": "2001-01-31", "history_years": 25.4, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "US Treasury Fiscal Data" ], "mcp_description": "Returns a 0-100 Treasury auction tail stress score (tail_bps z-score minus bid-to-cover z-score, 104-week rolling window by tenor; weekly from US Treasury Fiscal Data since 2001; higher = weaker auction demand) with auction_stress_score, tail_bps, and bid_to_cover_z. Call when the user asks about Treasury auction tails, bid-to-cover, weak demand, or whether markets can absorb new debt issuance, or when timing duration trades and order execution around scheduled auctions." }, { "id": "ADW-208", "name": "EDGAR Risk-to-MD&A Sentiment Divergence", "domain": "Finance/Corporate", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-208", "mcp_tool": "adw.adw_208", "sample": "https://alpinedataworks.com/showcase/adw-208", "description": "The sentiment gap between Risk-Factors and MD&A sections of EDGAR filings, a signal of earnings-disappointment risk.", "agent_question": "Does a company's Risk-Factors vs MD&A sentiment gap predict earnings disappointment?", "history_start": "2016-08-01", "history_years": 9.9, "product_class": "time-series", "tier": "Platinum", "refresh": "weekly", "source_apis": [ "SEC EDGAR Full-Text Search" ], "mcp_description": "Returns a 0-100 SEC-filing tone-divergence score (Loughran-McDonald negative-word density gap between Risk Factors and MD&A sections, z-scored weekly from EDGAR full-text since 2016) with divergence_score, risk_neg_density, and mda_neg_density. Call when the user asks about filing sentiment, 10-K/10-Q tone, management burying bad news, or earnings disappointment risk, or when timing pre-earnings position reviews and sell-side alerts on fundamental holdings." }, { "id": "ADW-210", "name": "OFR Financial-Stress Persistence Score", "domain": "Financial/Macro", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-210", "mcp_tool": "adw.adw_210", "sample": "https://alpinedataworks.com/showcase/adw-210", "description": "The persistence of financial-market stress, distinguishing transient spikes from durable regime shifts.", "agent_question": "Is current market stress a transient spike or a persistent regime shift?", "history_start": "1994-07-22", "history_years": 32.0, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "OFR Financial Stress Index", "FRED yield-curve proxy" ], "mcp_description": "Returns a 0-100 financial-stress persistence score (weekly; 20-day OFR Financial Stress Index persistence ratio x inverted-curve weight; spans five asset classes unlike equity-only VIX) with persistence_score, fsi_20d_avg, and yield_slope. Call when the user asks about transient vs. persistent market stress, regime shifts, credit or funding dislocations, or yield-curve inversion, or when timing hedge triggers and risk-on/risk-off posture changes." }, { "id": "ADW-233", "name": "FDIC Bank NIM Compression Index", "domain": "Financial/Banking", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-233", "mcp_tool": "adw.adw_233", "sample": "https://alpinedataworks.com/showcase/adw-233", "description": "The degree of net-interest-margin compression across FDIC-reporting banks, tracked sector-wide.", "agent_question": "Are bank net interest margins compressing across the sector?", "history_start": "1982-05-28", "history_years": 44.1, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FDIC BankFind Suite" ], "mcp_description": "Returns a 0-100 bank NIM compression score (asset-weighted z-score of QoQ net interest margin change from FDIC call reports, 20-quarter window, monthly since 1982) with nim_compression_score, sector_nim, and nim_zscore. Call when the user asks about bank net interest margins, sector margin squeeze, banking profitability, or rate-cycle impact on lenders, or when timing bank-counterparty risk escalation, covenant reviews, or credit-exposure monitoring." }, { "id": "ADW-234", "name": "GLEIF Counterparty Ownership Complexity", "domain": "Financial/Entity", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-234", "mcp_tool": "adw.adw_234", "sample": "https://alpinedataworks.com/showcase/adw-234", "description": "A real-time score of a counterparty's legal ownership complexity and opacity, built from GLEIF entity records.", "agent_question": "How complex/opaque is a counterparty's legal ownership structure?", "history_start": "2026-06-25", "history_years": 0.0, "product_class": "live", "tier": "Gold", "refresh": "weekly", "source_apis": [ "GLEIF LEI" ], "mcp_description": "Returns a 0-100 counterparty ownership-complexity score (GLEIF LEI relationship-graph depth and breadth composite, weekly; higher = more opaque) with complexity_score, ownership_depth, and relationship_count. Call when the user asks about counterparty legal-entity structure, beneficial ownership opacity, shell-company risk, KYC/AML due diligence, or corporate ownership chains, or when timing onboarding approval versus escalation to human sanctions review." }, { "id": "ADW-232", "name": "eCFR Regulatory-Change Impact", "domain": "Government/Regulatory", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-232", "mcp_tool": "adw.adw_232", "sample": "https://alpinedataworks.com/showcase/adw-232", "description": "The intensity of recent US federal regulatory-change activity, tracked from eCFR amendments.", "agent_question": "How intense is recent US federal regulatory-change activity?", "history_start": "1995-01-31", "history_years": 31.4, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "eCFR Versioner API" ], "mcp_description": "Returns a 0-100 US federal regulatory-change intensity score (share of CFR titles amended in the trailing 90 days, eCFR Versioner API, weekly since 1995) with regchange_score, titles_amended_90d, and recent_share. Call when the user asks about regulatory churn, rulemaking or deregulation activity, CFR amendments, compliance risk, or Federal Register volume, or when timing compliance audits, counsel review, or regulatory-monitoring alerts." }, { "id": "ADW-238", "name": "GDELT Conflict-to-Trade Disruption Signal", "domain": "International/Trade", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-238", "mcp_tool": "adw.adw_238", "sample": "https://alpinedataworks.com/showcase/adw-238", "description": "Escalation in global trade-disruption news \u2014 tariffs, sanctions, export bans \u2014 tracked from GDELT event coverage.", "agent_question": "Is global trade-disruption news (tariffs/sanctions/export bans) escalating?", "history_start": "2019-01-30", "history_years": 7.4, "product_class": "time-series", "tier": "Gold", "refresh": "hourly", "source_apis": [ "GDELT 2.0 DOC API" ], "mcp_description": "Returns a 0-100 global trade-disruption signal (GDELT news volume on tariffs, sanctions, and export bans; recent 3-day vs 30-day baseline, hourly) with disruption_score and recent_vs_baseline_ratio. Call when the user asks about tariff escalation, sanctions, export bans, trade wars, or supply-chain disruption risk, or when timing purchase-order commitments, sourcing-lane shifts, or procurement decisions ahead of lagging PMI export surveys." }, { "id": "ADW-209", "name": "US Federal Contract-Award Momentum", "domain": "Public/Procurement", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-209", "mcp_tool": "adw.adw_209", "sample": "https://alpinedataworks.com/showcase/adw-209", "description": "The momentum of US federal prime-contract award activity, tracking whether awards are accelerating or slowing.", "agent_question": "Is federal prime-contract award activity accelerating or slowing?", "history_start": "1949-12-31", "history_years": 76.5, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "USAspending.gov Search API" ], "mcp_description": "Returns a 0-100 federal prime-contract award momentum score (USAspending.gov top-100 obligated dollars, recent 45-day vs prior 45-day, weekly) with award_momentum_score and recent_vs_prior_ratio. Call when the user asks about federal procurement trends, government contract awards accelerating or slowing, defense contractor demand, or GovCon spending, or when timing contractor revenue forecasts or contracting-officer outreach \u2014 obligation dates lead earnings by 1-2 quarters." }, { "id": "ADW-213", "name": "Agricultural Input/Climate Stress (Corn Belt)", "domain": "Agriculture/Commodity", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-213", "mcp_tool": "adw.adw_213", "sample": "https://alpinedataworks.com/showcase/adw-213", "description": "Precipitation and soil-moisture stress across the US Corn Belt, scored 0-100 for crop-risk monitoring.", "agent_question": "Is the US Corn Belt under precipitation/soil-moisture stress?", "history_start": "1981-01-30", "history_years": 45.4, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "NASA POWER agroclimatology" ], "mcp_description": "Returns a 0-100 US Corn Belt precipitation/soil-moisture stress score (weekly NASA POWER agroclimatology since 1981; 0.55*precip-deficit-vs-30d + 0.45*root-moisture-deficit) with stress_score, precip_deficit, root_moisture_deficit. Call when the user asks about Corn Belt drought, corn crop stress, soil moisture, rainfall deficits, ethanol or livestock feed costs, or when timing corn/ethanol futures positioning ahead of weekly USDA crop progress releases." }, { "id": "ADW-212", "name": "Seismic Event Intensity", "domain": "Geophysical/Risk", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-212", "mcp_tool": "adw.adw_212", "sample": "https://alpinedataworks.com/showcase/adw-212", "description": "The current intensity of global seismic energy release, scored 0-100 against historical baselines.", "agent_question": "How elevated is global seismic energy release right now?", "history_start": "1960-01-09", "history_years": 66.5, "product_class": "time-series", "tier": "Gold", "refresh": "hourly", "source_apis": [ "USGS Earthquake FDSN" ], "mcp_description": "Returns a 0-100 global seismic energy-release intensity score (log10 of summed seismic-moment proxy 10^1.5M over M4+ events, rolling 7 days; USGS FDSN, hourly, history to 1960) with intensity_score, max_magnitude_7d, and m4plus_count. Call when the user asks about earthquakes, seismic activity, quake clusters, magnitudes, or geophysical hazard, or when timing catastrophe-risk triage, insured-exposure loss estimates, or severity-based alerts." }, { "id": "ADW-217", "name": "Renewable Resource Availability", "domain": "Energy/Transition", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-217", "mcp_tool": "adw.adw_217", "sample": "https://alpinedataworks.com/showcase/adw-217", "description": "The favorability of wind and solar resource conditions in the ERCOT region, scored 0-100.", "agent_question": "How favorable are wind+solar resource conditions in the ERCOT region?", "history_start": "1979-01-03", "history_years": 47.5, "product_class": "time-series", "tier": "Gold", "refresh": "hourly", "source_apis": [ "Open-Meteo" ], "mcp_description": "Returns a 0-100 renewable resource availability score for the ERCOT/Texas grid (equal-weighted wind and solar availability from the 48-hour Open-Meteo forecast, refreshed hourly \u2014 forward-looking, not lagged capacity factors) with availability_score, avg_wind, and avg_radiation. Call when the user asks about wind/solar conditions, renewable generation, ERCOT supply, or grid weather, or when timing electricity-price forecasts, day-ahead virtual offers, or LMP spike-risk windows." }, { "id": "ADW-219", "name": "FDA Drug-Recall Velocity", "domain": "Compliance/Risk", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-219", "mcp_tool": "adw.adw_219", "sample": "https://alpinedataworks.com/showcase/adw-219", "description": "The velocity of FDA Class-I drug-recall enforcement, tracking whether recall activity is accelerating.", "agent_question": "Is FDA Class-I drug-recall enforcement accelerating?", "history_start": "2012-09-25", "history_years": 13.8, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "openFDA Drug Enforcement" ], "mcp_description": "Returns a 0-100 FDA drug-recall velocity score (trailing 90-day count of Class-I recalls, the most severe, life-threatening category, from openFDA Drug Enforcement, refreshed weekly) with recall_velocity_score and class_I_90d. Call when the user asks about FDA drug recalls, Class-I enforcement acceleration, pharmaceutical quality-system or supply-chain compliance risk, or when timing supplier audits, Form 483 responses, and pre-consent-decree or import-alert remediation." }, { "id": "ADW-220", "name": "Food-Recall Safety Signal", "domain": "Consumer/Safety", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-220", "mcp_tool": "adw.adw_220", "sample": "https://alpinedataworks.com/showcase/adw-220", "description": "The velocity of Class-I food-recall enforcement, flagging accelerating food-safety risk.", "agent_question": "Is Class-I food-recall enforcement accelerating?", "history_start": "2012-09-30", "history_years": 13.8, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "openFDA Food Enforcement" ], "mcp_description": "Returns a 0-100 food-recall safety signal (scaled count of FDA Class-I food recalls in the trailing 90 days, openFDA Food Enforcement, weekly, history since 2012) with safety_signal_score and class_I_90d. Call when the user asks about food recalls, accelerating recall enforcement, food safety, contamination or foodborne-outbreak risk, or when timing supplier holds, FSMA traceability lookups, or private-label category exposure reviews." }, { "id": "ADW-250", "name": "USD Broad-Strength Index (DXY proxy)", "domain": "Market/FX", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-250", "mcp_tool": "adw.adw_250", "sample": "https://alpinedataworks.com/showcase/adw-250", "description": "The broad strength of the US dollar against a major-currency basket, a DXY-style index.", "agent_question": "How strong is the US dollar against the major-currency basket right now?", "history_start": "1999-01-04", "history_years": 27.5, "product_class": "time-series", "tier": "Gold", "refresh": "hourly", "source_apis": [ "ExchangeRate-API (keyless)" ], "mcp_description": "Returns a 0-100 US dollar broad-strength score (ICE DXY geometric formula, 6-currency fixed weights on live spot rates, hourly, history to 1999) with dxy_proxy_score, dxy_proxy, and eurusd fields. Call when the user asks about dollar strength or weakness, DXY, the dollar index, EUR/USD, exchange rates, or FX basket moves, or when timing USD hedging, hedge-ratio adjustments, or rebalancing FX exposure on dollar-denominated receivables." }, { "id": "ADW-251", "name": "US Power-Grid Outage Stress", "domain": "Energy/Resilience", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-251", "mcp_tool": "adw.adw_251", "sample": "https://alpinedataworks.com/showcase/adw-251", "description": "Current stress on the US power grid, measured by customers without power, scored 0-100.", "agent_question": "How stressed is the US power grid right now (customers out)?", "history_start": "2014-11-01", "history_years": 11.7, "product_class": "time-series", "tier": "Gold", "refresh": "hourly", "source_apis": [ "DOE EAGLE-I / ORNL ODIN (keyless)" ], "mcp_description": "Returns a 0-100 US power-grid outage stress score (log10 of total customers without power across counties, 10M out = 100; federal DOE EAGLE-I/ORNL ODIN feed, hourly) with outage_stress_score, total_customers_out, and counties_affected. Call when the user asks about power outages, blackouts, grid stress or reliability, storm/hurricane impact, or customers without electricity, or when timing outage alerts, field-crew pre-positioning, or storm-response decisions." }, { "id": "ADW-215", "name": "US Aviation Disruption Index", "domain": "Aviation/Operations", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-215", "mcp_tool": "adw.adw_215", "sample": "https://alpinedataworks.com/showcase/adw-215", "description": "The current disruption level of the US airspace system, scoring ground stops and delays 0-100.", "agent_question": "How disrupted is the US airspace system right now (ground stops/delays)?", "history_start": "2016-01-31", "history_years": 10.4, "product_class": "time-series", "tier": "Gold", "refresh": "hourly", "source_apis": [ "FAA Airport Status (ASWS)" ], "mcp_description": "Returns a 0-100 US airspace disruption index (hourly FAA ASWS airport status; ground stops and closures weighted 3x, delays 2x, plus breadth of airports affected) with disruption_score, ground_stops, and airports_affected. Call when the user asks about flight delays, ground stops, airport closures, or current US air-travel disruption, or when timing freight re-routing, shipment ETAs, or rebooking before systemic delays cascade across hubs." }, { "id": "ADW-252", "name": "US Severe-Weather Hazard Load", "domain": "Climate/Risk", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-252", "mcp_tool": "adw.adw_252", "sample": "https://alpinedataworks.com/showcase/adw-252", "description": "The current load of active US severe-weather alerts, scored 0-100 by coverage and severity.", "agent_question": "How heavy is the current US severe-weather alert load?", "history_start": "2016-07-10", "history_years": 10.0, "product_class": "time-series", "tier": "Gold", "refresh": "hourly", "source_apis": [ "NWS api.weather.gov alerts" ], "mcp_description": "Returns a 0-100 US severe-weather hazard load score (severity-weighted active NWS alerts: Extreme 4/Severe 3/Moderate 2/Minor 1, scaled; hourly, 10-year history, mean ~30, 60+ = elevated) with hazard_load_score, extreme_alerts, severe_alerts. Call when the user asks about storm severity, weather alerts or warnings, tornado/hurricane risk, or national weather disruption, or when timing logistics re-routing, fleet dispatch, delivery/supply-chain delays, or outdoor-event decisions." }, { "id": "ADW-223", "name": "Global Trade-Openness Signal", "domain": "International/Trade", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-223", "mcp_tool": "adw.adw_223", "sample": "https://alpinedataworks.com/showcase/adw-223", "description": "The expansion or contraction of global trade openness, measured as trade's share of GDP.", "agent_question": "Is global trade openness (trade as % of GDP) expanding or contracting?", "history_start": "1958-10-01", "history_years": 67.8, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "World Bank Open Data" ], "mcp_description": "Returns a 0-100 global trade-openness score (scaled YoY change in World Bank world trade as % of GDP, monthly, since 1958) with openness_score, trade_pct_gdp, and yoy_change. Call when the user asks about globalization, deglobalization, trade expansion or contraction, tariffs, or supply-chain shifts, or when timing rotations between export-dependent sectors (industrials, materials, semiconductors) and domestic defensives on confirmed trade flows, not PMI sentiment surveys." }, { "id": "ADW-253", "name": "US Flood-Risk Signal (Gulf Coast)", "domain": "Climate/Risk", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-253", "mcp_tool": "adw.adw_253", "sample": "https://alpinedataworks.com/showcase/adw-253", "description": "River-discharge buildup toward flood risk on the US Gulf Coast, scored 0-100.", "agent_question": "Is river-discharge building toward flood risk on the US Gulf Coast?", "history_start": "2016-07-06", "history_years": 10.0, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Open-Meteo Flood (GloFAS)" ], "mcp_description": "Returns a 0-100 US Gulf Coast flood-risk score (scaled peak-vs-current 7-day GloFAS river-discharge ratio via Open-Meteo Flood, daily, 10y history) with flood_risk_score, peak_vs_current, and peak_discharge. Call when the user asks about Gulf Coast flooding, river discharge, rising water levels, or flood exposure, or when timing insurance loss-reserve reviews, property-portfolio risk checks, or underwriting decisions ahead of NWS gauges reaching flood stage." }, { "id": "ADW-254", "name": "US Labor-Market Stress", "domain": "Macro/Labor", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-254", "mcp_tool": "adw.adw_254", "sample": "https://alpinedataworks.com/showcase/adw-254", "description": "US labor-market stress from the unemployment level and its recent trend, scored 0-100.", "agent_question": "Is the US labor market weakening (unemployment level + recent trend)?", "history_start": "1975-06-01", "history_years": 51.1, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "BLS Public Data API v1" ], "mcp_description": "Returns a 0-100 US labor-market stress score (monthly BLS unemployment rate: 50% level-stress vs a 3.5% full-employment floor, 50% 3-month trend deterioration; history since 1975) with stress_score, unemployment_rate, and change_3mo. Call when the user asks about unemployment, jobless trends, layoffs, labor-market softening, or recession risk, or when timing macro-scenario shifts such as base-to-adverse credit-loss provisioning." }, { "id": "ADW-255", "name": "US Housing-Starts Momentum", "domain": "Real Estate/Leading", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-255", "mcp_tool": "adw.adw_255", "sample": "https://alpinedataworks.com/showcase/adw-255", "description": "The momentum of US housing starts, tracking whether residential construction is accelerating or stalling.", "agent_question": "Is US housing construction accelerating or stalling?", "history_start": "1962-12-01", "history_years": 63.6, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (St. Louis Fed)" ], "mcp_description": "Returns a 0-100 US housing-starts momentum score (monthly FRED HOUST residential construction data since 1962, recent value vs trailing-mean percent deviation) with momentum_score, recent_value, and deviation_pct. Call when the user asks about housing starts, homebuilding, whether US housing construction is accelerating or stalling, or the residential real-estate cycle, or when timing homebuilder and building-materials equity overweights or tactical sector rebalancing." }, { "id": "ADW-256", "name": "US Retail-Sales Momentum", "domain": "Consumer/Spending", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-256", "mcp_tool": "adw.adw_256", "sample": "https://alpinedataworks.com/showcase/adw-256", "description": "The momentum of US retail sales, tracking whether consumer spending is accelerating or slowing.", "agent_question": "Is US consumer retail spending accelerating?", "history_start": "1995-12-01", "history_years": 30.6, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (St. Louis Fed)" ], "mcp_description": "Returns a 0-100 US retail-sales momentum score (monthly FRED RSAFS; recent value vs trailing-mean % deviation, scaled; history to 1995) with momentum_score, recent_value, and deviation_pct. Call when the user asks about US consumer spending, retail sales trends, or whether consumer demand is accelerating or slowing, or when timing inventory replenishment, demand forecasting, or revenue-guidance updates after monthly Census retail releases." }, { "id": "ADW-257", "name": "US Industrial-Production Momentum", "domain": "Industry/Output", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-257", "mcp_tool": "adw.adw_257", "sample": "https://alpinedataworks.com/showcase/adw-257", "description": "The momentum of US industrial production, tracking whether output is accelerating or slowing.", "agent_question": "Is US industrial output accelerating?", "history_start": "1922-12-01", "history_years": 103.6, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (St. Louis Fed)" ], "mcp_description": "Returns a 0-100 US industrial-production momentum score (FRED INDPRO, recent value vs trailing-mean % deviation, monthly since 1922) with momentum_score, recent_value, and deviation_pct. Call when the user asks about US industrial output acceleration, manufacturing activity, factory production trends, or business-cycle strength, or when timing sector rotation into industrial and manufacturing equities or overweight/underweight shifts." }, { "id": "ADW-258", "name": "US Consumer-Sentiment Level", "domain": "Consumer/Sentiment", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-258", "mcp_tool": "adw.adw_258", "sample": "https://alpinedataworks.com/showcase/adw-258", "description": "The level and direction of US consumer sentiment, tracking improvement or deterioration over time.", "agent_question": "Is US consumer sentiment improving or deteriorating?", "history_start": "1966-11-01", "history_years": 59.7, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (St. Louis Fed)" ], "mcp_description": "Returns a 0-100 US consumer-sentiment momentum score (FRED UMCSENT, University of Michigan survey, monthly since 1966; recent value vs trailing-mean % deviation, scaled) with momentum_score, recent_value, and deviation_pct. Call when the user asks about US consumer sentiment improving or deteriorating, consumer confidence, or household spending mood, or when timing promotional budgets, ad-spend reallocation, price increases, or discretionary-goods demand planning." }, { "id": "ADW-259", "name": "US Jobless-Claims Stress", "domain": "Macro/Labor", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-259", "mcp_tool": "adw.adw_259", "sample": "https://alpinedataworks.com/showcase/adw-259", "description": "Labor-market stress signaled by US initial jobless claims, scored against the recent trend.", "agent_question": "Are US initial jobless claims signaling labor stress?", "history_start": "2016-07-02", "history_years": 10.0, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (St. Louis Fed)" ], "mcp_description": "Returns a 0-100 US jobless-claims stress score (FRED ICSA weekly initial unemployment claims, recent vs trailing-mean % deviation, scaled; higher = more labor stress) with momentum_score, recent_value, and deviation_pct. Call when the user asks about initial jobless claims, unemployment filings, layoffs, labor-market health, or recession risk, or when timing consumer-credit underwriting, hiring plans, or macro risk-posture decisions." }, { "id": "ADW-260", "name": "US Nonfarm-Payrolls Momentum", "domain": "Macro/Labor", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-260", "mcp_tool": "adw.adw_260", "sample": "https://alpinedataworks.com/showcase/adw-260", "description": "The momentum of US nonfarm payrolls, tracking whether job creation is accelerating or slowing.", "agent_question": "Is US job creation accelerating or slowing?", "history_start": "1942-12-01", "history_years": 83.6, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (St. Louis Fed)" ], "mcp_description": "Returns a 0-100 US nonfarm-payrolls momentum score (FRED PAYEMS recent job growth vs trailing-mean % deviation, monthly since 1942) with momentum_score, recent_value, and deviation_pct fields. Call when the user asks about US job creation accelerating or slowing, employment growth, hiring momentum, payrolls, or labor-market strength, or when timing consumption and GDP assumption changes in macro forecasts or recession-risk models." }, { "id": "ADW-261", "name": "US Building-Permits Momentum", "domain": "Real Estate/Leading", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-261", "mcp_tool": "adw.adw_261", "sample": "https://alpinedataworks.com/showcase/adw-261", "description": "The momentum of US building permits, a leading indicator of housing construction activity.", "agent_question": "Are US building permits (leading housing) accelerating?", "history_start": "1964-06-01", "history_years": 62.1, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (St. Louis Fed)" ], "mcp_description": "Returns a 0-100 US building-permits momentum score (FRED PERMIT, recent vs trailing-mean % deviation, monthly since 1964) with momentum_score, recent_value, and deviation_pct. Call when the user asks about building permits, housing starts, homebuilding activity, residential construction momentum, or leading housing-supply indicators, or when timing REIT allocation, homebuilder exposure, or land-acquisition decisions around the 6-12-month housing cycle." }, { "id": "ADW-262", "name": "US Durable-Goods Orders Momentum", "domain": "Industry/Capex", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-262", "mcp_tool": "adw.adw_262", "sample": "https://alpinedataworks.com/showcase/adw-262", "description": "The momentum of US durable-goods orders, a proxy for business capital spending.", "agent_question": "Is US business capex (durable-goods orders) accelerating?", "history_start": "1996-01-01", "history_years": 30.5, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (St. Louis Fed)" ], "mcp_description": "Returns a 0-100 US durable-goods orders momentum score (FRED DGORDER, monthly; recent vs trailing-mean % deviation, scaled; history since 1996) with momentum_score, recent_value, and deviation_pct. Call when the user asks about business capex acceleration, capital spending, manufacturing demand, factory or equipment orders, or the industrial cycle, or when timing capacity expansion, industrial equipment sales, or capex-cycle positioning decisions." }, { "id": "ADW-263", "name": "US Consumption Momentum", "domain": "Consumer/Spending", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-263", "mcp_tool": "adw.adw_263", "sample": "https://alpinedataworks.com/showcase/adw-263", "description": "The momentum of US personal consumption, tracking whether household spending is accelerating.", "agent_question": "Is US personal consumption accelerating?", "history_start": "1962-12-01", "history_years": 63.6, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (St. Louis Fed)" ], "mcp_description": "Returns a 0-100 US consumption momentum score (monthly FRED PCE; recent value vs trailing-mean % deviation, scaled; history to 1962) with momentum_score, recent_value, and deviation_pct. Call when the user asks about US consumer spending, personal consumption expenditures, PCE, household spending trends, or whether consumption is accelerating or slowing, or when timing revenue forecasts, marketing/expansion budgets, or consumer-demand-sensitive decisions." }, { "id": "ADW-264", "name": "US Vehicle-Sales Momentum", "domain": "Consumer/Autos", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-264", "mcp_tool": "adw.adw_264", "sample": "https://alpinedataworks.com/showcase/adw-264", "description": "The momentum of US vehicle sales, tracking whether auto demand is accelerating or slowing.", "agent_question": "Is US auto demand accelerating or slowing?", "history_start": "1979-12-01", "history_years": 46.6, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (St. Louis Fed)" ], "mcp_description": "Returns a 0-100 US vehicle-sales momentum score (FRED TOTALSA monthly SAAR, recent vs trailing-mean % deviation, history to 1979) with momentum_score, recent_value, and deviation_pct. Call when the user asks about US auto demand, car or vehicle sales trends, consumer autos, or the auto cycle, or when timing dealer inventory, production planning, or supply-chain stocking decisions around auto-cycle peaks and slowdowns." }, { "id": "ADW-302", "name": "GeoHealth Index", "domain": "Health/Geographic", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-302", "mcp_tool": "adw.health_risk", "sample": "https://alpinedataworks.com/showcase/adw-302", "description": "Per-ZCTA composite health-risk score (0-100) from 40 CDC PLACES measures, national-percentile-ranked and weighted (mortality-linked chronic disease highest). Higher = higher community health risk.", "agent_question": "How healthy or at-risk is this US ZIP code, and what's driving it?", "history_start": "1951-12-01", "history_years": 74.6, "product_class": "time-series", "tier": "Gold", "refresh": "annual (manual offline recompute + D1 reload; no auto-cron yet)", "source_apis": [ "CDC PLACES ZCTA 2025 (data.cdc.gov)" ], "mcp_description": "Returns a 0-100 community health-risk score for any US ZIP code/ZCTA (40 CDC PLACES measures, percentile-ranked across 32,520 ZCTAs, mortality-linked chronic disease weighted highest) with risk_band, confidence, rank_eligible, top_drivers, and geography. Call when the user asks about ZIP-code or neighborhood health, at-risk communities, or what drives local chronic-disease burden, or when timing clinic siting, outreach targeting, or service-area investment decisions." }, { "id": "ADW-310", "name": "Policy Volatility Index", "domain": "Government/Regulatory", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-310", "mcp_tool": "adw.adw_310", "sample": "https://alpinedataworks.com/showcase/adw-310", "description": "US federal rule-publication pace vs 90-day baseline (Federal Register, keyless).", "agent_question": "Is US federal rulemaking accelerating or decelerating right now?", "history_start": "1988-12-01", "history_years": 37.6, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Federal Register API (https://www.federalregister.gov/api/v1)" ], "mcp_description": "Returns a 0-100 US federal rulemaking-pace index (Federal Register published-rule counts, 30-day vs rolling-90-day ratio, final rules weighted over proposed; daily since 1988) with an IOM carrying score, historical percentile, source lineage, and methodology version. Call when the user asks about regulatory volatility, rulemaking acceleration or slowdown, Federal Register activity, policy or compliance risk, or when timing compliance-review sprints and regulated-feature prioritization." }, { "id": "ADW-311", "name": "Labor Market Tightness Score", "domain": "Labor/Macro", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-311", "mcp_tool": "adw.adw_311", "sample": "https://alpinedataworks.com/showcase/adw-311", "description": "JOLTS job openings vs CPS unemployment ratio, normalized to historical anchors (BLS, keyless).", "agent_question": "How tight is the US labor market right now, and tightening or loosening?", "history_start": "2005-01-01", "history_years": 21.5, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "BLS (api.bls.gov/publicAPI/v2)" ], "mcp_description": "Returns a 0-100 US labor market tightness score (BLS JOLTS job openings per unemployed worker, normalized 2020 trough to 2022 peak; monthly since 2005) with tightening/loosening trend, percentile, top_drivers (openings-side vs unemployment-side), and source lineage. Call when the user asks about labor market tightness, hiring difficulty, worker shortages, job openings vs unemployment, or wage pressure, or when timing salary-band uplifts, compensation planning, or recruiting pushes." }, { "id": "ADW-313", "name": "Energy Regulatory Exposure Index", "domain": "Energy/Regulatory", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-313", "mcp_tool": "adw.adw_313", "sample": "https://alpinedataworks.com/showcase/adw-313", "description": "Z-score of US commercial electricity + natural gas prices vs trailing 36-mo baseline, 60/40 (EIA).", "agent_question": "How elevated are US commercial energy prices vs historical norms?", "history_start": "1995-11-01", "history_years": 30.7, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "EIA API (api.eia.gov)" ], "mcp_description": "Returns a 0-100 US commercial energy price elevation index (weekly EIA data; z-scored commercial electricity 60% + natural gas 40% vs 30-year norms; 50 = normal) with score, top_drivers, confidence, and methodology_version. Call when the user asks about commercial electricity rates, natural gas costs, energy price spikes, utility cost inflation, or energy regulatory exposure, or when timing fixed-rate electricity/gas contract RFPs, procurement, or hedging decisions." }, { "id": "ADW-314", "name": "Infrastructure Investment Velocity", "domain": "Industry/Capex", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-314", "mcp_tool": "adw.adw_314", "sample": "https://alpinedataworks.com/showcase/adw-314", "description": "US total + public construction spending YoY + 3-mo momentum (Census VIP via FRED keyless mirror).", "agent_question": "Is US infrastructure investment accelerating or contracting relative to trend?", "history_start": "1996-12-01", "history_years": 29.6, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (api.stlouisfed.org/fred)", "US Census (api.census.gov)", "EPA (www.epa.gov)" ], "mcp_description": "Returns a 0-100 US infrastructure investment velocity score (Census construction value-in-place via FRED; equal-weight total and public spend, YoY plus 3-month momentum; above 50 = accelerating; monthly since 1996) with top_drivers splitting private vs public drag and source_lineage to the primary release. Call when the user asks about infrastructure spending, construction capex, or public works momentum, or when timing infrastructure-linked equity, materials, or engineering exposure." }, { "id": "ADW-347", "name": "Global Liquidity Stress Index", "domain": "Financial/Liquidity", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-347", "mcp_tool": "adw.adw_347", "sample": "https://alpinedataworks.com/showcase/adw-347", "description": "5yr rolling z-score composite of Chicago Fed NFCI (60%) + Fed balance sheet WALCL (25%) + ON reverse-repo (15%); higher=more stress (FRED keyless).", "agent_question": "What is the current global liquidity stress level \u2014 tightening or easing?", "history_start": "2016-06-24", "history_years": 10.0, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "fred.stlouisfed.org/graph/fredgraph.csv?id=NFCI (keyless; Chicago Fed, weekly)", "fred.stlouisfed.org/graph/fredgraph.csv?id=WALCL (keyless; Fed H.4.1, weekly)", "fred.stlouisfed.org/graph/fredgraph.csv?id=RRPONTSYD (keyless; NY Fed, daily)" ], "mcp_description": "Returns a 0-100 global liquidity stress index (weekly composite z-score: Chicago Fed NFCI 60%, Fed balance sheet WALCL 25%, reverse-repo RRP 15%; 50 neutral, higher = tighter; 10y history) with score, trend, percentile, and source_lineage. Call when the user asks about liquidity stress, financial conditions, money-market or funding strain, Fed liquidity, tightening or easing, or when timing counterparty credit limits, commercial paper, or short-duration fixed-income liquidity reviews." }, { "id": "ADW-335", "name": "US Freight Regulatory Risk Index", "domain": "Transport/Regulatory", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-335", "mcp_tool": "adw.adw_335", "sample": "https://alpinedataworks.com/showcase/adw-335", "description": "Z-score composite of BTS Transportation Services Index-Freight (45%) + ATA truck tonnage (35%) + cross-border truck crossings (20%) (data.bts.gov keyless).", "agent_question": "Is US freight activity elevated vs baseline (carrier utilization / regulatory demand)?", "history_start": "2000-05-01", "history_years": 26.2, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "BTS Monthly Transportation Statistics (crem-w557) \u2014 Transportation Services Index Freight (keyless Socrata)", "BTS Monthly Transportation Statistics (crem-w557) \u2014 ATA Truck Tonnage Index (keyless Socrata)", "BTS Monthly Transportation Statistics (crem-w557) \u2014 CBP Cross-Border Truck Crossings US-MX + US-CA (keyless Socrata)" ], "mcp_description": "Returns a 0-100 US freight activity and regulatory-demand index (recent-3mo vs trailing-baseline z-scores of ATA truck tonnage, BTS Transportation Services Index, and cross-border truck crossings, weighted 45/35/20, monthly since 2000) with score, percentile, trend, top_drivers, and source_lineage. Call when the user asks about freight demand, trucking activity, carrier utilization, truck tonnage, or cross-border freight, or when timing spot surcharges, load-board pricing, or dispatch capacity." }, { "id": "ADW-339", "name": "Software Supply-Chain Vulnerability Index", "domain": "Tech/Security", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-339", "mcp_tool": "adw.adw_339", "sample": "https://alpinedataworks.com/showcase/adw-339", "description": "CVSS-weighted advisory pressure across a 6-package npm+pypi basket (deps.dev keyless); 0-100, higher=more pressure.", "agent_question": "Is the OSS software supply chain under elevated vulnerability pressure, and where?", "history_start": "1975-12-01", "history_years": 50.6, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "api.deps.dev/v3/systems/{system}/packages/{name} (keyless)", "api.deps.dev/v3/systems/{system}/packages/{name}/versions/{version} (keyless)", "api.deps.dev/v3/advisories/{id} (keyless)" ], "mcp_description": "Returns a 0-100 software supply-chain vulnerability pressure index (per-package CVSS3 sums over recent npm and PyPI GA releases via deps.dev, max-normalized, basket mean) with weekly history, top_drivers identifying pressure-driving packages, and audit-ready source lineage. Call when the user asks about open-source dependency risk, CVE/CVSS severity trends, npm or PyPI package security, or supply-chain attacks, or when timing dependency upgrades, patch prioritization, or deployment gating." }, { "id": "ADW-312", "name": "Healthcare Cost Transparency Gap", "domain": "Healthcare/Macro", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-312", "mcp_tool": "adw.adw_312", "sample": "https://alpinedataworks.com/showcase/adw-312", "description": "CMS Open Payments (Sunshine Act) industry-payment intensity; recent year vs 3yr baseline (openpaymentsdata.cms.gov keyless).", "agent_question": "How intense is pharma/device industry financial engagement with US physicians, and growing?", "history_start": "1950-12-01", "history_years": 75.6, "product_class": "time-series", "tier": "Gold", "refresh": "annual", "source_apis": [ "CMS Open Payments API (https://openpaymentsdata.cms.gov/api)" ], "mcp_description": "Returns a 0-100 pharma/device industry physician-payment intensity score (annual CMS Open Payments record counts vs 3-year baseline mean, since 1950) with trend, top_drivers by payment category (consulting, research, education), and source_lineage. Call when the user asks about drug or device company payments to US doctors, physician financial ties, conflicts of interest, Sunshine Act, or Open Payments trends, or when timing healthcare compliance reviews of industry engagement exposure." }, { "id": "ADW-355", "name": "Raw Material Production Stress Indicator", "domain": "Commodities/Production", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-355", "mcp_tool": "adw.adw_355", "sample": "https://alpinedataworks.com/showcase/adw-355", "description": "Composite of US industrial output (IPMAT/IPMINE) + input prices (PPIIDC/WPU10) via FRED keyless CSV; higher=more stress.", "agent_question": "Is US raw-material production stressed (output decline or input-price surge)?", "history_start": "1916-12-01", "history_years": 109.6, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "fred.stlouisfed.org/graph/fredgraph.csv?id=IPMAT (keyless; FRB G.17, IP Materials, SA index 2017=100)", "fred.stlouisfed.org/graph/fredgraph.csv?id=IPMINE (keyless; FRB G.17, IP Mining, SA index 2017=100)", "fred.stlouisfed.org/graph/fredgraph.csv?id=PPIIDC (keyless; BLS PPI, Industrial Commodities, NSA index 1982=100)", "fred.stlouisfed.org/graph/fredgraph.csv?id=WPU10 (keyless; BLS PPI, Metals & Metal Products, NSA index 1982=100)" ], "mcp_description": "Returns a 0-100 US raw-material production stress score (half output leg, half price leg: mining/raw-materials output momentum plus industrial-commodity PPI surge, z-scored monthly FRED data since 1916) with confidence, top_drivers flagging output-led vs price-led stress, and source_lineage. Call when the user asks about commodity input costs, raw-material shortages, mining output declines, or producer-price spikes, or when timing procurement hedges, inventory pre-buys, or futures entries." }, { "id": "ADW-348", "name": "Labor Market Cooling Signal", "domain": "Labor/Macro", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-348", "mcp_tool": "adw.adw_348", "sample": "https://alpinedataworks.com/showcase/adw-348", "description": "4-series FRED momentum composite (UNRATE, ICSA, JTSQUR, JTSHIR); higher=more cooling. Distinct from ADW-311 (level).", "agent_question": "Is the US labor market actively deteriorating (claims/unemployment up, quits/hires down)?", "history_start": "1968-02-01", "history_years": 58.4, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "fred.stlouisfed.org/graph/fredgraph.csv?id=UNRATE (keyless; canonical source = BLS CPS monthly unemployment rate, SA)", "fred.stlouisfed.org/graph/fredgraph.csv?id=ICSA (keyless; canonical source = DOL Employment & Training Administration, weekly initial claims, SA)", "fred.stlouisfed.org/graph/fredgraph.csv?id=JTSQUR (keyless; canonical source = BLS Job Openings and Labor Turnover Survey, quits rate, SA)", "fred.stlouisfed.org/graph/fredgraph.csv?id=JTSHIR (keyless; canonical source = BLS Job Openings and Labor Turnover Survey, hires rate, SA)" ], "mcp_description": "Returns a 0-100 US labor-market cooling signal (weighted momentum vs. baseline across unemployment rate, initial jobless claims, quits, and hires; monthly since 1968) with score, percentile, trend, and top_drivers decomposing the deterioration pathway. Call when the user asks about labor market cooling or turning points, rising claims or unemployment, falling quits or hires, layoffs, or recession risk, or when timing risk-off moves like reducing equity beta or adding bonds." }, { "id": "ADW-349", "name": "EU Fiscal Sustainability Gap Score", "domain": "Financial/Sovereign", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-349", "mcp_tool": "adw.adw_349", "sample": "https://alpinedataworks.com/showcase/adw-349", "description": "Maastricht-anchored composite: debt/GDP (60%) + deficit/GDP (40%) for EA20 via Eurostat gov_10dd_edpt1; higher=worse.", "agent_question": "Are Euro-Area governments on a sustainable fiscal path?", "history_start": "1995-12-31", "history_years": 30.5, "product_class": "time-series", "tier": "Gold", "refresh": "quarterly", "source_apis": [ "Eurostat gov_10dd_edpt1 na_item=GD sector=S13 unit=PC_GDP geo=EA20 (General government consolidated gross debt, keyless)", "Eurostat gov_10dd_edpt1 na_item=B9 sector=S13 unit=PC_GDP geo=EA20 (Net lending/borrowing, keyless)" ], "mcp_description": "Returns a 0-100 Euro-Area fiscal sustainability gap score (0.6\u00d7debt/GDP vs the 60-120% Maastricht band + 0.4\u00d7deficit/GDP vs 0-6%, quarterly Eurostat EDP data since 1995) with confidence, top_drivers decomposition, and source_lineage. Call when the user asks about eurozone sovereign debt, government deficits, Maastricht compliance, or EU fiscal health, or when timing credit-spread assumptions on euro-denominated sovereign bond exposure." }, { "id": "ADW-354", "name": "Supply Chain Geopolitical Risk Index", "domain": "Trade/Geopolitical", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-354", "mcp_tool": "adw.adw_354", "sample": "https://alpinedataworks.com/showcase/adw-354", "description": "Weighted composite of FRED/BEA bilateral trade (China concentration, import trend, balance stress, imbalance ratio); higher=more risk.", "agent_question": "What geopolitical risk is embedded in US supply chains; is China dependence improving?", "history_start": "2002-01-01", "history_years": 24.5, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED/BEA IMPCH \u2014 US Imports of Goods from China (keyless)", "FRED/BEA EXPCH \u2014 US Exports of Goods to China (keyless)", "FRED/BEA IMPMX \u2014 US Imports of Goods from Mexico (keyless)", "FRED/BEA IMPCA \u2014 US Imports of Goods from Canada (keyless)", "FRED/BEA IMPKR \u2014 US Imports of Goods from South Korea (keyless)", "FRED/BEA BOPGSTB \u2014 US Trade Balance in Goods and Services (keyless)" ], "mcp_description": "Returns a 0-100 US supply-chain geopolitical risk index (China import share 40% plus import-flow and trade-balance z-scores; monthly FRED/BEA bilateral trade data since 2002) with score, trend, top_drivers, and source_lineage. Call when the user asks about supply chain risk, China dependence, decoupling, reshoring, tariffs, or trade-war exposure, or when timing supplier diversification, procurement audits, or supply-chain due-diligence reporting." }, { "id": "ADW-377", "name": "Clinical Trial Complexity Index", "domain": "Healthcare/Research", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-377", "mcp_tool": "adw.adw_377", "sample": "https://alpinedataworks.com/showcase/adw-377", "description": "5-dimension composite (late-phase, large-enrollment, industry-sponsor, RCT, blinding) over all recruiting/active ClinicalTrials.gov studies; baseline 50.", "agent_question": "Is the global clinical-trial landscape becoming more or less complex?", "history_start": "2010-01-31", "history_years": 16.4, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "clinicaltrials.gov/api/v2/studies \u2014 filter.overallStatus=RECRUITING,ACTIVE_NOT_RECRUITING", "clinicaltrials.gov/api/v2/studies \u2014 filter.advanced=AREA[Phase]PHASE3", "clinicaltrials.gov/api/v2/studies \u2014 filter.advanced=AREA[Phase]PHASE4", "clinicaltrials.gov/api/v2/studies \u2014 filter.advanced=AREA[EnrollmentCount]RANGE[1000,MAX]", "clinicaltrials.gov/api/v2/studies \u2014 filter.advanced=AREA[LeadSponsorClass]INDUSTRY", "clinicaltrials.gov/api/v2/studies \u2014 filter.advanced=AREA[DesignAllocation]RANDOMIZED", "clinicaltrials.gov/api/v2/studies \u2014 filter.advanced=AREA[DesignMasking]TRIPLE|QUADRUPLE" ], "mcp_description": "Returns a 0-100 Clinical Trial Complexity Index (weighted shares of late-phase, large-enrollment, industry-sponsored, RCT, and blinded trials in ClinicalTrials.gov active/recruiting snapshots; 50=baseline, monthly since 2010) with score, trend, top_drivers, and methodology_version. Call when the user asks about clinical-trial landscape complexity, trial design trends, or CRO capacity pressure, or when timing site-selection bids, site fees, or recruitment strategy." }, { "id": "ADW-382", "name": "Food Security Price Shock Index", "domain": "Commodities/Food", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-382", "mcp_tool": "adw.adw_382", "sample": "https://alpinedataworks.com/showcase/adw-382", "description": "Composite of IMF global food index (40%) + US food CPI (40%) + farm PPI (20%) via FRED keyless CSV; higher=more shock.", "agent_question": "Is there an acute food-price shock now, and how severe across global + US markets?", "history_start": "1947-01-01", "history_years": 79.5, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "fred.stlouisfed.org/graph/fredgraph.csv?id=PFOODINDEXM (keyless; IMF Primary Commodity Prices, NSA index 2016=100)", "fred.stlouisfed.org/graph/fredgraph.csv?id=CPIUFDSL (keyless; BLS CPI Food at Home, SA index 1982-84=100)", "fred.stlouisfed.org/graph/fredgraph.csv?id=WPU01 (keyless; BLS PPI Farm Products, NSA index 1982=100)" ], "mcp_description": "Returns a 0-100 food price shock severity score (IMF global food index, US food CPI, and farm PPI blended 40/40/20 on year-over-year and 3-month momentum, monthly since 1947) with percentile rank, trend, top_drivers, and FRED source_lineage. Call when the user asks about food inflation, grocery or commodity price spikes, food security, or agricultural costs, or when timing retail price increases, pass-through, or procurement decisions." }, { "id": "ADW-356", "name": "Global Volcanic Alert Level Index", "domain": "Natural Hazard", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-356", "mcp_tool": "adw.adw_356", "sample": "https://alpinedataworks.com/showcase/adw-356", "description": "Weighted-pressure index (WARNING=100, WATCH=66, ADVISORY=33) over all USGS HANS elevated volcanoes; baseline 50 = 5 mid-severity volcanoes.", "agent_question": "How elevated is US volcanic alert pressure right now?", "history_start": "2016-07-05", "history_years": 10.0, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "volcanoes.usgs.gov/hans-public/api/volcano/getElevatedVolcanoes (keyless, real-time)" ], "mcp_description": "Returns a 0-100 US volcanic alert pressure index (USGS HANS alert weights WARNING=100/WATCH=66/ADVISORY=33, summed and normalized to a 5-volcano baseline; daily, 10-year history) with score, elevated volcano names, and methodology version. Call when the user asks about volcano alerts, volcanic activity, eruption risk, volcanic unrest, or natural-hazard exposure, or when timing catastrophe loss-model runs or insured-property risk reviews near US volcanoes." }, { "id": "ADW-357", "name": "Drug Labeling Volatility Index", "domain": "Healthcare/Pharma Regulatory", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-357", "mcp_tool": "adw.adw_357", "sample": "https://alpinedataworks.com/showcase/adw-357", "description": "Rolling 12-month FDA drug-label count vs prior 12-month baseline via openFDA effective_time facet; >50 = elevated regulatory/labeling churn.", "agent_question": "Is drug labeling activity accelerating or decelerating vs baseline?", "history_start": "1972-01-03", "history_years": 54.5, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "api.fda.gov/drug/label.json (keyless)" ], "mcp_description": "Returns a 0-100 Drug Labeling Volatility Index (rolling 12-month openFDA drug label counts vs prior 12-month baseline; 50 = neutral 10% YoY; monthly since 1972) with score and source_lineage (openFDA effective_time window). Call when the user asks about FDA drug label changes, labeling activity acceleration, safety label or prescribing-information updates, or pharma regulatory intelligence, or when timing review-queue expansion and label-change parsing workflows (e.g., score crossing 60)." }, { "id": "ADW-383", "name": "Sovereign Debt Refinancing Cliff", "domain": "Macro Economics", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-383", "mcp_tool": "adw.adw_383", "sample": "https://alpinedataworks.com/showcase/adw-383", "description": "Sovereign debt refinancing pressure, tracking bidder participation as a leading indicator of liquidity stress and yield spikes.", "agent_question": "Low bidder participation is a leading indicator of liquidity stress and yield spikes before official rating downgrades.", "history_start": "1985-11-01", "history_years": 40.7, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Treasury Auction Participation Rates" ], "mcp_description": "Returns a 0-100 sovereign debt refinancing pressure score (U.S. Treasury auction bid-to-cover and bidder-class participation, normalized over 40 years since 1985) with pressure_score, bid_to_cover_trend, dealer_takedown_share, indirect_bidder_share, confidence, and methodology_version. Call when the user asks about Treasury auction demand, sovereign liquidity stress, refinancing cliffs, or yield-spike risk, or when timing duration changes, bond issuance, or rate-hedging decisions." }, { "id": "ADW-384", "name": "US Marine & Port Freight Cost Pressure Index", "domain": "Global Logistics", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-384", "mcp_tool": "adw.adw_384", "sample": "https://alpinedataworks.com/showcase/adw-384", "description": "Cost pressure in US marine and port freight, tracking dwell-time variance that precedes inventory holding-cost spikes.", "agent_question": "Variance in dwell times predicts downstream inventory holding cost spikes more accurately than average dwell time.", "history_start": "2008-12-01", "history_years": 17.6, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "Vessel AIS-Dwell-Time-Distribution" ], "mcp_description": "Returns a 0-100 US marine and port freight cost-pressure score (variance of vessel AIS dwell-time distributions at US ports, percentile-ranked against 17.6 years since 2008) with cost_pressure_score, dwell_variance, dwell_time_median, trend_direction, confidence, and methodology_version. Call when the user asks about port congestion, container dwell times, ocean freight costs, or supply-chain bottlenecks, or when timing inventory builds, warehouse commitments, or holding-cost budgets." }, { "id": "ADW-385", "name": "US Power-Grid Capacity Utilization Stress", "domain": "Energy Infrastructure", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-385", "mcp_tool": "adw.adw_385", "sample": "https://alpinedataworks.com/showcase/adw-385", "description": "Stress on US power-grid capacity utilization, tracking regional load pressure from demand surges such as AI training.", "agent_question": "Correlates AI training bursts with regional blackouts and energy arbitrage opportunities.", "history_start": "1976-06-01", "history_years": 50.1, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "Cloud-Provider-Region-Uptime-Logs" ], "mcp_description": "Returns a 0-100 US power-grid capacity-utilization stress score (regional load pressure inferred from cloud-provider region-uptime logs, history to 1976) with stress_score, region_scores, load_pressure, capacity_margin, trend_direction, confidence, and methodology_version. Call when the user asks about grid strain, AI-training demand surges, blackout risk, or regional power tightness, or when timing workload placement, power hedges, or energy-arbitrage entries." }, { "id": "ADW-386", "name": "Pharma Patent Exclusivity Velocity", "domain": "Healthcare", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-386", "mcp_tool": "adw.adw_386", "sample": "https://alpinedataworks.com/showcase/adw-386", "description": "The speed of generic drug entry after patent expiry, tracking formulary cost reductions and branded revenue erosion.", "agent_question": "Tracks speed of generic entry post-patent cliff to predict hospital formulary cost reductions and revenue erosion.", "history_start": "1954-12-01", "history_years": 71.6, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FDA-Orange-Book-Approvals" ], "mcp_description": "Returns a 0-100 pharma patent-exclusivity velocity score (speed of first-generic entry after patent and exclusivity expiry, computed from FDA Orange Book approval records) with median_days_to_first_generic, anda_approvals_trailing_12m, velocity_trend, and methodology_version. Call when the user asks about generic drug entry, patent cliffs, branded revenue erosion, or formulary savings, or when timing hospital drug-purchasing contracts and pharma revenue forecasts." }, { "id": "ADW-387", "name": "US Residential Electricity Cost Barrier", "domain": "Energy", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-387", "mcp_tool": "adw.adw_387", "sample": "https://alpinedataworks.com/showcase/adw-387", "description": "The cost barrier US residential electricity poses to households, including its drag on electrification and EV adoption.", "agent_question": "Longer permitting cycles significantly reduce residential EV adoption rates in high-density areas.", "history_start": "1978-11-01", "history_years": 47.7, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "Municipal-Charging-Station-Permit-Proces" ], "mcp_description": "Returns a 0-100 US residential electricity cost-barrier score (price-per-kWh history since 1978, percentile-normalized, plus municipal charging-station permit friction as a driver) with barrier_score, price_percentile, yoy_price_change, permit_friction, drivers, confidence, and methodology_version. Call when the user asks about household electricity costs, electrification headwinds, or EV-adoption barriers, or when timing charger deployment and EV market-entry decisions." }, { "id": "ADW-388", "name": "US Semiconductor Fab Utilization Tightness", "domain": "Semiconductors", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-388", "mcp_tool": "adw.adw_388", "sample": "https://alpinedataworks.com/showcase/adw-388", "description": "Tightness in US semiconductor fab utilization, tracking capacity strain and single-region dependency risk.", "agent_question": "High dependency on single-region fabrication correlates with extended order-fulfillment delays during regulatory shocks.", "history_start": "1976-06-01", "history_years": 50.1, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "Geopolitical Export-Control-Enforcement-" ], "mcp_description": "Returns a 0-100 US semiconductor fab-utilization tightness score (capacity strain plus single-region dependency risk, with export-control enforcement inputs; history to 1976) with tightness_score, capacity_strain, single_region_dependency, confidence, and methodology_version. Call when the user asks about chip supply tightness, fab capacity, or export-control exposure to chip lead times, or when timing procurement buffers, lead-time commitments, or second-source qualification." }, { "id": "ADW-390", "name": "US Commercial Liability Premium Volatility", "domain": "Insurance", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-390", "mcp_tool": "adw.adw_390", "sample": "https://alpinedataworks.com/showcase/adw-390", "description": "Volatility in US commercial liability insurance premiums, tracking spikes that precede rising cyber-incident frequency.", "agent_question": "Sudden premium spikes precede increased frequency of non-ransomware cyber incidents in high-risk sectors.", "history_start": "1999-07-01", "history_years": 27.0, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "Annual-Cyber-Insurance-Premium-Change-Pe" ], "mcp_description": "Returns a 0-100 US commercial-liability premium-volatility score (spike detection over 27 years of annual premium-change data since 1999) with volatility_score, premium_change_yoy, spike_flag, trend_direction, and methodology_version. Call when the user asks about insurance hard markets, liability premium spikes, or leading indicators of non-ransomware cyber-incident frequency, or when timing policy renewals, security-budget escalation, or incident-response pre-positioning." }, { "id": "ADW-391", "name": "Colorado River Basin Water-Stress Index", "domain": "Environment", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-391", "mcp_tool": "adw.adw_391", "sample": "https://alpinedataworks.com/showcase/adw-391", "description": "Water stress in the Colorado River Basin, tracking supply pressure on water-intensive industries in the region.", "agent_question": "High materiality scores predict higher cost of capital for water-intensive industries in stressed regions.", "history_start": "2010-01-01", "history_years": 16.5, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "Corporate Water Risk Disclosures vs. Loc" ], "mcp_description": "Returns a 0-100 Colorado River Basin water-stress score (corporate water-risk disclosures benchmarked against local basin supply conditions, since 2010) with stress_score, supply_pressure, percentile_rank, trend_direction, confidence, and methodology_version. Call when the user asks about Colorado River water stress, drought exposure, or water-intensive industry risk, or when timing financing, siting, or capex decisions for basin-exposed operations." }, { "id": "ADW-392", "name": "US Federal Monthly Budget Deficit Stress", "domain": "Public Finance", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-392", "mcp_tool": "adw.adw_392", "sample": "https://alpinedataworks.com/showcase/adw-392", "description": "Stress in the US federal monthly budget deficit, tracking the gap between revenue and spending.", "agent_question": "The gap between actual digital tax revenue and potential liability indicates erosion of the domestic tax base.", "history_start": "1980-10-01", "history_years": 45.8, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "OECD Digital Services Tax Receipts vs. E" ], "mcp_description": "Returns a 0-100 US federal budget deficit stress score (monthly federal receipts vs. outlays, z-scored against 45.8 years of history since FY1981) with stress_score, revenue_trend, spending_trend, historical_percentile, confidence, and methodology_version. Call when the user asks about the federal deficit, fiscal stress, tax-revenue erosion, Treasury borrowing needs, or shutdown risk, or when timing duration, auction-supply, or government-contract exposure decisions." }, { "id": "ADW-393", "name": "AI Energy Intensity", "domain": "Tech Infrastructure", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-393", "mcp_tool": "adw.adw_393", "sample": "https://alpinedataworks.com/showcase/adw-393", "description": "The energy intensity of AI workloads, tracking energy-per-token trends and marginal-cost inflection in LLM compute.", "agent_question": "Rising energy-per-token correlates with diminishing returns in LLM performance, signaling marginal cost inflection.", "history_start": "1985-10-01", "history_years": 40.8, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "Data Center PUE vs Compute Throughput" ], "mcp_description": "Returns a 0-100 AI energy-intensity score (data-center PUE trends vs compute-throughput growth, tracking energy-per-token direction) with trend, confidence, ranked top_drivers, methodology_version, and freshness. Call when the user asks about AI energy costs, energy-per-token, GPU power efficiency, data-center PUE, or LLM marginal-cost inflection, or when timing GPU capacity commitments, colocation power contracts, or inference-pricing decisions." }, { "id": "ADW-394", "name": "Supply-Chain Modal Shift", "domain": "Logistics", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-394", "mcp_tool": "adw.adw_394", "sample": "https://alpinedataworks.com/showcase/adw-394", "description": "Cargo modal shift between rail and truck, tracking disruption-driven rebalancing that precedes local inflation spikes.", "agent_question": "Measures cargo shift from rail to truck due to rail strikes, predicting local inflation spikes.", "history_start": "2001-01-01", "history_years": 25.5, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "AIS-Maritime-Automatic-Identification-Sy" ], "mcp_description": "Returns a 0-100 supply-chain modal-shift score (rail-to-truck cargo rebalancing inferred from AIS-observed freight flows, time series to 2001) with truck_share_delta, shift_velocity, disruption_flag, confidence, and methodology_version. Call when the user asks about rail strikes, trucking capacity, freight disruption, or local inflation risk, or when timing freight-rate locks, inventory pre-buys, or regional price forecasts." }, { "id": "ADW-395", "name": "US Cooling-Demand Grid Stress Index", "domain": "Climate", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-395", "mcp_tool": "adw.adw_395", "sample": "https://alpinedataworks.com/showcase/adw-395", "description": "Grid stress from US cooling demand during heat events, tracking localized transformer-failure and maintenance risk.", "agent_question": "High grid stress during heatwaves in UHI zones predicts localized transformer failures and disproportionate maintenance costs.", "history_start": "1895-01-01", "history_years": 131.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Smart-Grid-Load-Data + Satellite-LST-Ano" ], "mcp_description": "Returns a 0-100 US cooling-demand grid-stress index (smart-grid load anomalies fused with satellite land-surface-temperature anomalies, seasonal baseline back to 1895) with stress_score, load_anomaly, lst_anomaly, transformer_risk_flag, confidence, and methodology_version. Call when the user asks about heatwave grid strain, urban-heat-island load risk, or transformer-failure exposure, or when timing maintenance dispatch, crew pre-staging, or summer O&M budget decisions." }, { "id": "ADW-397", "name": "US Student-Loan Servicer Complaint Velocity", "domain": "Consumer Finance", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-397", "mcp_tool": "adw.adw_397", "sample": "https://alpinedataworks.com/showcase/adw-397", "description": "The velocity of US student-loan servicer complaints, tracking severity spikes that precede delinquency increases.", "agent_question": "Rising severity scores in servicer complaints precede spikes in delinquency rates and refinancing failure rates.", "history_start": "2012-03-31", "history_years": 14.3, "product_class": "time-series", "tier": "Gold", "refresh": "daily (CFPB Consumer Complaint DB)", "source_apis": [ "CFPB Complaint Logs (NLP Severity Score)" ], "mcp_description": "Returns a 0-100 US student-loan servicer complaint-velocity score (NLP-severity-weighted daily complaint flow from the CFPB complaint database, history to 2012) with severity_index, severity_trend, complaint_count, servicer_breakdown, and methodology_version. Call when the user asks about servicer quality, borrower distress, or delinquency early warning, or when timing credit-risk, SLABS, or refi-underwriting decisions ahead of official delinquency data." }, { "id": "ADW-400", "name": "EU-ETS Carbon Price Pressure (CBAM proxy)", "domain": "Climate Policy", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-400", "mcp_tool": "adw.adw_400", "sample": "https://alpinedataworks.com/showcase/adw-400", "description": "EU-ETS carbon price pressure as a CBAM proxy, tracking compliance deficits that precede tariff and cost inflation.", "agent_question": "Higher compliance deficits in key sectors predict increased tariffs and supply chain cost inflation.", "history_start": "1989-12-01", "history_years": 36.6, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Import Declaration Data vs. EU CBAM Regi" ], "mcp_description": "Returns a 0-100 EU-ETS carbon price pressure score (CBAM proxy: import declarations reconciled against EU CBAM Registry compliance, deficits by sector) with pressure_score, sector_deficits, deficit_trend, as_of, confidence, and methodology_version. Call when the user asks about EU carbon prices, CBAM tariff exposure, ETS compliance deficits, or carbon border costs, or when timing import contracts, hedges, or price escalators exposed to EU carbon pass-through." }, { "id": "ADW-401", "name": "US Commercial Insurance Renewal Spike", "domain": "Real Estate/Insurance", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-401", "mcp_tool": "adw.adw_401", "sample": "https://alpinedataworks.com/showcase/adw-401", "description": "Spikes in US commercial insurance renewal premiums, tracking year-over-year increases tied to rising office vacancy.", "agent_question": "Renewal premiums exceeding 15% YoY correlate with increased vacancy rates in Class B/C office assets.", "history_start": "1999-06-01", "history_years": 27.1, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "Carrier Renewal Quote Aggregates" ], "mcp_description": "Returns a 0-100 US commercial insurance renewal spike score (year-over-year premium change computed from carrier renewal quote aggregates, 27 years of history) with premium_yoy_pct, spike_flag, trend_direction, history_percentile, confidence, and methodology_version. Call when the user asks about commercial insurance renewal costs, hard-market pricing, or office operating-expense pressure, or when timing Class B/C office underwriting, NOI budgets, or hold/sell decisions." }, { "id": "ADW-402", "name": "US Consumer Loan Delinquency Stress", "domain": "Consumer Finance", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-402", "mcp_tool": "adw.adw_402", "sample": "https://alpinedataworks.com/showcase/adw-402", "description": "Stress in US consumer-loan delinquencies, tracking acceleration that leads residential eviction filings by about two months.", "agent_question": "Acceleration predicts residential eviction filings with a 2-month lag.", "history_start": "1988-01-01", "history_years": 38.5, "product_class": "time-series", "tier": "Gold", "refresh": "quarterly", "source_apis": [ "EIA-Electricity-Data-Consumer-Surveys" ], "mcp_description": "Returns a 0-100 US consumer-loan delinquency stress score (z-scored composite of EIA consumer-survey and utility-payment stress indicators, history to 1988) with stress_score, acceleration, percentile_rank, confidence, and methodology_version. Call when the user asks about consumer credit stress, delinquency trends, or eviction risk, or when timing collections staffing, bad-debt provisioning, or rental-portfolio exposure \u2014 acceleration leads residential eviction filings by about two months." }, { "id": "ADW-404", "name": "US Healthcare Admin Overhead", "domain": "Corporate-Efficiency-Stress", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-404", "mcp_tool": "adw.adw_404", "sample": "https://alpinedataworks.com/showcase/adw-404", "description": "The administrative overhead burden in US healthcare, tracking a gap index that correlates with inpatient margin compression.", "agent_question": "High-gap-index correlates with inpatient margin compression.", "history_start": "2009-06-01", "history_years": 17.1, "product_class": "time-series", "tier": "Gold", "refresh": "quarterly", "source_apis": [ "CMS-Medicare-Provider-Super-Data-Tool" ], "mcp_description": "Returns a 0-100 US healthcare administrative-overhead gap index (CMS Medicare provider cost and utilization data; administrative-cost growth vs. care-delivery growth, time series to 2009) with gap_index, admin_burden_trend, percentile_rank, confidence, and methodology_version. Call when the user asks about hospital admin overhead, billing or payer friction, or inpatient margin compression, or when timing hospital cost-reduction programs, RCM investments, or provider-credit reviews." }, { "id": "ADW-405", "name": "US Student-Loan Refinance Exhaustion", "domain": "Consumer-Credit-Stress", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-405", "mcp_tool": "adw.adw_405", "sample": "https://alpinedataworks.com/showcase/adw-405", "description": "Exhaustion in US student-loan refinancing capacity, tracking momentum tied to payroll declines and default velocity.", "agent_question": "Index-momentum correlates with NFP decline and default velocity.", "history_start": "2007-01-01", "history_years": 19.5, "product_class": "time-series", "tier": "Gold", "refresh": "quarterly", "source_apis": [ "Federal-Reserve-Student-Loan-Data-Portal" ], "mcp_description": "Returns a 0-100 US student-loan refinance exhaustion score (refinancing-capacity depletion and its momentum, from Federal Reserve Student-Loan Data Portal series, history to 2007) with exhaustion_score, momentum, default_velocity, confidence, and methodology_version. Call when the user asks about student-loan borrower stress, refinance capacity, consumer-credit deterioration, or default velocity, or when timing underwriting tightening, loss provisioning, or consumer-ABS positioning." }, { "id": "ADW-115", "name": "Bitcoin Network Activity Index", "domain": "Market/Crypto", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-115", "mcp_tool": "adw.adw_115", "sample": "https://alpinedataworks.com/showcase/adw-115", "description": "Daily Bitcoin network-activity momentum from on-chain transaction count, transfer volume, and fees \u2014 a 0-100 z-score composite (50 = normal, high = surge). Full history to the 2009 genesis block.", "agent_question": "Is Bitcoin on-chain network activity surging or unusually quiet right now?", "history_start": "2009-01-03", "history_years": 17.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "EPA (www.epa.gov)" ], "mcp_description": "Returns a 0-100 Bitcoin network-activity index (daily z-score composite of on-chain transaction count, transfer volume, and fees; 50 = normal, history to the 2009 genesis block) with score, trend, top_drivers, confidence, and methodology_version. Call when the user asks whether Bitcoin on-chain activity is surging or unusually quiet, about fee pressure or network congestion, or when timing BTC settlement batching, miner revenue planning, or crypto exposure decisions." }, { "id": "ADW-408", "name": "Climate Loss Exposure Monitor", "domain": "Climate/Risk", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-408", "mcp_tool": "adw.adw_408", "sample": "https://alpinedataworks.com/showcase/adw-408", "description": "Tracks climate loss pressure by monitoring rising flood-insurance claim frequency and severity by state.", "agent_question": "What is the current climate loss pressure indicated by flood-insurance claim trends by state?", "history_start": "2014-01-08", "history_years": 12.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "FEMA OpenFEMA DisasterDeclarationsSummaries API (www.fema.gov/api/open/v2/DisasterDeclarationsSummaries, keyless)" ], "mcp_description": "Returns a 0-100 climate loss pressure score by state (z-scored 90-day FEMA disaster-declaration frequency vs. a 12.5-year baseline, refreshed daily) with climate_loss_score, z_score, recent_90d_count, top_state_recent, and top_incident_type_recent. Call when the user asks about flood or disaster loss trends, state-level climate risk, or FEMA declaration activity, or when timing underwriting throttles, reinsurance purchases, or catastrophe reserve decisions." }, { "id": "ADW-409", "name": "Regulatory-Financial Impact Score", "domain": "Finance/Regulatory", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-409", "mcp_tool": "adw.adw_409", "sample": "https://alpinedataworks.com/showcase/adw-409", "description": "Measures regulatory burden by assessing the volume and weight of financial-sector rulemakings over the trailing 90 days.", "agent_question": "What is the current regulatory burden based on recent financial-sector rulemakings?", "history_start": "1995-06-01", "history_years": 31.1, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "federalregister.gov /api/v1/documents.json (keyless, conditions[agencies][]+conditions[type][] filters)" ], "mcp_description": "Returns a 0-100 regulatory-burden score for the U.S. financial sector (type-weighted Federal Register rulemaking volume, trailing 90 days, history to 1995) with weighted_current, weighted_prior, and current_90d_rules/proposed_rules/notices counts plus prior_90d_* baselines. Call when the user asks about regulatory burden, rulemaking pace, or financial-sector compliance load, or when timing compliance staffing, budgets, or policy-risk decisions." }, { "id": "ADW-411", "name": "Textile-Input Cost Pressure", "domain": "Retail/Commodities", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-411", "mcp_tool": "adw.adw_411", "sample": "https://alpinedataworks.com/showcase/adw-411", "description": "Signals textile and apparel cost pressure through the price momentum of cotton and wool inputs.", "agent_question": "What is the current cost pressure on the textile and apparel sector based on input prices?", "history_start": "1976-12-01", "history_years": 49.6, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "FRED fredgraph.csv \u2014 BLS PPI Farm products: Raw cotton (WPU015), keyless (fred.stlouisfed.org/graph/fredgraph.csv?id=WPU015)", "FRED fredgraph.csv \u2014 BLS PPI Textile products and apparel: Processed yarns and threads (WPU032), keyless (fred.stlouisfed.org/graph/fredgraph.csv?id=WPU032)" ], "mcp_description": "Returns a 0-100 textile and apparel input cost-pressure score (price momentum of BLS PPI raw cotton WPU015 and processed yarns WPU032, daily via FRED, history to 1976) with cotton_sub_score, cotton_ppi_yoy_pct, cotton_ppi_mom3_pct, textile_yarn_ppi_latest, and weight_note. Call when the user asks about cotton prices, fabric or apparel input inflation, or textile margins, or when timing fabric purchase orders, supplier negotiations, or retail price changes." }, { "id": "ADW-412", "name": "Seismic Catastrophe Risk Pulse", "domain": "Geophysical/Risk", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-412", "mcp_tool": "adw.adw_412", "sample": "https://alpinedataworks.com/showcase/adw-412", "description": "Daily 0-100 seismic-catastrophe risk momentum: global M5.5+ earthquake frequency + energy (USGS) z-scored vs trailing baseline.", "agent_question": "What is the current catastrophe-insurance risk based on recent seismic activity?", "history_start": "2015-01-01", "history_years": 11.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "USGS Earthquake Hazards Program - FDSN Event Web Service (earthquake.usgs.gov/fdsnws/event/1/query, keyless)" ], "mcp_description": "Returns a 0-100 seismic-catastrophe risk pulse (global M5.5+ earthquake frequency plus energy release from keyless USGS data, z-scored vs a trailing baseline, refreshed daily) with risk_pulse_score, risk_level, energy_z_score, count_z_score, composite_z_score, and window metadata. Call when the user asks about earthquake activity, seismic risk, or catastrophe-insurance exposure, or when timing cat-bond positions, reinsurance renewals, or earthquake-coverage decisions." }, { "id": "ADW-413", "name": "Open-Source Dependency Risk Index", "domain": "Tech", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-413", "mcp_tool": "adw.adw_413", "sample": "https://alpinedataworks.com/showcase/adw-413", "description": "Monitors OSS dependency volatility by analyzing release cadence and yanked-version rates across a top-package basket.", "agent_question": "What is the current volatility in open-source dependencies based on release and yank trends?", "history_start": "2015-01-01", "history_years": 11.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "PyPI JSON API (pypi.org/pypi//json, keyless, releases[].upload_time_iso_8601 + yanked flags)" ], "mcp_description": "Returns a 0-100 open-source dependency risk score (release-cadence variability and yanked-release rates across a top-PyPI-package basket, daily since 2015) with risk_level, packages_analyzed, avg_yanked_release_rate_pct, avg_cadence_cv, and per-package package_detail. Call when the user asks about open-source ecosystem volatility, dependency churn, yanked releases, or supply-chain stability, or when timing dependency upgrades, lockfile refreshes, or pre-release dependency freezes." }, { "id": "ADW-414", "name": "Essentials Wage vs Device-Safety Cross-Signal", "domain": "Health/Labor", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-414", "mcp_tool": "adw.adw_414", "sample": "https://alpinedataworks.com/showcase/adw-414", "description": "Analyzes the cross-signal between essentials wage growth and medical-device adverse-event rates.", "agent_question": "What is the current cross-signal between essentials wage growth and medical-device adverse events?", "history_start": "2007-03-31", "history_years": 19.3, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "BLS CES CES4200000003 \u2014 Retail Trade, Average Hourly Earnings (api.bls.gov, keyless)", "BLS CES CES6562000003 \u2014 Health Care and Social Assistance, Average Hourly Earnings (api.bls.gov, keyless)", "BLS CES CES7000000003 \u2014 Leisure and Hospitality, Average Hourly Earnings (api.bls.gov, keyless)", "BLS CES CES4300000003 \u2014 Transportation and Warehousing, Average Hourly Earnings (api.bls.gov, keyless)", "openFDA device adverse events (MAUDE) \u2014 api.fda.gov/device/event.json (keyless, rate-limited)" ], "mcp_description": "Returns a 0-100 essentials-wage subscore and cross-signal regime (YoY average-hourly-earnings growth across four BLS CES sectors crossed against openFDA MAUDE adverse-event surge) with regime, essentials_wage_yoy_pct, wage_subscore, device_event_surge_ratio, and recent/prior report counts. Call when the user asks about essential-worker wage pressure, medical-device safety trends, or staffing-stress risk, or when timing device rollouts, quality staffing, or med-tech risk reviews." }, { "id": "ADW-415", "name": "Heating-Demand Grid Stress", "domain": "Energy/Climate", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-415", "mcp_tool": "adw.adw_415", "sample": "https://alpinedataworks.com/showcase/adw-415", "description": "Evaluates grid heating stress by comparing heating-degree-days against commercial electricity demand.", "agent_question": "What is the current grid heating stress based on temperature and electricity demand?", "history_start": "2006-01-01", "history_years": 20.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "NOAA NCEI Climate-at-a-Glance national time-series (ncei.noaa.gov/access/monitoring/climate-at-a-glance, keyless)", "EIA v2 electricity/retail-sales (api.eia.gov/v2/electricity/retail-sales, EIA_API_KEY)" ], "mcp_description": "Returns a 0-100 grid heating-stress score (NOAA heating-degree-days z-scored against a multi-decade baseline, cross-read with EIA commercial electricity retail sales) with stress_score, stress_level, hdd_zscore, hdd_latest_value, hdd_baseline_mean, and data-month fields. Call when the user asks about cold-snap grid stress, heating demand, winter electricity load, or HDD anomalies, or when timing power procurement, demand-response dispatch, or energy-cost decisions." }, { "id": "ADW-416", "name": "Climate-Degree Groundwater Stress", "domain": "Climate/Agriculture", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-416", "mcp_tool": "adw.adw_416", "sample": "https://alpinedataworks.com/showcase/adw-416", "description": "Measures agricultural water stress by correlating degree-day anomalies with groundwater levels.", "agent_question": "What is the current agricultural water stress based on temperature anomalies and groundwater levels?", "history_start": "2009-07-21", "history_years": 17.0, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "USGS Water Data OGC API \u2014 daily groundwater depth-to-water (api.waterdata.usgs.gov/ogcapi/v0/collections/daily, keyless, parameter_code=72019, statistic_id=00003)", "NOAA NCEI Climate at a Glance \u2014 national Cooling Degree Days (ncei.noaa.gov/access/monitoring/climate-at-a-glance, keyless)" ], "mcp_description": "Returns a 0-100 agricultural water-stress read (USGS daily well depth-to-water Z-scores crossed with NOAA national cooling-degree-day anomalies) with groundwater_score, groundwater_mean_z, wells_analyzed, well_detail, cdd_anomaly_score, cdd_z_score, and cdd_target_month/year. Call when the user asks about drought, irrigation stress, aquifer depletion, or heat-driven crop risk, or when timing grain hedges, irrigation capex, or crop-insurance reviews." }, { "id": "ADW-417", "name": "Global Food-Insecurity Pulse", "domain": "Economy/Global", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-417", "mcp_tool": "adw.adw_417", "sample": "https://alpinedataworks.com/showcase/adw-417", "description": "Population-weighted momentum in insufficient-food-consumption (poor+borderline FCS) prevalence across a 24-country WFP HungerMap sample, current vs each country's own trailing 60-90 day baseline.", "agent_question": "Is global population-weighted food-insecurity prevalence rising or falling versus its recent trailing baseline right now?", "history_start": "2024-01-28", "history_years": 2.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "WFP HungerMap LIVE data API (api.hungermapdata.org/v2/adm0//countryData.json, keyless, fcsGraph daily series + population)" ], "mcp_description": "Returns a 0-100 food-insecurity pulse score (population-weighted momentum in insufficient-food-consumption prevalence across 24 WFP HungerMap countries vs each country's trailing 60-90-day baseline) with current and baseline prevalence, z_score, most_affected_adm0_id, and countries_analyzed. Call when the user asks about global hunger trends, food-crisis momentum, or humanitarian conditions, or when timing early-action funding, aid pre-positioning, or ag-commodity risk reviews." }, { "id": "ADW-418", "name": "Open-Source Vulnerability Density", "domain": "Tech/Security", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-418", "mcp_tool": "adw.adw_418", "sample": "https://alpinedataworks.com/showcase/adw-418", "description": "A 0-100 software-supply-chain risk-momentum index from OSV.dev (keyless): bins each of 18 top npm+PyPI packages' published vulnerabilities into 90-day windows and z-scores the recent 90 days vs the prior 8-window baseline. 50 = at baseline, >50 = accelerating disclosures.", "agent_question": "Is newly-disclosed vulnerability activity across widely-used npm and PyPI packages accelerating above its own baseline right now?", "history_start": "2008-01-01", "history_years": 18.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "OSV.dev query API (api.osv.dev/v1/query, keyless POST, vulns[].published ISO8601 dates binned into 90-day windows)" ], "mcp_description": "Returns a 0-100 software-supply-chain risk-momentum score (18 top npm/PyPI packages' OSV.dev vulnerabilities, recent 90 days z-scored vs the prior eight 90-day windows; 50 = baseline, higher = accelerating) with vulnerability_density_score, risk_level, basket_z, and recent_vulns_90d. Call when the user asks about open-source vulnerability trends, npm or PyPI supply-chain risk, or disclosure momentum, or when timing dependency upgrades, automerge policy, or a patching sprint." }, { "id": "ADW-419", "name": "Superfund Contamination Load", "domain": "Climate/Health", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-419", "mcp_tool": "adw.adw_419", "sample": "https://alpinedataworks.com/showcase/adw-419", "description": "Tracks EPA Superfund/NPL site status-change velocity (proposals, deletions, withdrawals, NFRAP determinations) vs a trailing baseline, alongside the live count of actively listed Final-NPL sites, as a proxy for environmental contamination-response pressure.", "agent_question": "What is the current Superfund/NPL site status-change activity level and active-site count by EPA region?", "history_start": "1977-06-01", "history_years": 49.1, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "EPA Envirofacts Data Service API \u2014 sems.envirofacts_site (data.epa.gov/dmapservice, keyless)" ], "mcp_description": "Returns a 0-100 Superfund contamination-load score (EPA SEMS status-change velocity \u2014 NPL proposals, deletions, withdrawals, NFRAP determinations \u2014 z-scored vs a trailing 100-day baseline) with recent_100d_status_changes, z_score, active_final_npl_site_count, and top_epa_region_recent. Call when the user asks about Superfund/NPL activity, contaminated sites, or EPA cleanup pressure, or when timing environmental due diligence, pollution-liability underwriting, or remediation bids." }, { "id": "ADW-422", "name": "Pharmacogenomic Adoption Index", "domain": "Health", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-422", "mcp_tool": "adw.adw_422", "sample": "https://alpinedataworks.com/showcase/adw-422", "description": "Tracks the pace of CPIC/ClinPGx pharmacogenomic guideline-system expansion (drug-gene pair growth, allele definitions, dosing-recommendation revisions) vs its own trailing-year baseline, as a leading indicator of PGx-guided prescribing adoption momentum.", "agent_question": "What is the current momentum of pharmacogenomic (PGx) guideline-system expansion, as a leading proxy for precision-medicine clinical adoption?", "history_start": "2013-09-01", "history_years": 12.9, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "ClinPGx/CPIC public API (api.cpicpgx.org/v1/change_log, /pair, /guideline \u2014 keyless, PostgREST-backed)" ], "mcp_description": "Returns a 0-100 pharmacogenomic adoption-momentum score (CPIC/ClinPGx drug-gene pair, allele, and dosing-recommendation change events z-scored against a trailing-year baseline) with pgx_adoption_score, z_pair_change_events, current_active_pairs, current_guidelines, and top_change_type_recent. Call when the user asks about PGx guideline expansion, precision-medicine adoption pace, or drug-gene pair growth, or when timing diagnostics coverage, test-panel, or market-access decisions." }, { "id": "ADW-424", "name": "Federal Web-Traffic Economy", "domain": "Government/Tech", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-424", "mcp_tool": "adw.adw_424", "sample": "https://alpinedataworks.com/showcase/adw-424", "description": "Tracks aggregate US federal .gov website visit volume (summed across all participating agencies) against its own trailing ~3-week baseline as a real-time proxy for federal digital-service demand.", "agent_question": "Is demand for US federal .gov digital services rising or falling right now versus its own trailing baseline?", "history_start": "2024-11-09", "history_years": 1.7, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "analytics.usa.gov /data/live/daily-sessions-30-days.json (keyless, GSA Digital Analytics Program public feed)" ], "mcp_description": "Returns a 0-100 federal digital-demand score (aggregate US federal .gov daily visit volume from GSA's Digital Analytics Program, scored against its own trailing ~3-week baseline; refreshed daily) with z_score, momentum_vs_baseline_pct, and recent-vs-baseline average daily visits. Call when the user asks about federal website traffic, .gov demand, government digital-service usage, or public-sector surge detection, or when timing staffing, capacity, or gov-facing go-to-market decisions." }, { "id": "ADW-426", "name": "Clinical-Trial Attrition Risk", "domain": "Health", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-426", "mcp_tool": "adw.adw_426", "sample": "https://alpinedataworks.com/showcase/adw-426", "description": "Tracks clinical trial attrition risk by analyzing the most recent 4,000 trials in the CTIS database ordered by decision date.", "agent_question": "Retrieve the latest clinical trial attrition risk data from the CTIS decision date stream.", "history_start": "2023-05-31", "history_years": 3.1, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "EU CTIS Public API (euclinicaltrials.eu/ctis-public-api/search, keyless POST; decisionDateOverall binned into 90-day windows; ctStatus 6/7 = Halted/Suspended)" ], "mcp_description": "Returns a 0-100 clinical-trial attrition risk score for the EU (halted/suspended counts in the latest 90-day CTIS decision window, z-scored against the rolling baseline of the 4,000 most recent trials) with risk_level, z_score_winsorized, recent_90d_decisions, and halted_or_suspended_count. Call when the user asks about halted or suspended trials, EU pipeline health, or drug-development risk, or when timing CRO capacity, enrollment contingencies, or biotech exposure decisions." }, { "id": "ADW-428", "name": "Agro-Ecological Yield Stress Index", "domain": "Economy", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-428", "mcp_tool": "adw.adw_428", "sample": "https://alpinedataworks.com/showcase/adw-428", "description": "Calculates agro-ecological yield stress by averaging weekly US Drought Monitor DSCI scores across the top 10 row-crop states.", "agent_question": "Get the agro-ecological yield stress index based on US Drought Monitor data for key crop states.", "history_start": "2002-12-24", "history_years": 23.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "US Drought Monitor Data Services \u2014 StateStatistics/GetDSCI (usdmdataservices.unl.edu, keyless)", "US Drought Monitor Data Services \u2014 USStatistics/GetDroughtSeverityStatisticsByAreaPercent (keyless)" ], "mcp_description": "Returns a 0-100 agro-ecological yield stress score (weekly US Drought Monitor DSCI averaged across the top 10 row-crop states, z-scored against a 23-year seasonal baseline) with agbelt_dsci_current, z_score, momentum_13w_dsci, and conus_d2plus_area_pct. Call when the user asks about drought impact on corn or soybean yields, Corn Belt growing conditions, or ag drought stress, or when timing grain hedges, forward crop purchases, or ag-commodity positioning." }, { "id": "ADW-430", "name": "Foreign-Entity Lobbying Index", "domain": "Government", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-430", "mcp_tool": "adw.adw_430", "sample": "https://alpinedataworks.com/showcase/adw-430", "description": "Quantifies foreign-entity lobbying activity by z-scoring recent FARA registrations against a 12-quarter baseline.", "agent_question": "Retrieve the foreign-entity lobbying index derived from recent FARA registration data.", "history_start": "1945-10-01", "history_years": 80.8, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "DOJ FARA eFile API \u2014 Registrants/json/New (efile.fara.gov/api/v1, keyless, MM-DD-YYYY date params)", "DOJ FARA eFile API \u2014 Registrants/json/Active (stock context, best-effort)" ], "mcp_description": "Returns a 0-100 foreign-entity lobbying index (z-score of new FARA registrations over the trailing 90 days against a 12-quarter DOJ baseline) with foreign_lobbying_score, z_score, recent_90d_new_registrations, baseline_90d_mean/std, active_registrant_stock, and top_registrant_state_recent. Call when the user asks about foreign influence, FARA activity, or foreign-government lobbying intensity, or when timing policy-risk hedges, government-affairs spend, or compliance business development." }, { "id": "ADW-431", "name": "Soil-Input-Stress Index", "domain": "Economy", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-431", "mcp_tool": "adw.adw_431", "sample": "https://alpinedataworks.com/showcase/adw-431", "description": "Assesses soil-input stress by comparing year-over-year Producer Price Index changes to a trailing 120-month baseline.", "agent_question": "Fetch the soil-input stress index based on Producer Price Index year-over-year changes.", "history_start": "1973-08-01", "history_years": 52.9, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "FRED fredgraph.csv \u2014 BLS PPI Chemicals and Allied Products: Fertilizer Materials (WPU0652), keyless (fred.stlouisfed.org/graph/fredgraph.csv?id=WPU0652)", "FRED fredgraph.csv \u2014 BLS PPI Chemicals and Allied Products: Other Agricultural Chemicals (WPU0653), keyless (fred.stlouisfed.org/graph/fredgraph.csv?id=WPU0653)" ], "mcp_description": "Returns a 0-100 soil-input stress score (year-over-year BLS fertilizer and agricultural-chemical PPI changes z-scored against a trailing 120-month baseline, daily, history to 1973) with fertilizer_ppi_yoy_pct, fertilizer_z_score, fertilizer_sub_score, and baseline mean/std. Call when the user asks about fertilizer prices, crop-input cost inflation, or agricultural input stress, or when timing fertilizer procurement, prepay pricing, or farm-budget decisions." }, { "id": "ADW-432", "name": "Water-Compliance-Risk Score", "domain": "Climate", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-432", "mcp_tool": "adw.adw_432", "sample": "https://alpinedataworks.com/showcase/adw-432", "description": "Evaluates water compliance risk using 13 consecutive trailing 90-day windows of ICIS entry data with a 14-day lag guard.", "agent_question": "Retrieve the water compliance risk score from the ICIS entry data windows.", "history_start": "1983-05-25", "history_years": 43.1, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "EPA ECHO case_rest_services.get_cases (echodata.epa.gov, keyless; Referer-gated)" ], "mcp_description": "Returns a 0-100 water compliance risk score (current 90-day EPA ICIS water enforcement case volume z-scored against trailing 90-day baseline windows, 14-day entry-lag guard) with CWA, SDWA, and federal-penalty case counts, baseline mean/std, and z_score. Call when the user asks about EPA water enforcement intensity, Clean Water Act or Safe Drinking Water Act risk, or when timing environmental audits, discharge-permit reviews, or water-utility exposure decisions." }, { "id": "ADW-434", "name": "Global Air-Quality Health Load", "domain": "Health", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-434", "mcp_tool": "adw.adw_434", "sample": "https://alpinedataworks.com/showcase/adw-434", "description": "Calculates global air-quality health load by comparing recent PM2.5 means to an 85-day baseline for each city.", "agent_question": "Retrieve the global air-quality health load data based on recent PM2.5 levels.", "history_start": "2022-10-31", "history_years": 3.7, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Open-Meteo Air Quality API (air-quality-api.open-meteo.com/v1/air-quality, keyless, hourly pm2_5, past_days=92, multi-location)" ], "mcp_description": "Returns a 0-100 global air-quality health load score (recent city PM2.5 means vs an 85-day per-city baseline, Open-Meteo hourly data, daily refresh) with mean_city_z, cities_analyzed, WHO-guideline exceedance count/pct (who_guideline_ug_m3), and hottest_city/coolest_city extremes. Call when the user asks about global air pollution, PM2.5 spikes, wildfire-smoke health load, or WHO guideline breaches, or when timing respirator/purifier inventory, travel advisories, or outdoor-work scheduling." }, { "id": "ADW-435", "name": "AI-Inference Cost Efficiency", "domain": "Tech", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-435", "mcp_tool": "adw.adw_435", "sample": "https://alpinedataworks.com/showcase/adw-435", "description": "Determines AI inference cost efficiency by filtering text-output models and calculating blended cost per million tokens.", "agent_question": "Fetch the AI inference cost efficiency metrics for text-output models.", "history_start": "2024-12-23", "history_years": 1.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "OpenRouter model catalog API (openrouter.ai/api/v1/models, keyless)" ], "mcp_description": "Returns a 0-100 AI inference cost-efficiency score for text-output models (blended USD per million tokens from the OpenRouter catalog, 90-day window z-scored against baseline) with recent median and p10-floor prices, baseline median, and z_median/z_p10_floor/z_composite. Call when the user asks about LLM pricing trends, cost per token, or whether inference is getting cheaper, or when timing model-routing changes, committed-spend negotiations, or AI COGS forecasts." }, { "id": "ADW-436", "name": "Software Dependency Risk", "domain": "Tech", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-436", "mcp_tool": "adw.adw_436", "sample": "https://alpinedataworks.com/showcase/adw-436", "description": "Assesses software dependency risk by analyzing release frequency and download volume z-scores against historical baselines.", "agent_question": "Retrieve the software dependency risk scores for specific packages.", "history_start": "2013-06-01", "history_years": 13.1, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Packagist p2 release metadata (repo.packagist.org/p2/{vendor}/{package}.json, keyless, tagged-release ISO8601 times)", "Packagist download stats (packagist.org/packages/{vendor}/{package}/stats/all.json?average=monthly, keyless, monthly install counts)" ], "mcp_description": "Returns a 0-100 software dependency risk score for a basket of PHP/Composer packages (release-frequency and download-volume z-scores against 13 years of Packagist baselines, refreshed daily) with risk_level, basket_z, stalest_package, release_window_days, and packages_analyzed. Call when the user asks about package health, abandonware risk, Composer dependency hygiene, or supply-chain exposure, or when timing a dependency migration, framework upgrade, or maintenance sprint." }, { "id": "ADW-439", "name": "Carbon Credit Liquidity Index", "domain": "Energy", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-439", "mcp_tool": "adw.adw_439", "sample": "https://alpinedataworks.com/showcase/adw-439", "description": "Measures carbon credit liquidity by analyzing trailing one-year daily trading bars and excluding symbols with no recent trades.", "agent_question": "Fetch the carbon credit liquidity index based on recent daily trading data.", "history_start": "2022-03-07", "history_years": 4.3, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Yahoo Finance v8 chart API (query1.finance.yahoo.com/v8/finance/chart, keyless) \u2014 daily OHLCV for KRBN, KCCA, KEUA carbon-allowance ETFs" ], "mcp_description": "Returns a 0-100 carbon credit liquidity score (z-scored composite of trailing one-year daily trading bars for the KRBN, KCCA, and KEUA carbon-allowance ETFs, refreshed daily) with z_composite, per_symbol detail, symbols_used, symbols_failed, and window_trading_days. Call when the user asks about carbon market liquidity, allowance ETF tradability, or EUA/CCA market depth, or when timing compliance purchases, carbon position entries or exits, or order sizing." }, { "id": "ADW-P01", "name": "Community Intelligence Package", "domain": "V2/Place-Intelligence", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-p01", "mcp_tool": "adw.adw_p01", "sample": "https://alpinedataworks.com/showcase/adw-p01", "description": "A bundle of place-intelligence layers profiling everyday quality of life in a given community.", "agent_question": "What is it like to live here?", "history_start": "2010-01-01", "history_years": 16.5, "product_class": "package", "tier": "Package", "refresh": "per source cadence", "source_apis": [ "AlpineDataWorks V2 county layers" ], "mcp_description": "Returns a 0-100 community quality-of-life composite for any US county (9 AlpineDataWorks V2 county layers joined on county_fips) with composite_score, component_scores, named drivers, and layer coverage. Call when the user asks what it's like to live in a place or compares counties for relocation or hiring, or when timing site-selection, expansion, or community-investment decisions that hinge on local livability." }, { "id": "ADW-P02", "name": "Family Intelligence Package", "domain": "V2/Place-Intelligence", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-p02", "mcp_tool": "adw.adw_p02", "sample": "https://alpinedataworks.com/showcase/adw-p02", "description": "A bundle of place-intelligence layers scoring an area's suitability for raising a family.", "agent_question": "Is this a good place to raise a family?", "history_start": "2010-01-01", "history_years": 16, "product_class": "package", "tier": "Package", "refresh": "per source cadence", "source_apis": [ "AlpineDataWorks V2 county layers" ], "mcp_description": "Returns a 0-100 family-suitability score for any US county (composite of 11 AlpineDataWorks V2 place-intelligence layers, joined on county_fips) with composite_score, component_scores, drivers, and coverage. Call when the user asks whether an area is a good place to raise a family or compares counties for relocation, or when timing a move, home purchase, or family-oriented site selection." }, { "id": "ADW-P03", "name": "Retirement Intelligence Package", "domain": "V2/Place-Intelligence", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-p03", "mcp_tool": "adw.adw_p03", "sample": "https://alpinedataworks.com/showcase/adw-p03", "description": "A bundle of place-intelligence layers scoring an area's suitability for retirement living.", "agent_question": "Is this a good place to retire?", "history_start": "2016-01-01", "history_years": 10.5, "product_class": "package", "tier": "Package", "refresh": "per source cadence", "source_apis": [ "AlpineDataWorks V2 county layers" ], "mcp_description": "Returns a 0-100 retirement-suitability score for any US county (composite of 8 AlpineDataWorks place-intelligence layers spanning health, cost, climate risk, and livability, joined on county_fips) with composite_score, per-layer component_scores, ranked drivers, and coverage. Call when the user asks whether a place is a good spot to retire or compares retirement destinations, or when timing a relocation, retirement home purchase, or senior-housing market entry." }, { "id": "ADW-P04", "name": "Business Expansion Package", "domain": "V2/Place-Intelligence", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-p04", "mcp_tool": "adw.adw_p04", "sample": "https://alpinedataworks.com/showcase/adw-p04", "description": "A bundle of place-intelligence layers scoring locations for business expansion potential.", "agent_question": "Where should a business expand?", "history_start": "2017-01-01", "history_years": 7, "product_class": "package", "tier": "Package", "refresh": "per source cadence", "source_apis": [ "AlpineDataWorks V2 county layers" ], "mcp_description": "Returns a 0-100 business-expansion score for US counties (composite of six AlpineDataWorks county layers \u2014 employment, consumer, housing, telecom/broadband, population demographics, business density \u2014 joined on county_fips) with composite_score, component_scores, drivers, and coverage. Call when the user asks about business expansion, site selection, or comparing counties for a new location, or when timing a market-entry, franchise, or store-siting decision." }, { "id": "ADW-P05", "name": "Consumer Convenience Package", "domain": "V2/Place-Intelligence", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-p05", "mcp_tool": "adw.adw_p05", "sample": "https://alpinedataworks.com/showcase/adw-p05", "description": "A bundle of place-intelligence layers measuring the day-to-day convenience of living in an area.", "agent_question": "How convenient is daily life here?", "history_start": "2013-01-01", "history_years": 13, "product_class": "package", "tier": "Package", "refresh": "per source cadence", "source_apis": [ "AlpineDataWorks V2 county layers" ], "mcp_description": "Returns a 0-100 county convenience score (composite of 3 AlpineDataWorks place-intelligence layers joined on county_fips) with composite_score, component_scores, drivers, and coverage. Call when the user asks how convenient daily life is in a county, compares places to live, or evaluates relocation targets \u2014 or when timing site-selection, housing-investment, or market-expansion decisions that hinge on local quality-of-life." }, { "id": "ADW-P06", "name": "Risk Intelligence Package", "domain": "V2/Place-Intelligence", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-p06", "mcp_tool": "adw.adw_p06", "sample": "https://alpinedataworks.com/showcase/adw-p06", "description": "A bundle of place-intelligence layers profiling the local hazards and risks of a given place.", "agent_question": "What can go wrong here?", "history_start": "2020-12-01", "history_years": 5.6, "product_class": "package", "tier": "Package", "refresh": "per source cadence", "source_apis": [ "AlpineDataWorks V2 county layers" ], "mcp_description": "Returns a 0-100 place-risk profile for a US county (composite of 8 AlpineDataWorks V2 hazard layers \u2014 severe weather, seismic, natural-hazard cost, air quality, drinking water, community health \u2014 joined on county_fips) with composite_score, component_scores, ranked drivers, and coverage. Call when the user asks what can go wrong in a place or about hazard and environmental exposure for a county or market, or when timing site-selection, underwriting, lending, or expansion decisions." }, { "id": "ADW-P07", "name": "Infrastructure Intelligence Package", "domain": "V2/Place-Intelligence", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-p07", "mcp_tool": "adw.adw_p07", "sample": "https://alpinedataworks.com/showcase/adw-p07", "description": "A bundle of place-intelligence layers rating the strength of local physical and digital infrastructure.", "agent_question": "How strong is the physical/digital infrastructure?", "history_start": "2013-01-01", "history_years": 13.5, "product_class": "package", "tier": "Package", "refresh": "per source cadence", "source_apis": [ "AlpineDataWorks V2 county layers" ], "mcp_description": "Returns a 0-100 county infrastructure-strength score (composite of 9 AlpineDataWorks V2 place-intelligence layers spanning physical and digital infrastructure, joined on county_fips) with composite_score, component_scores, drivers, and coverage. Call when the user asks about broadband, power, road, bridge, or overall infrastructure quality for a US county or region, or when timing site-selection, expansion, or infrastructure-dependent capital deployment." }, { "id": "ADW-P08", "name": "Travel, Tourism & Heritage Package", "domain": "V2/Place-Intelligence", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-p08", "mcp_tool": "adw.adw_p08", "sample": "https://alpinedataworks.com/showcase/adw-p08", "description": "A bundle of place-intelligence layers cataloging local attractions, tourism assets, and heritage sites.", "agent_question": "What is worth visiting here?", "history_start": "2006-01-01", "history_years": 20, "product_class": "package", "tier": "Package", "refresh": "per source cadence", "source_apis": [ "AlpineDataWorks V2 county layers" ], "mcp_description": "Returns a 0-100 travel, tourism, and heritage appeal score for any US county (composite of AlpineDataWorks place-intelligence layers cataloging attractions, tourism assets, and heritage sites, joined on county_fips) with composite_score, component_scores, named drivers, and coverage. Call when the user asks what is worth visiting in a place, which destinations to compare, or where tourism assets cluster \u2014 or when timing itinerary, site-selection, or market-entry decisions." }, { "id": "ADW-P09", "name": "Real Estate Intelligence Package", "domain": "V2/Place-Intelligence", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-p09", "mcp_tool": "adw.adw_p09", "sample": "https://alpinedataworks.com/showcase/adw-p09", "description": "A bundle of place-intelligence layers assessing the strength of a local property and housing market.", "agent_question": "Is this a good property or market?", "history_start": "2016-01-08", "history_years": 10.5, "product_class": "package", "tier": "Package", "refresh": "per source cadence", "source_apis": [ "AlpineDataWorks V2 county layers" ], "mcp_description": "Returns a 0-100 local real-estate market strength score for any US county (composite of 8 AlpineDataWorks place-intelligence layers joined on county_fips) with composite_score, component_scores, named drivers, and coverage. Call when the user asks whether a property, housing market, county, or metro is a good buy, rental, or development target, or when timing a purchase, lot acquisition, or market-entry decision." }, { "id": "ADW-P10", "name": "Healthcare Planning Package", "domain": "V2/Place-Intelligence", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-p10", "mcp_tool": "adw.adw_p10", "sample": "https://alpinedataworks.com/showcase/adw-p10", "description": "A bundle of place-intelligence layers mapping local healthcare demand, capacity, and risk.", "agent_question": "Where is healthcare demand or risk?", "history_start": "2020-12-01", "history_years": 5.6, "product_class": "package", "tier": "Package", "refresh": "per source cadence", "source_apis": [ "AlpineDataWorks V2 county layers" ], "mcp_description": "Returns a 0-100 county healthcare planning score (composite of 6 AlpineDataWorks place-intelligence layers covering local demand, capacity, and risk, joined on county_fips) with composite_score, component_scores, per-layer drivers, and coverage. Call when the user asks about healthcare demand, provider capacity, underserved counties, or health risk by place, or when timing clinic site selection, network expansion, or community health investment decisions." }, { "id": "ADW-P11", "name": "Insurance Intelligence Package", "domain": "V2/Place-Intelligence", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-p11", "mcp_tool": "adw.adw_p11", "sample": "https://alpinedataworks.com/showcase/adw-p11", "description": "A bundle of place-intelligence layers profiling local underwriting risk for insurers.", "agent_question": "What is the underwriting risk?", "history_start": "2016-01-01", "history_years": 10, "product_class": "package", "tier": "Package", "refresh": "per source cadence", "source_apis": [ "AlpineDataWorks V2 county layers" ], "mcp_description": "Returns a 0-100 county underwriting-risk composite (8 AlpineDataWorks V2 place-intelligence layers joined on county_fips) with composite_score, per-layer component_scores, ranked drivers, and coverage. Call when the user asks about underwriting risk, insurance exposure, or a county's hazard and property risk profile, or when timing appetite changes, rate filings, quote triage, or territory expansion." }, { "id": "ADW-P12", "name": "Government Planning Package", "domain": "V2/Place-Intelligence", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-p12", "mcp_tool": "adw.adw_p12", "sample": "https://alpinedataworks.com/showcase/adw-p12", "description": "A bundle of place-intelligence layers highlighting where public investment is most needed, for government planning.", "agent_question": "Where should public investment go?", "history_start": "2013-12-31", "history_years": 12.5, "product_class": "package", "tier": "Package", "refresh": "per source cadence", "source_apis": [ "AlpineDataWorks V2 county layers" ], "mcp_description": "Returns a 0-100 public-investment-need score per U.S. county (composite of 9 AlpineDataWorks place-intelligence layers joined on county_fips) with composite_score, component_scores, named drivers, and coverage. Call when the user asks where public investment, grants, or infrastructure spending is most needed, which counties are underserved, or when timing capital-improvement plans, grant applications, or district-level budget allocations." }, { "id": "ADW-P13", "name": "Logistics Intelligence Package", "domain": "V2/Place-Intelligence", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-p13", "mcp_tool": "adw.adw_p13", "sample": "https://alpinedataworks.com/showcase/adw-p13", "description": "A bundle of place-intelligence layers rating the strength of the local freight and movement network.", "agent_question": "How strong is the movement network?", "history_start": "2017-12-31", "history_years": 8.5, "product_class": "package", "tier": "Package", "refresh": "per source cadence", "source_apis": [ "AlpineDataWorks V2 county layers" ], "mcp_description": "Returns a 0-100 county freight-and-movement network strength score (composite of 6 AlpineDataWorks place-intelligence layers joined on county_fips) with composite_score, component_scores, per-layer drivers, and coverage. Call when the user asks about logistics strength, freight access, distribution-network quality, or how strong a county's movement network is, or when timing site selection, warehouse placement, or market-entry decisions." }, { "id": "ADW-P14", "name": "AI Infrastructure Package", "domain": "V2/Place-Intelligence", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-p14", "mcp_tool": "adw.adw_p14", "sample": "https://alpinedataworks.com/showcase/adw-p14", "description": "A bundle of place-intelligence layers mapping where AI-ready infrastructure and data-center capacity are concentrated.", "agent_question": "Where is AI-ready infrastructure concentrated?", "history_start": "2018-12-31", "history_years": 7.5, "product_class": "package", "tier": "Package", "refresh": "per source cadence", "source_apis": [ "AlpineDataWorks V2 county layers" ], "mcp_description": "Returns a 0-100 county-level concentration score for AI-ready infrastructure and data-center capacity (composite of 6 AlpineDataWorks V2 place-intelligence layers joined on county_fips) with composite_score, component_scores, drivers, and coverage. Call when the user asks where AI-ready infrastructure or data-center capacity is concentrated, which counties can support AI build-out, or when timing data-center site selection, land acquisition, or market-entry decisions." }, { "id": "ADW-P15", "name": "Health & Safety MVP Package", "domain": "V2/Place-Intelligence", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-p15", "mcp_tool": "adw.adw_p15", "sample": "https://alpinedataworks.com/showcase/adw-p15", "description": "A bundle of place-intelligence layers profiling the current health and safety risk of a location.", "agent_question": "What is the current health and safety risk profile here?", "history_start": "2020-01-01", "history_years": 6.5, "product_class": "package", "tier": "Package", "refresh": "per source cadence", "source_apis": [ "AlpineDataWorks V2 county layers" ], "mcp_description": "Returns a 0-100 health-and-safety risk profile for a US county (composite of 7 AlpineDataWorks V2 place-intelligence layers joined on county_fips, refreshed at each source's cadence) with composite_score, component_scores, drivers, and coverage. Call when the user asks about a location's health and safety risk, local hazards, or community health conditions, or when timing site selection, underwriting, relocation, or expansion decisions." }, { "id": "ADW-P16", "name": "Move Mode Workflow Package", "domain": "V2/Place-Intelligence", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-p16", "mcp_tool": "adw.adw_p16", "sample": "https://alpinedataworks.com/showcase/adw-p16", "description": "A bundle of place-intelligence layers for comparing, shortlisting, and choosing where to move.", "agent_question": "Where should I move, compare, or shortlist?", "history_start": "2010-01-01", "history_years": 16.5, "product_class": "package", "tier": "Package", "refresh": "per source cadence", "source_apis": [ "AlpineDataWorks V2 county layers" ], "mcp_description": "Returns a 0-100 county move-suitability composite (12 AlpineDataWorks V2 place-intelligence layers joined on county_fips) with composite_score, per-layer component_scores, ranked drivers, and coverage. Call when the user asks about where to move, comparing two counties or metros, or building a relocation shortlist, or when timing a household move, employee transfer, or remote-work location decision that needs side-by-side county evidence." }, { "id": "ADW-P17", "name": "Deep Health Package", "domain": "V2/Place-Intelligence", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-p17", "mcp_tool": "adw.adw_p17", "sample": "https://alpinedataworks.com/showcase/adw-p17", "description": "A bundle of place-intelligence layers breaking down the drivers of local health risk beneath the headline score.", "agent_question": "What is driving health risk below the headline score?", "history_start": "2020-12-01", "history_years": 5.6, "product_class": "package", "tier": "Package", "refresh": "per source cadence", "source_apis": [ "AlpineDataWorks V2 county layers" ], "mcp_description": "Returns a 0-100 county health-risk breakdown (composite of 8 AlpineDataWorks V2 place-intelligence layers joined on county_fips) with composite_score, per-layer component_scores, ranked drivers, and coverage. Call when the user asks what is driving health risk in a county beneath the headline score, why a place scores as unhealthy, or how counties compare \u2014 or when timing market entry, provider-network expansion, or community-health investment." }, { "id": "ADW-P18", "name": "Weather Severity Index Package", "domain": "V2/Place-Intelligence", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-p18", "mcp_tool": "adw.adw_p18", "sample": "https://alpinedataworks.com/showcase/adw-p18", "description": "A bundle of place-intelligence layers measuring how abnormal, severe, and changing local weather risk is.", "agent_question": "How abnormal, severe, or changing is the local weather risk?", "history_start": "2016-01-01", "history_years": 10.5, "product_class": "package", "tier": "Package", "refresh": "per source cadence", "source_apis": [ "AlpineDataWorks V2 county layers" ], "mcp_description": "Returns a 0-100 county weather-severity index (composite of 5 AlpineDataWorks V2 county layers \u2014 severe-weather risk, natural-hazard pressure, climate-disaster cost trend, air quality, drinking-water violations \u2014 joined on county_fips across ~3,200 US counties) with composite_score, component_scores, drivers, and coverage. Call when the user asks how abnormal, severe, or changing local weather or climate risk is, or when timing property, insurance, site-selection, or relocation decisions." }, { "id": "ADW-P19", "name": "Earthquake & Seismic Package", "domain": "V2/Place-Intelligence", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-p19", "mcp_tool": "adw.adw_p19", "sample": "https://alpinedataworks.com/showcase/adw-p19", "description": "A bundle of place-intelligence layers profiling local earthquake, fault, and ground-shaking risk.", "agent_question": "What is the local earthquake, fault, and shake-risk profile?", "history_start": "2016-01-08", "history_years": 10.5, "product_class": "package", "tier": "Package", "refresh": "per source cadence", "source_apis": [ "AlpineDataWorks V2 county layers" ], "mcp_description": "Returns a 0-100 county earthquake and seismic risk profile (composite of 2 AlpineDataWorks V2 county layers covering fault and ground-shaking hazard, joined on county_fips) with composite_score, component_scores, drivers, and coverage. Call when the user asks about local earthquake risk, fault proximity, or shake hazard for a county or address, or when timing site selection, property underwriting, or seismic-resilience spending." }, { "id": "ADW-P21", "name": "Environmental Burden Package", "domain": "V2/Place-Intelligence", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-p21", "mcp_tool": "adw.adw_p21", "sample": "https://alpinedataworks.com/showcase/adw-p21", "description": "A bundle of place-intelligence layers mapping environmental exposures, regulated facilities, and toxic burdens shaping a place.", "agent_question": "What environmental exposures, regulated facilities, and toxic burdens shape this place?", "history_start": "2015-01-01", "history_years": 10, "product_class": "package", "tier": "Package", "refresh": "per source cadence", "source_apis": [ "AlpineDataWorks V2 county layers" ], "mcp_description": "Returns a 0-100 county environmental burden score (composite of 3 ADW place-intelligence layers \u2014 exposures, regulated facilities, toxic burdens \u2014 joined on county_fips) with composite_score, component_scores, drivers, and coverage. Call when the user asks about pollution, regulated facilities, toxic releases, or environmental risk in a US county, or when timing site selection, underwriting, or due diligence." }, { "id": "ADW-P22", "name": "Transportation & Mobility Package", "domain": "V2/Place-Intelligence", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-p22", "mcp_tool": "adw.adw_p22", "sample": "https://alpinedataworks.com/showcase/adw-p22", "description": "A bundle of place-intelligence layers rating the local movement network for people, goods, and services.", "agent_question": "How strong is the local movement network for people, goods, and services?", "history_start": "2013-01-01", "history_years": 13.5, "product_class": "package", "tier": "Package", "refresh": "per source cadence", "source_apis": [ "AlpineDataWorks V2 county layers" ], "mcp_description": "Returns a 0-100 county movement-network strength score (composite of 5 AlpineDataWorks V2 place-intelligence layers joined on county_fips) with composite_score, component_scores, drivers, and coverage. Call when the user asks about local transportation, transit, commute, freight, or road-network strength for a county or region, or when timing site selection, distribution-network expansion, or relocation decisions that hinge on mobility infrastructure." }, { "id": "ADW-P23", "name": "Agriculture & Rural Resilience Package", "domain": "V2/Place-Intelligence", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-p23", "mcp_tool": "adw.adw_p23", "sample": "https://alpinedataworks.com/showcase/adw-p23", "description": "A bundle of place-intelligence layers measuring the resilience of rural land, agriculture, and food supply in a region.", "agent_question": "How resilient is rural land, agriculture, and food supply in this region?", "history_start": "2002-01-01", "history_years": 24, "product_class": "package", "tier": "Package", "refresh": "per source cadence", "source_apis": [ "AlpineDataWorks V2 county layers" ], "mcp_description": "Returns a 0-100 agriculture and rural resilience score for any US county (composite of four AlpineDataWorks V2 county layers joined on county_fips) with composite_score, per-layer component_scores, ranked drivers, and coverage. Call when the user asks about farmland risk, agricultural stability, rural land quality, or food-supply resilience in a county or region, or when timing farmland acquisition, agricultural lending, or supply-sourcing decisions." }, { "id": "ADW-P24", "name": "Population & Business Baseline Package", "domain": "V2/Place-Intelligence", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-p24", "mcp_tool": "adw.adw_p24", "sample": "https://alpinedataworks.com/showcase/adw-p24", "description": "A bundle of place-intelligence layers providing the population and business-activity baseline behind place scores.", "agent_question": "What is the denominator and economic baseline behind the place score?", "history_start": "2013-01-01", "history_years": 10, "product_class": "package", "tier": "Package", "refresh": "per source cadence", "source_apis": [ "AlpineDataWorks V2 county layers" ], "mcp_description": "Returns a 0-100 population-and-business baseline score for any US county (composite of 4 AlpineDataWorks V2 place-intelligence layers joined on county_fips) with composite_score, component_scores, drivers, and coverage. Call when the user asks about a county's population denominator, business activity, economic base, or the market size behind a place score, or when timing site-selection, expansion-screening, or per-capita normalization decisions." }, { "id": "ADW-500", "name": "Housing Affordability Index", "domain": "Real Estate", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-500", "mcp_tool": "adw.adw_500", "sample": "https://alpinedataworks.com/showcase/adw-500", "description": "Per-county 0-100 score of local housing affordability, mapped across all 3,222 US counties.", "agent_question": "How affordable is housing in this county?", "history_start": "2009-01-01", "history_years": 16, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "US Census ACS 5-Year API (api.census.gov/data/{2009..2023}/acs/acs5?get=B25077_001E,B25064_001E,B19013_001E&for=county:*) \u2014 verified live, 3,222 county rows, key required", "FHFA Annual House Price Index by county via FRED (api.stlouisfed.org/fred/series/observations, series ATNHPIUS{county_fips}A) \u2014 verified live, annual back to 1975 for larger counties" ], "mcp_description": "Returns a 0-100 county-level housing affordability score (local home prices and rents scaled against household incomes) with affordability_score, price_to_income and rent_to_income sub-components, national_percentile, county_fips, and methodology_version for all 3,222 US counties. Call when the user asks how affordable housing is in a county or how markets compare on cost burden, or when timing relocation, site-selection, geographic-pay, or housing-investment decisions." }, { "id": "ADW-501", "name": "Property Tax Burden Index", "domain": "Real Estate", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-501", "mcp_tool": "adw.adw_501", "sample": "https://alpinedataworks.com/showcase/adw-501", "description": "Per-county 0-100 score of local property-tax burden, mapped across all 3,222 US counties.", "agent_question": "How heavy is the local property-tax load?", "history_start": "2013-01-01", "history_years": 11, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "US Census ACS 5-year API (api.census.gov/data/{2013..2023}/acs/acs5; tables B25103 median real-estate taxes, B25077 median home value, B19013 median hh income, B01003 population; free key) \u2014 history vintages", "Census Reporter latest-ACS API (api.censusreporter.org/1.0/data/show/latest?table_ids=B25103,B25077,B19013,B01003&geo_ids=050|01000US; keyless) \u2014 current snapshot, 3,222 counties verified", "Census PEP county totals CSV (www2.census.gov/programs-surveys/popest/datasets/2020-2025/counties/totals/co-est2025-alldata.csv) \u2014 county display names" ], "mcp_description": "Returns a 0-100 property-tax burden score for each of 3,222 US counties (effective tax rate and tax-to-income share, normalized nationally) with burden_score, effective_tax_rate, tax_share_of_income, national_percentile, and methodology_version fields. Call when the user asks about local property-tax load, homeownership or landlord carrying costs, or county tax comparisons, or when timing site-selection, rental buy-box, or relocation decisions." }, { "id": "ADW-502", "name": "School Quality Index", "domain": "Public Sector", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-502", "mcp_tool": "adw.adw_502", "sample": "https://alpinedataworks.com/showcase/adw-502", "description": "Per-county 0-100 score of local school quality, mapped across all 3,222 US counties.", "agent_question": "How strong are the local schools?", "history_start": "2009-01-01", "history_years": 17, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "Urban Institute Education Data Portal API \u2014 NCES CCD, EDFacts grad rates, SEDA (educationdata.urban.org/api/v1, verified 200 live)", "Stanford Education Data Archive (SEDA) county-level files via https://edopportunity.org/get-the-data/", "Census ACS 5-year API, table S1501 educational attainment (api.census.gov/data/{year}/acs/acs5, free key required)" ], "mcp_description": "Returns a 0-100 school quality score for any of 3,222 US counties (composite of public K-12 outcome and resource measures \u2014 proficiency, graduation, staffing, attainment) with school_quality_score, national_percentile, drivers, confidence, and methodology_version. Call when the user asks about local school quality, district strength, education-driven demand, or family relocation, or when timing residential site selection, homebuilding product mix, or corporate relocation decisions." }, { "id": "ADW-503", "name": "Employment Health Index", "domain": "Labor", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-503", "mcp_tool": "adw.adw_503", "sample": "https://alpinedataworks.com/showcase/adw-503", "description": "Per-county 0-100 score of local job-market health, mapped across all 3,222 US counties.", "agent_question": "How healthy is the local job market?", "history_start": "2013-01-01", "history_years": 13.5, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "Census ACS 5-Year Detailed Tables B23025/B19013/B01003 via https://api.census.gov/data/{2013..2023}/acs/acs5 (keyed) \u2014 powers employment_history vintages", "Census Reporter latest ACS 5-yr release (api.censusreporter.org/1.0/data/show/latest) \u2014 keyless 2020-2024-vintage snapshot; verified live 2026-07-18", "BLS LAUS county series (api.bls.gov/publicAPI/v2, monthly, 1990+) \u2014 verified live from residential IP but Akamai 403 from Worker/datacenter egress; upgrade path only, NOT wired (registry use-case's 'monthly LAUS' cadence does not match shipped product)" ], "mcp_description": "Returns a 0-100 employment health score for any of 3,222 US counties (composited from county-level unemployment, job-growth, and wage indicators, refreshed on source cadence) with health_score, percentile_rank, drivers, as_of, and methodology_version. Call when the user asks how healthy a local job market is or compares counties for hiring, siting, or lending, or when timing expansion, headcount, or county-level credit decisions." }, { "id": "ADW-504", "name": "Broadband Access Index", "domain": "Tech", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-504", "mcp_tool": "adw.adw_504", "sample": "https://alpinedataworks.com/showcase/adw-504", "description": "Per-county 0-100 score of local broadband access, mapped across all 3,222 US counties.", "agent_question": "How good is local broadband access?", "history_start": "2022-06-30", "history_years": 4, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "FCC National Broadband Map / Broadband Data Collection county availability summaries (broadbandmap.fcc.gov/data-download; BDC public API with free registered token)", "US Census ACS 5-Year API, table B28002 internet subscriptions (api.census.gov/data/{yyyy}/acs/acs5)", "FCC Form 477 fixed deployment archive 2014-2021, pre-BDC historical context (fcc.gov/general/broadband-deployment-data-fcc-form-477)" ], "mcp_description": "Returns a 0-100 broadband access score for all 3,222 US counties (availability, household adoption, and provider competition composited from federal broadband and census data) with broadband_score, availability/adoption sub-scores, provider_competition, national_percentile, and methodology_version. Call when the user asks about internet quality, connectivity gaps, or underserved markets, or when timing site selection, remote-hiring geography, or build-out decisions." }, { "id": "ADW-505", "name": "Population Vitality Index", "domain": "Consumer", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-505", "mcp_tool": "adw.adw_505", "sample": "https://alpinedataworks.com/showcase/adw-505", "description": "Per-county 0-100 score of population growth and vitality, mapped across all 3,222 US counties.", "agent_question": "Is the local population growing and vital?", "history_start": "2013-01-01", "history_years": 11, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "US Census PEP county totals Vintage 2025 (www2.census.gov/programs-surveys/popest/datasets/2020-2025/counties/totals/co-est2025-alldata.csv)", "US Census ACS 5-year API, tables B01003/B01002/B25010, vintages 2013-2023 (api.census.gov/data/{year}/acs/acs5, free key)", "Census Reporter latest-ACS API, keyless (api.censusreporter.org/1.0/data/show/latest)" ], "mcp_description": "Returns a 0-100 county population-vitality score (z-composite of Census PEP 2020-2025 population growth, ACS median age, household size, and population scale) with county_fips, county_name, natl_pctile, band, population, and methodology_version for all 3,222 US counties. Call when the user asks whether a local population is growing, young, or family-forming, or when timing site-selection, housing, retail-expansion, or market-entry decisions." }, { "id": "ADW-506", "name": "Food Access Index", "domain": "Public Sector", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-506", "mcp_tool": "adw.adw_506", "sample": "https://alpinedataworks.com/showcase/adw-506", "description": "Per-county 0-100 score of access to healthy food, mapped across all 3,222 US counties.", "agent_question": "How accessible is healthy food locally?", "history_start": "2010-01-01", "history_years": 16, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "USDA ERS Food Access Research Atlas \u2014 tract-level low-income/low-access (LILA) measures, vintages 2010/2015/2019 (ers.usda.gov/data-products/food-access-research-atlas; mirrored at catalog.data.gov/dataset/food-access-research-atlas)", "USDA ERS Food Environment Atlas \u2014 280+ county-level food-environment indicators incl. grocery-store and SNAP-retailer counts (ers.usda.gov/data-products/food-environment-atlas)", "US Census ACS 5-year API \u2014 S2201 SNAP households, B08201 household vehicle availability (api.census.gov/data)", "CDC PLACES Health-Related Social Needs \u2014 county FOODINSECU measure via Socrata SODA (data.cdc.gov); supplementary only, covers states running the BRFSS SDOH module" ], "mcp_description": "Returns a 0-100 healthy-food access score for all 3,222 US counties (grocery availability, distance-to-store, vehicle access, and income constraints from federal sources) with food_access_score, national_percentile, ranked drivers, county_fips, methodology_version, and source_vintage. Call when the user asks about food deserts, grocery access, food insecurity geography, or nutrition equity, or when timing food-program siting, retail expansion, or grant targeting." }, { "id": "ADW-507", "name": "Transport Corridor Index", "domain": "Transport", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-507", "mcp_tool": "adw.adw_507", "sample": "https://alpinedataworks.com/showcase/adw-507", "description": "Per-county 0-100 score of transport-corridor connectivity, mapped across all 3,222 US counties.", "agent_question": "How connected is the county by transport?", "history_start": "2016-01-01", "history_years": 10, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "BTS NTAD National Highway System via https://services.arcgis.com/xOi1kZaI0eWDREZv/arcgis/rest/services/NTAD_National_Highway_System/FeatureServer/0 (geodata.bts.gov)", "FRA North American Rail Network Lines via https://services.arcgis.com/xOi1kZaI0eWDREZv/arcgis/rest/services/NTAD_North_American_Rail_Network_Lines/FeatureServer/0 (geodata.bts.gov)", "BTS Intermodal Passenger Connectivity Database via https://services.arcgis.com/xOi1kZaI0eWDREZv/arcgis/rest/services/NTAD_Intermodal_Passenger_Connectivity_Database/FeatureServer/0", "FHWA HPMS annual vintage archive (www.fhwa.dot.gov/policyinformation/hpms/shapefiles.cfm; 2020/2023/2024 vintages on geodata.bts.gov)" ], "mcp_description": "Returns a 0-100 transport-corridor connectivity score for all 3,222 US counties (highway, rail, and air access scored from federal transport-network data) with connectivity_score, highway/rail/air components, national_percentile, and methodology_version. Call when the user asks how connected a county is by transport, about freight corridors or logistics connectivity, or when timing distribution-center siting, network expansion, or site selection." }, { "id": "ADW-508", "name": "Airport Access Index", "domain": "Transport", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-508", "mcp_tool": "adw.adw_508", "sample": "https://alpinedataworks.com/showcase/adw-508", "description": "Per-county 0-100 score of proximity to commercial air service, mapped across all 3,222 US counties.", "agent_question": "How close is commercial air service?", "history_start": "forward-only", "history_years": 0, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "HIFLD Airport Facilities (hifld-geoplatform.opendata.arcgis.com)" ], "mcp_description": "Returns a 0-100 county airport-access score (distance to the nearest commercial-service airports, graded by hub size) for all 3,222 US counties, with access_score, nearest_airport, distance_miles, hub_class, national_percentile, and methodology_version. Call when the user asks about a county's proximity to commercial air service, airport access, or travel accessibility, or when timing site-selection, relocation, or field-coverage decisions that hinge on air access." }, { "id": "ADW-509", "name": "Consumer Spending Index", "domain": "Consumer", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-509", "mcp_tool": "adw.adw_509", "sample": "https://alpinedataworks.com/showcase/adw-509", "description": "Per-county 0-100 score of local consumer spending power, mapped across all 3,222 US counties.", "agent_question": "How strong is local consumer spending power?", "history_start": "forward-only", "history_years": 0, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "US Census ACS S1901 median household income + retail sales per capita (BEA CAINC1) (api.census.gov/data/2022/acs/acs5)" ], "mcp_description": "Returns a 0-100 consumer spending power score for all 3,222 US counties (built from federal income and employment series: Census ACS, BEA, BLS) with spending_score, national_percentile, state_rank, income_component, employment_component, methodology_version, and as_of. Call when the user asks about local consumer strength or county purchasing power, or when timing store openings, geo-targeted ad spend, or territory expansion." }, { "id": "ADW-510", "name": "Business Density Index", "domain": "Consumer", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-510", "mcp_tool": "adw.adw_510", "sample": "https://alpinedataworks.com/showcase/adw-510", "description": "Per-county 0-100 score of local business density, mapped across all 3,222 US counties.", "agent_question": "How dense is local business activity?", "history_start": "forward-only", "history_years": 0, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "US Census County Business Patterns (CBP) establishments per capita (api.census.gov/data/2022/cbp)" ], "mcp_description": "Returns a 0-100 business density score for any of 3,222 US counties (business-establishment concentration, percentile-ranked nationally) with density_score, national_percentile, county_fips, county_name, and methodology_version. Call when the user asks about local business activity, commercial density, market saturation, or how one county's business landscape compares to another, or when timing site selection, retail expansion, or market-entry decisions." }, { "id": "ADW-511", "name": "Library Access Index", "domain": "Public Sector", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-511", "mcp_tool": "adw.adw_511", "sample": "https://alpinedataworks.com/showcase/adw-511", "description": "Per-county 0-100 score of public library access, mapped across all 3,222 US counties.", "agent_question": "How strong is public library access?", "history_start": "forward-only", "history_years": 0, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "IMLS Public Libraries Survey + Census population (www.imls.gov/research-evaluation/data-collection/public-libraries-survey)" ], "mcp_description": "Returns a 0-100 public library access score for any of 3,222 US counties (per-capita branch density, service hours, and service-capacity measures, normalized to the national distribution) with score, national_percentile, driver attributions, confidence, and methodology_version. Call when the user asks about library access, civic or educational infrastructure, or digital-equity gaps, or when timing grant targeting, levy proposals, or public-sector market prioritization." }, { "id": "ADW-512", "name": "Crime & Safety Index", "domain": "Public Sector", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-512", "mcp_tool": "adw.adw_512", "sample": "https://alpinedataworks.com/showcase/adw-512", "description": "Per-county 0-100 score of crime levels and public safety, mapped across all 3,222 US counties.", "agent_question": "How safe is this county?", "history_start": "2019-01-01", "history_years": 7, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "County Health Rankings analytic data CSVs (countyhealthrankings.org/sites/default/files/media/document/analytic_data.csv, keyless, 2019-2025; verified live 2026-07-18)", "Upstream via CHR: FBI UCR violent-crime rate (v043, 2019-2022 only \u2014 CHR retired it after the NIBRS transition) + CDC/NVSS injury & firearm death rates (v135/v148, 2019-2025)" ], "mcp_description": "Returns a 0-100 per-county crime and safety score (violent- and property-crime rates from federal reporting, normalized across all 3,222 US counties; higher = safer) with safety_score, violent_crime_component, property_crime_component, national_percentile, confidence, data_vintage, and methodology_version. Call when the user asks how safe a county or area is, or about local crime levels, or when timing site selection, relocation, expansion, or security-spend decisions." }, { "id": "ADW-513", "name": "Childcare Access Index", "domain": "Public Sector", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-513", "mcp_tool": "adw.adw_513", "sample": "https://alpinedataworks.com/showcase/adw-513", "description": "Per-county 0-100 score of local childcare availability, mapped across all 3,222 US counties.", "agent_question": "How available is childcare locally?", "history_start": "forward-only", "history_years": 0, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "HRSA / CCDF childcare provider data + Census under-5 population (www.acf.hhs.gov/occ/data)" ], "mcp_description": "Returns a 0-100 childcare availability score for any of 3,222 US counties (licensed provider capacity weighed against the local population of young children, normalized nationally) with access_score, national_percentile, drivers, county_fips, as_of, and methodology_version. Call when the user asks about childcare availability, childcare deserts, or how family-friendly a location is, or when timing site selection, relocation, center expansion, or employee-benefits decisions." }, { "id": "ADW-514", "name": "Power Grid Index", "domain": "Energy", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-514", "mcp_tool": "adw.adw_514", "sample": "https://alpinedataworks.com/showcase/adw-514", "description": "Per-county 0-100 score of power-grid robustness, mapped across all 3,222 US counties.", "agent_question": "How robust is the local power grid?", "history_start": "forward-only", "history_years": 0, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "HIFLD Electric Substations + Transmission Lines (hifld-geoplatform.opendata.arcgis.com)" ], "mcp_description": "Returns a 0-100 power-grid robustness score for any of 3,222 US counties (composite of outage burden, capacity margin, and hazard exposure from federal reliability and storm data) with grid_score, percentile_rank, driver sub-scores, county_fips, and methodology_version. Call when the user asks about grid reliability, blackout risk, or local power resilience, or when timing site selection, backup-power investment, or continuity planning for a specific county." }, { "id": "ADW-515", "name": "Data Center Density Index", "domain": "Tech", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-515", "mcp_tool": "adw.adw_515", "sample": "https://alpinedataworks.com/showcase/adw-515", "description": "Per-county 0-100 score of data-center capacity concentration, mapped across all 3,222 US counties.", "agent_question": "Where is data-center capacity concentrated?", "history_start": "forward-only", "history_years": 0, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "HIFLD Data Centers layer + colocation.com (hifld-geoplatform.opendata.arcgis.com)" ], "mcp_description": "Returns a 0-100 data-center capacity-concentration score for any of 3,222 US counties (facility and hosting-industry footprint aggregated to county grain) with density_score, national_rank, percentile, county_fips, and methodology_version. Call when the user asks about data-center density, where compute or AI infrastructure is concentrated, or colocation markets, or when timing site selection, fiber buildout, or grid-capacity planning decisions." }, { "id": "ADW-516", "name": "Agriculture Production Index", "domain": "Agriculture", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-516", "mcp_tool": "adw.adw_516", "sample": "https://alpinedataworks.com/showcase/adw-516", "description": "Per-county 0-100 score of agricultural production significance, mapped across all 3,222 US counties.", "agent_question": "How significant is local agricultural output?", "history_start": "2007-01-01", "history_years": 18.5, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "USDA NASS Cash Receipts by county + Census of Agriculture (quickstats.nass.usda.gov/api)" ], "mcp_description": "Returns a 0-100 agricultural-production significance score for any of 3,222 US counties (normalized from USDA county-level production statistics) with score, national_percentile, state_rank, top_drivers, as_of, and methodology_version. Call when the user asks about local farm output, crop or livestock concentration, or which counties lead US agricultural production, or when timing ag lending, equipment or facility siting, and rural supply-chain decisions." }, { "id": "ADW-517", "name": "Soil & Land Quality Index", "domain": "Agriculture", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-517", "mcp_tool": "adw.adw_517", "sample": "https://alpinedataworks.com/showcase/adw-517", "description": "Per-county 0-100 score of soil and land quality, mapped across all 3,222 US counties.", "agent_question": "What is the local soil/land quality?", "history_start": "forward-only", "history_years": 0, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "USDA NRCS SSURGO soil productivity index + gSSURGO (www.nrcs.usda.gov/resources/data-and-reports/soil-survey-geographic-database-ssurgo)" ], "mcp_description": "Returns a 0-100 soil and land quality score for each of 3,222 US counties (composite of soil-productivity, erosion, and land-cover indicators from public sources) with score, national_percentile, ranked drivers, methodology_version, and confidence. Call when the user asks about local soil or farmland quality, land productivity, or growing conditions, or when timing farmland acquisition, lease pricing, project siting, or agricultural lending decisions." }, { "id": "ADW-518", "name": "Regulated Facilities Index", "domain": "Climate", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-518", "mcp_tool": "adw.adw_518", "sample": "https://alpinedataworks.com/showcase/adw-518", "description": "Per-county 0-100 score of regulated-facility concentration, mapped across all 3,222 US counties.", "agent_question": "How concentrated are regulated facilities?", "history_start": "forward-only", "history_years": 0, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "EPA Facility Registry Service (FRS) (www.epa.gov/frs)" ], "mcp_description": "Returns a 0-100 county regulated-facility concentration score (log-scaled z-score of active EPA ECHO facility counts across all 3,222 US counties; higher = denser facility burden) with prevalence, natl_pctile, Low/Elevated/High band, population, and methodology_version. Call when the user asks about EPA-regulated facilities, polluter or industrial concentration, or compliance burden in a county, or when timing site selection, Phase I escalation, or premises-pollution underwriting." }, { "id": "ADW-519", "name": "Toxic Releases Index", "domain": "Climate", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-519", "mcp_tool": "adw.adw_519", "sample": "https://alpinedataworks.com/showcase/adw-519", "description": "Per-county 0-100 score of toxic-release burden, mapped across all 3,222 US counties.", "agent_question": "How high is local toxic-release burden?", "history_start": "1987-01-01", "history_years": 39.0, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "EPA Toxics Release Inventory (TRI) annual reporting (www.epa.gov/toxics-release-inventory-tri-program)" ], "mcp_description": "Returns a 0-100 toxic-release burden score for any of 3,222 US counties (EPA Toxics Release Inventory facility releases, normalized cross-county) with national percentile, rank, top release drivers, methodology_version, and source vintage. Call when the user asks about local pollution, industrial toxic releases, or environmental risk for a county or address, or when timing site selection, relocation, underwriting, or environmental due-diligence decisions." }, { "id": "ADW-520", "name": "Weather Severity Index", "domain": "Climate", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-520", "mcp_tool": "adw.adw_520", "sample": "https://alpinedataworks.com/showcase/adw-520", "description": "Per-county 0-100 score of severe-weather risk, mapped across all 3,222 US counties.", "agent_question": "How severe is local weather risk?", "history_start": "1950-01-01", "history_years": 76.0, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "NOAA Storm Events Database + SPC storm reports (www.ncdc.noaa.gov/stormevents)" ], "mcp_description": "Returns a 0-100 severe-weather severity score for any of 3,222 US counties (composite of federal storm-event frequency, intensity, and hazard mix) with severity_score, national_percentile, top_drivers, as_of, confidence, and methodology_version. Call when the user asks about local weather risk, storm/hail/tornado exposure, or comparing county-level hazard severity, or when timing property, siting, insurance, or hardening decisions with weather exposure." }, { "id": "ADW-521", "name": "Seismic History Index", "domain": "Climate", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-521", "mcp_tool": "adw.adw_521", "sample": "https://alpinedataworks.com/showcase/adw-521", "description": "Per-county 0-100 score of historical earthquake activity, mapped across all 3,222 US counties.", "agent_question": "What is the local earthquake history?", "history_start": "1900-01-01", "history_years": 126.0, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "USGS ANSS Comprehensive Earthquake Catalog (ComCat) (earthquake.usgs.gov/fdsnws/event/1)" ], "mcp_description": "Returns a 0-100 seismic history score for any of 3,222 US counties (normalized from the historical earthquake record \u2014 frequency and magnitude of past events) with score, percentile, county_fips, county_name, state, as_of, and methodology_version. Call when the user asks about local earthquake history, seismic exposure, or county risk rankings, or when timing site selection, underwriting, or retrofit-budget decisions." }, { "id": "ADW-522", "name": "Hospital Access Index", "domain": "Health", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-522", "mcp_tool": "adw.adw_522", "sample": "https://alpinedataworks.com/showcase/adw-522", "description": "Per-county 0-100 score of hospital access, mapped across all 3,222 US counties.", "agent_question": "How strong is local hospital access?", "history_start": "forward-only", "history_years": 0, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "HRSA Health Resources & Services Admin Hospitals + HIFLD hospital facilities (data.hrsa.gov)" ], "mcp_description": "Returns a 0-100 hospital access score for any of 3,222 US counties (hospital facility density and staffed-bed capacity relative to population, from federal provider data) with access_score, national_percentile, drivers, county_fips, and methodology_version. Call when the user asks about hospital access, healthcare deserts, or county care capacity, or when timing site selection, network-adequacy filings, or relocation and expansion decisions." }, { "id": "ADW-523", "name": "Park Access Index", "domain": "Public Sector", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-523", "mcp_tool": "adw.adw_523", "sample": "https://alpinedataworks.com/showcase/adw-523", "description": "Per-county 0-100 score of park access, mapped across all 3,222 US counties.", "agent_question": "How good is local park access?", "history_start": "forward-only", "history_years": 0, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "USGS Protected Areas Database of the United States (PAD-US) + NPS units (www.usgs.gov/programs/gap-analysis-project/science/pad-us-data-download)" ], "mcp_description": "Returns a 0-100 park-access score for any of 3,222 US counties (composite of public parkland coverage and population proximity, percentile-ranked nationally) with score, trend, confidence, top_drivers, and source_lineage. Call when the user asks about park access, green-space equity, livability, or recreation infrastructure in a county, or when timing site selection, parks-bond planning, or recreation grant targeting." }, { "id": "ADW-524", "name": "EV Charging Index", "domain": "Transport", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-524", "mcp_tool": "adw.adw_524", "sample": "https://alpinedataworks.com/showcase/adw-524", "description": "Per-county 0-100 score of EV-charging build-out, mapped across all 3,222 US counties.", "agent_question": "How built-out is EV charging locally?", "history_start": "2007-01-01", "history_years": 18.5, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "DOE Alternative Fuels Data Center (AFDC) EV Charging Stations (developer.nrel.gov/api/alt-fuel-stations/v1)" ], "mcp_description": "Returns a 0-100 per-county EV-charging build-out score for all 3,222 US counties (public station and port density, DC fast and Level 2, normalized per capita) with ev_charging_score, dcfc_ports_per_100k, l2_ports_per_100k, county_percentile, state_rank, and methodology_version. Call when the user asks about local EV-charging build-out, charging deserts, or county EV readiness, or when timing charger deployment, fleet electrification, or site-selection decisions." }, { "id": "ADW-528", "name": "Local Attractions Index", "domain": "Travel", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-528", "mcp_tool": "adw.adw_528", "sample": "https://alpinedataworks.com/showcase/adw-528", "description": "Per-county 0-100 score of local-attraction richness, mapped across all 3,222 US counties.", "agent_question": "How rich are local attractions?", "history_start": "forward-only", "history_years": 0, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "OpenStreetMap tourism/leisure tags + NPS + Yelp restaurant density (overpass-api.de/api)" ], "mcp_description": "Returns a 0-100 local-attraction richness score for all 3,222 US counties (per-capita attraction density plus category breadth across outdoor, cultural, and dining attraction types) with attractions_score, national_percentile, county_rank, category_breadth, attraction_density, as_of, and methodology_version. Call when the user asks how attraction-rich a county or destination is, compares travel markets, or when timing hotel, short-term-rental, or tourism site-selection decisions." }, { "id": "ADW-529", "name": "Heritage Sites Index", "domain": "Travel", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-529", "mcp_tool": "adw.adw_529", "sample": "https://alpinedataworks.com/showcase/adw-529", "description": "Per-county 0-100 score of historic-heritage richness, mapped across all 3,222 US counties.", "agent_question": "How rich is local historic heritage?", "history_start": "1966-10-15", "history_years": 59.0, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "National Register of Historic Places (NRHP) (www.nps.gov/subjects/nationalregister/database-research.htm)" ], "mcp_description": "Returns a 0-100 historic-heritage richness score for any of 3,222 US counties (density and significance of listed historic sites, districts, and landmarks) with score, top_drivers, confidence, coverage, freshness, and methodology_version. Call when the user asks about historic sites, heritage tourism, or the old-town character of a county or destination, or when timing itinerary routing, hotel site selection, or heritage-market screening." }, { "id": "ADW-525", "name": "Seismic Hazard Index", "domain": "Geophysical", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-525", "mcp_tool": "adw.adw_525", "sample": "https://alpinedataworks.com/showcase/adw-525", "description": "Per-county 0-100 score of long-term earthquake shaking hazard from USGS ASCE7 design ground motions, across all 3,222 US counties.", "agent_question": "How much long-term earthquake ground-shaking hazard does this county face (USGS ASCE7 design ground motion)?", "history_start": "forward-only", "history_years": 0, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "USGS 2018 National Seismic Hazard Model + ASCE 7 design ground motion (earthquake.usgs.gov/hazards/hazmaps)" ], "mcp_description": "Returns a 0-100 long-term earthquake ground-shaking hazard score for each of 3,222 US counties (USGS ASCE7 design ground motions: PGA, SS, S1) with hazard_score, seismic_design_category, national_percentile, driver values, and methodology_version. Call when the user asks about earthquake risk, seismic hazard, ground shaking, or building-code seismic exposure for a US county or location, or when timing site-selection, property-underwriting, or retrofit-prioritization decisions." }, { "id": "ADW-526", "name": "Agroclimate Stress Index", "domain": "Agriculture", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-526", "mcp_tool": "adw.adw_526", "sample": "https://alpinedataworks.com/showcase/adw-526", "description": "Per-county 0-100 score of current agricultural moisture stress from NASA POWER root-zone soil wetness, across all 3,222 US counties.", "agent_question": "How moisture-stressed is this county's agricultural ground right now (NASA POWER root-zone soil wetness)?", "history_start": "1981-01-01", "history_years": 44.5, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "NASA POWER root-zone soil wetness + Prism climate (power.larc.nasa.gov/api)" ], "mcp_description": "Returns a 0-100 agricultural moisture-stress score for any of 3,222 US counties (scaled from NASA POWER root-zone soil wetness) with stress_score, county_fips, soil_wetness, as_of, and methodology_version. Call when the user asks about drought, soil moisture, crop stress, or growing conditions in a US county, or when timing planting, irrigation, hedging, ag-lending, or crop-insurance decisions that depend on current ground moisture." }, { "id": "ADW-527", "name": "US Metro Housing Heat Index", "domain": "Real Estate", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-527", "mcp_tool": "adw.adw_527", "sample": "https://alpinedataworks.com/showcase/adw-527", "description": "Metro-level buyer-vs-seller housing heat across ~894 US metros from Zillow/Redfin listing dynamics.", "agent_question": "Which US metros are seller's vs buyer's markets right now (0-100 housing heat)?", "history_start": "2001-01-31", "history_years": 25.4, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "alpine-data real_estate feed (Zillow ZHVI + Redfin listing dynamics)" ], "mcp_description": "Returns a 0-100 metro housing heat score (composite z-score of Zillow/Redfin listing dynamics \u2014 inventory, price cuts, days on market \u2014 for ~894 US metros, weekly since 2001) with per-metro score, driver attribution, confidence, and methodology_version. Call when the user asks which US metros are seller's vs buyer's markets, about housing heat or metro rankings, or when timing a home purchase, listing, or SFR acquisition." }, { "id": "ADW-530", "name": "AI/Data Ecosystem Positioning Index", "domain": "Tech", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-530", "mcp_tool": "adw.adw_530", "sample": "https://alpinedataworks.com/showcase/adw-530", "description": "Per-vendor market-quality positioning (vision \u00d7 execution) across ~619 AI/data vendors.", "agent_question": "Where does each AI/data vendor sit on vision vs execution?", "history_start": "2026-07-11", "history_years": 0.0, "product_class": "live", "tier": "Gold", "refresh": "weekly", "source_apis": [ "alpine-data vendors feed (non-summit AI/data landscape, MQ vision/execution)" ], "mcp_description": "Returns a 0-100 market-quality positioning score for each of ~619 AI/data vendors (composite z-score across vision and execution dimensions, refreshed weekly) with vision_score, execution_score, drivers, and methodology_version. Call when the user asks where an AI or data vendor sits on vision vs execution, vendor shortlists, or ecosystem landscape comparisons, or when timing vendor selection, renewal, or partnership decisions." }, { "id": "ADW-531", "name": "Long-Term Compounder Universe", "domain": "Market", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-531", "mcp_tool": "adw.adw_531", "sample": "https://alpinedataworks.com/showcase/adw-531", "description": "Curated ~217-name long-term-compounder universe with maturity-stage quality tilt.", "agent_question": "What is the durability/quality profile of the long-term compounder universe?", "history_start": "2026-07-11", "history_years": 0.0, "product_class": "live", "tier": "Gold", "refresh": "weekly", "source_apis": [ "alpine-data lthcs universe feed (classified universe)" ], "mcp_description": "Returns a 0-100 durability/quality score for a curated ~217-name long-term-compounder universe (composite z-score with maturity-stage quality tilt, refreshed weekly) with score, drivers, confidence, and methodology_version on the IOM. Call when the user asks about compounder quality, buy-and-hold universe health, or quality-factor durability, or when timing additions or trims to a long-horizon quality equity sleeve." }, { "id": "ADW-532", "name": "Federal Contract & Grant Dependency", "domain": "Public", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-532", "mcp_tool": "adw.adw_532", "sample": "https://alpinedataworks.com/showcase/adw-532", "description": "Tracks 12mo federal obligations per county to flag economic dependency risks for developers.", "agent_question": "Which counties rely most on federal grants?", "history_start": "2001-01-01", "history_years": 24.5, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "USAspending.gov federal contracts + grants API (api.usaspending.gov/api/v2)" ], "mcp_description": "Returns a 0-100 federal dependency score per US county (trailing-12-month contract and grant obligations from USAspending, normalized against county population and economic base) with obligations_per_capita, grant_share, yoy_obligation_change, national_percentile, and methodology_version. Call when the user asks which counties rely most on federal grants or contracts, shutdown or budget-cut exposure, or when timing site-selection, underwriting, or muni-credit decisions." }, { "id": "ADW-533", "name": "DoD Contract Obligation", "domain": "Public", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-533", "mcp_tool": "adw.adw_533", "sample": "https://alpinedataworks.com/showcase/adw-533", "description": "Maps 12mo DoD prime awards per county to identify key defense investment hubs.", "agent_question": "Where is DoD prime spending concentrated?", "history_start": "2001-01-01", "history_years": 24.5, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "USAspending.gov DoD contracts (agency_id 097) (api.usaspending.gov/api/v2)" ], "mcp_description": "Returns a 0-100 county defense-spending concentration score (trailing-12-month DoD prime-award obligations by place of performance, percentile-ranked across all US counties) with obligations_12mo_usd, award_count, national_share_pct, rank, and methodology_version. Call when the user asks about DoD spending concentration, defense hub counties, or a region's defense-economy exposure, or when timing facility siting, govcon market entry, or defense-dependent credit reviews." }, { "id": "ADW-534", "name": "Streamflow Stress Index", "domain": "Climate", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-534", "mcp_tool": "adw.adw_534", "sample": "https://alpinedataworks.com/showcase/adw-534", "description": "Scores drought stress by comparing current river flows to historical normals per county.", "agent_question": "Which areas face critical water stress?", "history_start": "1900-01-01", "history_years": 126.0, "product_class": "map", "tier": "Gold", "refresh": "per source cadence", "source_apis": [ "USGS WaterWatch daily streamflow + NWIS (waterwatch.usgs.gov)" ], "mcp_description": "Returns a 0-100 county-level streamflow stress score (current gauge-measured river discharge vs. historical flow normals) with stress_score, flow_percentile, severity_band, station_count, as_of, and methodology_version fields. Call when the user asks about drought severity, water stress, low river levels, or irrigation and water-supply risk in a county or region, or when timing water-dependent decisions \u2014 crop lending, facility siting, drought-contingency triggers." }, { "id": "ADW-535", "name": "Ethereum Network Sentiment Index", "domain": "Crypto", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-535", "mcp_tool": "adw.adw_535", "sample": "https://alpinedataworks.com/showcase/adw-535", "description": "Daily ETH on-chain sentiment composite (z-scores of active addresses + tx count vs 30d baseline) with full per-component attribution and an ETH network-context tile set. Directional indicator, not a trading signal.", "agent_question": "Is Ethereum on-chain demand and network activity heating up or cooling off right now?", "history_start": "2015-08-29", "history_years": 10.9, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Coin Metrics Community API (free tier: AdrActCnt, TxCnt, SplyCur daily series)", "Blockchair Ethereum stats (free: 24h burn, ERC-20 tx, price, supply)", "alpine-data whale feed (pre-computed eth.sentiment composite)" ], "mcp_description": "Returns a 0-100 Ethereum network sentiment score (composite z-scores of active addresses and transaction count vs 30-day baselines, daily since 2015) with per-component attribution, ETH network-context tiles, and methodology_version. Call when the user asks about Ethereum on-chain activity, ETH network demand heating up or cooling off, or address/transaction trends, or when timing launches, deployments, or gas-sensitive operations. Directional indicator, not a trading signal." }, { "id": "ADW-536", "name": "Grocery Staples Cost Index", "domain": "Macro", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-536", "mcp_tool": "adw.adw_536", "sample": "https://alpinedataworks.com/showcase/adw-536", "description": "Household grocery-burden index from real dollar staple prices (milk, ground beef, chicken, bread, eggs \u2014 BLS CPI average prices via FRED). Per-staple YoY plus a 0-100 burden score. Monthly.", "agent_question": "How squeezed is the US household grocery budget right now, and which staple is driving it?", "history_start": "2016-06-01", "history_years": 10.1, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "FRED (BLS CPI Average Price data: APU series \u2014 milk, ground beef, chicken, bread, eggs)", "alpine-data cpi feed (data-cpi.json)" ], "mcp_description": "Returns a 0-100 US household grocery-burden score (composite z-score of BLS CPI average prices for milk, ground beef, chicken, bread, and eggs, monthly since 2016) with per-staple YoY changes and the top driver. Call when the user asks about grocery inflation, food-at-home costs, egg or beef prices, or consumer budget squeeze, or when timing staples promotions, trade-down forecasts, or consumer-staples positioning." }, { "id": "ADW-537", "name": "TSA Throughput Momentum Index", "domain": "Mobility", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-537", "mcp_tool": "adw.adw_537", "sample": "https://alpinedataworks.com/showcase/adw-537", "description": "Daily US air-travel demand pulse from TSA checkpoint traveler counts: z-score momentum vs 7d avg, 30d window, and same-weekday prior week. 50 = normal. Ships the 30-day daily series.", "agent_question": "Is US air-travel demand running hotter or cooler than normal right now?", "history_start": "2019-01-30", "history_years": 7.4, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "TSA checkpoint travel numbers \u2014 tsa.gov/travel/passenger-volumes", "alpine-data tsa feed (daily bridge)" ], "mcp_description": "Returns a 0-100 US air-travel demand momentum score (composite z-score of TSA checkpoint traveler counts vs 7-day average, 30-day window, and same-weekday prior week; 50 = normal) with drivers, confidence, methodology_version, and the 30-day daily series. Call when the user asks whether US air travel, airport traffic, or TSA throughput is running hotter or cooler than normal, or when timing airline-sector positioning, travel pricing, or airport staffing decisions." }, { "id": "ADW-538", "name": "Global Travel Risk Index", "domain": "Geopolitics", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-538", "mcp_tool": "adw.adw_538", "sample": "https://alpinedataworks.com/showcase/adw-538", "description": "World travel-safety risk composite (0-100) from US State Dept advisories across ~225 countries, with per-risk-type counts, the level-4 do-not-travel list, and a full per-country decoded table for lookup. Risk-side complement to ADW-117.", "agent_question": "How risky is international travel right now, and which countries carry which risk factors?", "history_start": "2026-07-12", "history_years": 0.0, "product_class": "live", "tier": "Gold", "refresh": "daily", "source_apis": [ "US State Dept Travel Advisories (travel.state.gov) via alpine-data travel feed", "US State Dept Travel Bulletins (travel.state.gov) via alpine-data travel feed" ], "mcp_description": "Returns a 0-100 world travel-safety risk composite (z-scored daily from US State Department advisories across ~225 countries) with per-risk-type counts, the current level-4 do-not-travel list, and a decoded per-country advisory table. Call when the user asks about travel safety, country risk factors, or do-not-travel status, or when timing international trips, employee travel approvals, or itinerary changes." }, { "id": "ADW-539", "name": "City Livability Context Index", "domain": "Macro", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-539", "mcp_tool": "adw.adw_539", "sample": "https://alpinedataworks.com/showcase/adw-539", "description": "Cross-city LEVELS comparison of metro livability fundamentals (income, rent, taxes, unemployment, air quality) on a 0-100 scale across major US metros, with per-city scores for lookup. Levels sibling of ADW-114 (momentum).", "agent_question": "How do major US metros compare on livability fundamentals right now, and which ranks highest or lowest?", "history_start": "2026-07-12", "history_years": 0.0, "product_class": "live", "tier": "Gold", "refresh": "daily", "source_apis": [ "alpine-data city feed \u2014 City Context composite (ACS income/rent/taxes, BLS unemployment, EPA AQI; min-max normalized 0-100 across reporting cities)", "City Context is a cross-city comparison of LEVELS, not a quality-of-life ranking and not a verdict on which city is 'best' to live in.", "City Context and City Pulse are two separate numbers shown side by side and are never merged: Pulse measures a city against its own history (momentum); Context compares cities to each other (levels).", "median_home_value is intentionally EXCLUDED: its direction is ambiguous (a high value reads as desirable to owners but unaffordable to renters/buyers) and affordability is already captured by median_rent. It is shown in the Context strip but left out of the score.", "Coverage honesty: a city is scored on the mean of the KPIs it has and is never penalized or imputed for a missing KPI; a KPI reported by fewer than two cities can't be normalized and is dropped for everyone; a city with no usable KPI has no Context score." ], "mcp_description": "Returns a 0-100 cross-metro livability levels comparison (ACS income/rent/property-tax, BLS unemployment, and EPA air-quality fundamentals normalized across major US metros, refreshed daily) with per-city context_score in cities, highest_context_city, lowest_context_city, and top_drivers. Call when the user asks how US metros compare on livability, rent, taxes, or job-market fundamentals, or when timing relocation, hiring-hub, or site-selection decisions. Levels, not momentum \u2014 that's ADW-114." }, { "id": "ADW-540", "name": "UFO Sighting Activity Index", "domain": "Novelty", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-540", "mcp_tool": "adw.adw_540", "sample": "https://alpinedataworks.com/showcase/adw-540", "description": "National anomalous-sighting-report momentum index (0-100) from 143k+ NUFORC/MUFON reports back to 1906. 7d/30d/90d report velocity vs prior year, with a state leaderboard and top shapes. Measures reporting activity, not phenomenon validity.", "agent_question": "Is US UFO/UAP sighting-report activity heating up or cooling off right now, and which states are driving it?", "history_start": "2004-06-01", "history_years": 22.1, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "alpine-data mufon feed (planetsig/ufo-reports mirror of NUFORC (MIT) (1906-2014) + nuforc.org direct (2014+) \u2014 https://nuforc.org/subndx/)" ], "mcp_description": "Returns a 0-100 US UFO/UAP sighting-report momentum index (composite z-score of 7d/30d/90d report velocity vs prior year, from 143k+ NUFORC/MUFON reports) with score, velocity_7d/30d/90d, state_leaderboard, and top_shapes. Call when the user asks whether UFO sighting activity is heating up or cooling off and which states drive it, or when timing UAP-themed content, merchandise, or coverage. Measures reporting activity, not phenomenon validity." }, { "id": "ADW-541", "name": "Pilot Pipeline Health Index", "domain": "Mobility", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-541", "mcp_tool": "adw.adw_541", "sample": "https://alpinedataworks.com/showcase/adw-541", "description": "0-100 health score for the US pilot-supply funnel from YoY growth across FAA airman certificate classes, weighted toward the early funnel (students, commercial, CFIs). Includes the full per-certificate KPI breakdown.", "agent_question": "Is the US pilot-supply funnel expanding or contracting right now?", "history_start": "1992-12-31", "history_years": 33.5, "product_class": "time-series", "tier": "Gold", "refresh": "annual", "source_apis": [ "alpine-data aviation feed (FAA U.S. Civil Airmen Statistics, Aeronautical Center OKC)" ], "mcp_description": "Returns a 0-100 US pilot-supply funnel health score (YoY growth across FAA airman certificate classes, weighted toward students, commercial pilots, and CFIs) with health_score, per-certificate KPI breakdown, and methodology_version, annual since 1992. Call when the user asks about pilot shortage, pilot supply, flight training demand, or aviation workforce trends, or when timing airline hiring plans, flight-school expansion, or trainer-aircraft demand forecasts." }, { "id": "ADW-542", "name": "GA Safety Trend Index", "domain": "Mobility", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-542", "mcp_tool": "adw.adw_542", "sample": "https://alpinedataworks.com/showcase/adw-542", "description": "0-100 safety-trajectory score (higher = safer): latest-year GA accident and fatal-accident rates per 100k flight hours, z-scored vs the 6-year trend. Includes the full per-year trend and slope.", "agent_question": "Is US general aviation getting safer or more dangerous vs its recent trend?", "history_start": "2020-12-31", "history_years": 5.5, "product_class": "time-series", "tier": "Gold", "refresh": "annual", "source_apis": [ "alpine-data aviation feed (NTSB/FAA general aviation safety statistics)" ], "mcp_description": "Returns a 0-100 US general aviation safety-trajectory score (latest-year GA accident and fatal-accident rates per 100k flight hours, z-scored against the 6-year trend) with slope and the full per-year rate trend. Call when the user asks whether US GA flying is getting safer or more dangerous, about GA accident-rate trends, or when timing aviation insurance renewals, flight-school fleet decisions, or safety-program investment." }, { "id": "ADW-543", "name": "Used-Aircraft Market Liquidity Index", "domain": "Mobility", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-543", "mcp_tool": "adw.adw_543", "sample": "https://alpinedataworks.com/showcase/adw-543", "description": "0-100 liquidity score from listings-to-registered-fleet turnover for major GA makes (Cessna, Piper, Cirrus). Includes per-make turnover and used-market price-band distribution.", "agent_question": "How liquid is the US used general-aviation aircraft market, and which makes turn over fastest?", "history_start": "2026-07-12", "history_years": 0.0, "product_class": "live", "tier": "Gold", "refresh": "monthly", "source_apis": [ "alpine-data aviation feed (FAA aircraft registry + used-market listing snapshot)" ], "mcp_description": "Returns a 0-100 US used general-aviation aircraft market liquidity score (listings-to-registered-fleet turnover for major GA makes: Cessna, Piper, Cirrus) with trend, per-make turnover in top_drivers, price-band distribution, confidence, and methodology_version. Call when the user asks about used aircraft market liquidity, GA resale demand, or which makes sell fastest, or when timing an aircraft purchase, sale, consignment intake, or collateral valuation." }, { "id": "ADW-544", "name": "Air-Travel Recovery Index", "domain": "Mobility", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-544", "mcp_tool": "adw.adw_544", "sample": "https://alpinedataworks.com/showcase/adw-544", "description": "US commercial enplanements vs the 2019 baseline: score = recovery ratio capped at 100, raw ratio exposed. Includes the 2015-2025 annual series, YoY change, and 3-year CAGR.", "agent_question": "Have US enplanements recovered to pre-pandemic levels, and what's the trajectory?", "history_start": "2000-12-31", "history_years": 25.5, "product_class": "time-series", "tier": "Gold", "refresh": "annual", "source_apis": [ "alpine-data aviation feed (BTS/FAA US enplanement statistics)" ], "mcp_description": "Returns a 0-100 US air-travel recovery score (annual commercial enplanements vs the 2019 pre-pandemic baseline, capped at 100) with raw_ratio, yoy_change, cagr_3y, and the 2015-2025 annual series. Call when the user asks about airline traffic recovery, passenger volumes vs pre-COVID levels, or air-travel demand trajectory, or when timing airline-sector, airport-concession, or travel-capacity decisions." }, { "id": "ADW-545", "name": "Fleet Aging Index", "domain": "Mobility", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-545", "mcp_tool": "adw.adw_545", "sample": "https://alpinedataworks.com/showcase/adw-545", "description": "GA fleet obsolescence score = share of the US fixed-wing fleet built before 1990 (~58% of 242k airframes). Includes build-decade distribution, median build decade, and shipment trend.", "agent_question": "How old is the US GA fleet, and how big is the retrofit/replacement opportunity?", "history_start": "2026-07-12", "history_years": 0.0, "product_class": "live", "tier": "Gold", "refresh": "annual", "source_apis": [ "alpine-data aviation feed (FAA aircraft registry build-year data + GAMA shipments)" ], "mcp_description": "Returns a 0-100 US general-aviation fleet obsolescence score (share of the 242k-airframe US fixed-wing fleet built before 1990, currently ~58%) with pre_1990_share, build_decade_distribution, median_build_decade, and shipment_trend. Call when the user asks about GA fleet age, avionics retrofit or aircraft replacement demand, or aviation aftermarket sizing, or when timing MRO capacity, retrofit product-line, or parts-inventory investments." }, { "id": "ADW-546", "name": "Airspace Concentration Index", "domain": "Mobility", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-546", "mcp_tool": "adw.adw_546", "sample": "https://alpinedataworks.com/showcase/adw-546", "description": "Live Herfindahl concentration index (0-100) over tracked aircraft counts by country from the OpenSky ADS-B network. Includes country leaderboard with shares, altitude distribution, and tracked/airborne/ground totals.", "agent_question": "How concentrated is live tracked air traffic across countries right now?", "history_start": "2026-07-12", "history_years": 0.0, "product_class": "live", "tier": "Gold", "refresh": "hourly", "source_apis": [ "OpenSky Network (alpine-data opensky feed, volunteer ADS-B sample)" ], "mcp_description": "Returns a 0-100 airspace concentration index (live Herfindahl over tracked aircraft counts by country from the OpenSky ADS-B network, hourly refresh) with country leaderboard shares, altitude distribution, and tracked/airborne/ground totals. Call when the user asks how concentrated global air traffic is right now, which countries dominate live flights, or whether an airspace disruption is visible, or when timing cargo rerouting, travel-risk escalations, or aviation-exposure decisions." }, { "id": "ADW-547", "name": "Global Supply Pressure (GSCPI) Tracker", "domain": "Macro", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-547", "mcp_tool": "adw.adw_547", "sample": "https://alpinedataworks.com/showcase/adw-547", "description": "Pure passthrough of the NY Fed Global Supply Chain Pressure Index with long-history percentile context (score = percentile vs ~346 obs to 1997), plus raw std-dev, 12m delta, 24m z, and regime label. Distinct from ADW-113.", "agent_question": "How stressed are global supply chains, and how does today's GSCPI rank vs three decades of history?", "history_start": "2016-07-31", "history_years": 9.9, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "alpine-data supplies feed (NY Fed Global Supply Chain Pressure Index)" ], "mcp_description": "Returns a 0-100 global supply-chain pressure score (NY Fed GSCPI ranked as a percentile against ~346 monthly observations to 1997) with raw_std_dev, delta_12m, z_24m, regime_label, and methodology_version. Call when the user asks about supply-chain stress, shipping bottlenecks, GSCPI, or logistics-driven inflation risk, or when timing inventory builds, freight-rate locks, or sourcing shifts." }, { "id": "ADW-548", "name": "Sector Money-Flow Rotation Index", "domain": "Markets", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-548", "mcp_tool": "adw.adw_548", "sample": "https://alpinedataworks.com/showcase/adw-548", "description": "Daily sector-rotation index from per-stock MFI/CMF money-flow composites: score = rotation intensity, trend flags rotating vs broad in/outflow. Includes per-sector means and a top-5 inflow/outflow leaderboard. Distinct from ADW-111.", "agent_question": "Which US equity sectors is capital rotating into and out of right now?", "history_start": "2026-07-12", "history_years": 0.0, "product_class": "live", "tier": "Gold", "refresh": "daily", "source_apis": [ "alpine-data stock-money-flow feed (per-stock MFI + CMF composite, daily)" ], "mcp_description": "Returns a 0-100 sector-rotation intensity score (daily aggregation of per-stock MFI/CMF money-flow composites across US equity sectors) with trend (rotating vs broad inflow/outflow), per-sector means, and top-5 inflow/outflow leaderboards. Call when the user asks which sectors capital is rotating into or out of, about sector money flow or accumulation/distribution, or when timing sector-ETF tilts, rotation trades, or rebalance decisions." }, { "id": "ADW-549", "name": "Global Seismic Activity Index", "domain": "Geophysics", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-549", "mcp_tool": "adw.adw_549", "sample": "https://alpinedataworks.com/showcase/adw-549", "description": "Real-time global earthquake activity momentum from USGS ComCat (M2.5+, 30d): 7d event rate + cumulative seismic energy z-scored vs the 30d daily norm. Includes recent significant quakes. Distinct from ADW-525 hazard.", "agent_question": "Is global earthquake activity accelerating or quieter than normal right now?", "history_start": "1975-01-31", "history_years": 51.4, "product_class": "time-series", "tier": "Gold", "refresh": "hourly", "source_apis": [ "USGS Earthquake Hazards Program \u2014 ComCat GeoJSON summary feed (earthquake.usgs.gov/earthquakes/feed/v1.0/summary/2.5_month.geojson, keyless)" ], "mcp_description": "Returns a 0-100 global earthquake activity momentum score, 50 = normal (USGS ComCat M2.5+: 7-day event rate and log seismic energy z-scored vs the trailing 30-day norm, hourly) with activity_level, trend, z_score_count, z_score_energy, recent_significant quakes, and 7d/30d counts. Call when the user asks if global seismic activity is accelerating or quieter than usual, or when timing catastrophe-monitoring escalation and seismic-exposure reviews. Momentum, not hazard (see ADW-525)." }, { "id": "ADW-550", "name": "Space Weather Storm Index", "domain": "Geophysics", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-550", "mcp_tool": "adw.adw_550", "sample": "https://alpinedataworks.com/showcase/adw-550", "description": "Near-real-time geomagnetic storm intensity (0-100) from NOAA SWPC planetary Kp + live solar wind, mapped to the NOAA G-scale. Includes last-24h Kp readings and storm trend. Keyless.", "agent_question": "How intense is the current geomagnetic storm, and what's the grid/satellite/GPS risk?", "history_start": "1932-01-01", "history_years": 94.5, "product_class": "time-series", "tier": "Gold", "refresh": "hourly", "source_apis": [ "NOAA SWPC Planetary K-index (services.swpc.noaa.gov/products/noaa-planetary-k-index.json, keyless)", "NOAA SWPC solar wind speed summary (services.swpc.noaa.gov/products/summary/solar-wind-speed.json, keyless)", "NOAA SWPC solar wind magnetic field summary (services.swpc.noaa.gov/products/summary/solar-wind-mag-field.json, keyless)" ], "mcp_description": "Returns a 0-100 geomagnetic storm intensity index (NOAA SWPC planetary Kp composited with live solar wind, mapped to the NOAA G-scale) with g_scale, kp_last_24h, and storm_trend. Call when the user asks about solar storms, aurora visibility, space weather, or grid, satellite, and GPS disruption risk, or when timing satellite maneuvers, precision-GPS field work, or power-grid maintenance windows. Keyless; refreshed hourly." }, { "id": "ADW-551", "name": "US Drug Shortage Index", "domain": "Health", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-551", "mcp_tool": "adw.adw_551", "sample": "https://alpinedataworks.com/showcase/adw-551", "description": "Daily 0-100 index of US drug supply-disruption pressure from the FDA shortage list (openFDA). Deduplicates package rows to unique drugs in Current shortage vs a crisis-band ceiling. Includes top therapeutic categories + recent shortages.", "agent_question": "How much pharmaceutical supply-disruption pressure is the US under, and which categories are hit hardest?", "history_start": "2026-07-12", "history_years": 0.0, "product_class": "live", "tier": "Gold", "refresh": "daily", "source_apis": [ "openFDA Drug Shortages \u2014 https://api.fda.gov/drug/shortages.json (keyless)" ], "mcp_description": "Returns a 0-100 US drug supply-disruption pressure index (unique drugs on the FDA Current-shortage list vs a ~250-drug crisis ceiling; openFDA, daily) with trend, current_shortages, new_last_30d, resolved_last_90d, by_category, and recent shortages. Call when the user asks about drug shortages, pharmaceutical supply pressure, or hardest-hit therapeutic categories, or when timing pharmacy inventory, pre-buy, or alternate-supplier decisions." }, { "id": "ADW-552", "name": "Drug Recall Activity Index", "domain": "Health", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-552", "mcp_tool": "adw.adw_552", "sample": "https://alpinedataworks.com/showcase/adw-552", "description": "Severity-weighted index of US drug recall enforcement from openFDA (Class I=3/II=2/III=1, trailing 90d vs prior 90d). Includes class breakdown, top recall reason, and recent Class I/II recalls.", "agent_question": "How intense is US drug recall enforcement, and what failure modes are driving it?", "history_start": "2013-01-05", "history_years": 13.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "api.fda.gov/drug/enforcement.json (keyless, daily refresh)" ], "mcp_description": "Returns a 0-100 US drug recall enforcement intensity score (severity-weighted openFDA recalls: Class I=3, II=2, III=1, trailing 90d vs prior 90d) with trend, by_class counts, top_reason driver, and the 10 latest Class I/II recalls (firm, product, reason, date). Call when the user asks about FDA drug recalls, pharma safety enforcement, or manufacturing failure modes, or when timing supplier audits, formulary reviews, or pharma supply-chain risk decisions." }, { "id": "ADW-553", "name": "US Bank Health Index", "domain": "Finance", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-553", "mcp_tool": "adw.adw_553", "sample": "https://alpinedataworks.com/showcase/adw-553", "description": "Aggregate US banking-sector health (0-100) from FDIC BankFind: trailing-12mo failures (40%), industry annualized ROA (30%), noncurrent-loan ratio (30%) across ~4,300 active institutions. Includes recent failures + balance-sheet signals.", "agent_question": "How healthy is the US banking sector right now?", "history_start": "1992-12-31", "history_years": 33.5, "product_class": "time-series", "tier": "Gold", "refresh": "quarterly", "source_apis": [ "FDIC BankFind Suite API \u2014 institutions, failures, financials endpoints (api.fdic.gov/banks, keyless)" ], "mcp_description": "Returns a 0-100 US banking-sector health score (quarterly composite from FDIC BankFind: trailing-12-month failures 40%, industry annualized ROA 30%, noncurrent-loan ratio 30%, ~4,300 institutions, history to 1992) with health_score, per-driver values, confidence, and methodology_version. Call when the user asks about bank failures, banking-sector stress, or deposit safety, or when timing counterparty limits, deposit allocation, or credit-sensitive decisions." }, { "id": "ADW-554", "name": "Food Recall Activity Index", "domain": "Health", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-554", "mcp_tool": "adw.adw_554", "sample": "https://alpinedataworks.com/showcase/adw-554", "description": "Daily 0-100 index of US food recall activity from openFDA food enforcement: 90d volume weighted by FDA class, trend vs prior 90d, top reasons (Listeria/Salmonella/allergens), and recent recalls.", "agent_question": "How much US food-safety recall pressure is there now, and is it rising vs last quarter?", "history_start": "2013-01-05", "history_years": 13.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "openFDA Food Enforcement API (api.fda.gov/food/enforcement)" ], "mcp_description": "Returns a 0-100 US food-recall activity index (90-day openFDA food-enforcement volume weighted by FDA class, trended against the prior 90 days) with score, trend, top_drivers such as Listeria, Salmonella, and undeclared allergens, confidence, and methodology_version. Call when the user asks about food-safety recall pressure, contamination outbreaks, or FDA enforcement activity, or when timing supplier audits, QA sampling intensity, or food-category risk decisions." }, { "id": "ADW-555", "name": "Corporate Disclosure Activity Index", "domain": "Markets", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-555", "mcp_tool": "adw.adw_555", "sample": "https://alpinedataworks.com/showcase/adw-555", "description": "Daily 0-100 velocity index of material SEC disclosure: last-7d 8-K filing pace vs trailing-28d baseline, with S-1 IPO-pipeline count and form mix. From the keyless SEC EDGAR full-text search API.", "agent_question": "Is US public-company material-disclosure activity surging or quiet vs its trailing-month norm?", "history_start": "2001-02-11", "history_years": 25.4, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "SEC EDGAR full-text search API (efts.sec.gov/LATEST/search-index, keyless, descriptive User-Agent required)" ], "mcp_description": "Returns a daily 0-100 US corporate disclosure-velocity index (last-7-day 8-K filing pace vs trailing-28-day baseline, keyless SEC EDGAR full-text search, history to 2001) with score, form_mix, s1_pipeline_count, drivers, and methodology_version. Call when the user asks about SEC filing activity, 8-K surges, material corporate-event flow, or IPO-pipeline buildup, or when timing deal launches, disclosure-driven event risk, or news-desk staffing." }, { "id": "ADW-556", "name": "US Air Quality Index", "domain": "Health", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-556", "mcp_tool": "adw.adw_556", "sample": "https://alpinedataworks.com/showcase/adw-556", "description": "Current national air-quality burden across 12 major US metros (score = mean EPA US AQI). Drivers: worst metro, share unhealthy, dominant pollutant. Per-metro table worst-first. Keyless Open-Meteo (CAMS).", "agent_question": "How bad is air quality across major US metros right now, and which metro/pollutant is worst?", "history_start": "2022-08-05", "history_years": 3.9, "product_class": "time-series", "tier": "Gold", "refresh": "hourly", "source_apis": [ "Open-Meteo Air Quality API \u2014 current us_aqi/pm2_5/pm10/ozone, CAMS-based (air-quality-api.open-meteo.com/v1/air-quality, keyless)" ], "mcp_description": "Returns a 0-100 US air-quality burden score (mean EPA US AQI across 12 major metros, hourly, keyless Open-Meteo/CAMS) with worst_metro, share_unhealthy, and dominant_pollutant drivers plus a worst-first per-metro table. Call when the user asks about current air quality, wildfire smoke, ozone, or which US city is worst right now, or when timing outdoor operations, respiratory staffing, or air-quality-sensitive logistics." }, { "id": "ADW-557", "name": "US Weather Alert Index", "domain": "Weather", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-557", "mcp_tool": "adw.adw_557", "sample": "https://alpinedataworks.com/showcase/adw-557", "description": "Real-time severe-weather warning pressure: every active NWS watch/warning/advisory weighted by severity (Extreme=4..Minor=1) on a saturating 0-100 scale. Includes top event types, severity breakdown, states affected, recent Extreme/Severe alerts. Keyless api.weather.gov.", "agent_question": "How severe is the active weather-warning load across the US right now?", "history_start": "2026-07-12", "history_years": 0.0, "product_class": "live", "tier": "Gold", "refresh": "hourly", "source_apis": [ "National Weather Service API \u2014 active alerts GeoJSON (api.weather.gov/alerts/active, keyless)" ], "mcp_description": "Returns a 0-100 US severe-weather warning-pressure score (every active NWS watch/warning/advisory weighted Extreme=4 to Minor=1 on a saturating scale, refreshed hourly) with trend, confidence, top_drivers by event type, severity breakdown, states affected, and recent Extreme/Severe alerts. Call when the user asks how severe the current US weather-warning load is, which states are under alerts, or about storm severity, or when timing logistics holds, staffing surges, or event go/no-go decisions." }, { "id": "ADW-558", "name": "Coastal Water Level Anomaly Index", "domain": "Climate", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-558", "mcp_tool": "adw.adw_558", "sample": "https://alpinedataworks.com/showcase/adw-558", "description": "Real-time storm-surge/coastal-flood pressure: observed water level minus NOAA harmonic tide prediction (non-tidal residual, ft) across a 10-station NOAA CO-OPS network (Atlantic/Gulf/Pacific). Per-station anomalies worst-first. Keyless.", "agent_question": "Are US coastal water levels running above predicted tide right now \u2014 active storm-surge pressure?", "history_start": "1995-01-01", "history_years": 31.5, "product_class": "time-series", "tier": "Gold", "refresh": "hourly", "source_apis": [ "NOAA CO-OPS Tides & Currents datagetter API \u2014 water_level + predictions, datum MLLW (api.tidesandcurrents.noaa.gov, keyless)" ], "mcp_description": "Returns a 0-100 US coastal water-level anomaly index (observed level minus NOAA harmonic tide prediction \u2014 non-tidal residual, ft \u2014 across 10 CO-OPS stations, Atlantic/Gulf/Pacific, hourly) with per-station drivers worst-first, confidence, and methodology_version. Call when the user asks about storm surge, coastal flooding, king tides, or water levels above predicted tide, or when timing surge prep, port or marina operations, or coastal flood-exposure decisions." }, { "id": "ADW-559", "name": "Global Disaster Activity Index", "domain": "Disaster", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-559", "mcp_tool": "adw.adw_559", "sample": "https://alpinedataworks.com/showcase/adw-559", "description": "Real-time 0-100 index of worldwide natural-disaster activity from GDACS (EC-JRC/UN OCHA): active EQ/cyclone/flood/volcano/drought/wildfire events weighted by alert level (Red=3/Orange=2/Green=1). Includes counts by type/level + top Red/Orange events. Keyless.", "agent_question": "How much natural-disaster activity is happening worldwide right now, and which events are most severe?", "history_start": "2026-07-12", "history_years": 0.0, "product_class": "live", "tier": "Gold", "refresh": "hourly", "source_apis": [ "GDACS \u2014 Global Disaster Alert and Coordination System, EC-JRC/UN OCHA (gdacs.org/gdacsapi/api/events/geteventlist/EVENTS4APP, keyless; RSS fallback gdacs.org/xml/rss.xml)" ], "mcp_description": "Returns a live hourly 0-100 index of worldwide natural-disaster activity (GDACS EC-JRC/UN OCHA events weighted Red=3, Orange=2, Green=1) with counts by event type and alert level plus top Red/Orange events. Call when the user asks how much disaster activity is happening globally or which earthquakes, cyclones, floods, volcanoes, droughts, or wildfires are most severe right now, or when timing logistics reroutes, continuity escalations, or humanitarian response." }, { "id": "ADW-560", "name": "Natural Hazard Events Index", "domain": "Disaster", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-560", "mcp_tool": "adw.adw_560", "sample": "https://alpinedataworks.com/showcase/adw-560", "description": "Global natural-hazard activity from NASA EONET: count + category mix of open events active in the trailing 30 days (wildfires/storms/volcanoes/ice), scored vs the ~140-event baseline (high-impact categories tilted 1.5x). Includes per-category counts + recent events. Keyless.", "agent_question": "How many natural-hazard events are active on Earth right now vs normal?", "history_start": "2024-06-30", "history_years": 2.0, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "NASA Earth Observatory Natural Event Tracker (EONET) v3 (eonet.gsfc.nasa.gov/api/v3/events, keyless)" ], "mcp_description": "Returns a 0-100 global natural-hazard activity score (open NASA EONET events, trailing 30 days, vs a ~140-event baseline with high-impact categories weighted 1.5x) with trend, confidence, top_drivers, per-category counts (wildfires/storms/volcanoes/ice), and recent events. Call when the user asks how many disasters are active now, whether hazard activity is abnormal, or which category drives it, or when timing supply-chain, insurance, or continuity decisions sensitive to global disaster load." }, { "id": "ADW-561", "name": "US Drought Severity Index", "domain": "Climate", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-561", "mcp_tool": "adw.adw_561", "sample": "https://alpinedataworks.com/showcase/adw-561", "description": "Severity-weighted share of US area in drought (0-100) from the weekly US Drought Monitor: D0x0.1+D1x0.3+D2x0.5+D3x0.75+D4x1.0 over categorical area %, with week-over-week trend and per-category coverage. Keyless.", "agent_question": "How much of the US is in drought right now, and how severe?", "history_start": "2000-01-04", "history_years": 26.5, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "US Drought Monitor data services (usdmdataservices.unl.edu, GetDroughtSeverityStatisticsByAreaPercent, categorical area %, keyless)" ], "mcp_description": "Returns a 0-100 US drought severity index (severity-weighted share of US area in drought from the weekly US Drought Monitor, D0\u00d70.1 through D4\u00d71.0) with week-over-week trend and per-category D0-D4 area coverage. Call when the user asks how much of the US is in drought and how severe, or when timing agricultural hedging, water-supply, irrigation, or wildfire-exposure decisions." }, { "id": "ADW-562", "name": "Global News Tone Index", "domain": "Geopolitics", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-562", "mcp_tool": "adw.adw_562", "sample": "https://alpinedataworks.com/showcase/adw-562", "description": "Live 0-100 stress gauge of global news negativity from the GDELT DOC 2.0 average-tone timeline (14d, global English firehose). Inverts tone so more-negative coverage scores higher, with calm/tense/crisis regimes, tone trend, 14d timeline. Keyless.", "agent_question": "How negative or stressed is the emotional tone of world news right now?", "history_start": "2026-07-12", "history_years": 0.0, "product_class": "live", "tier": "Gold", "refresh": "daily", "source_apis": [ "GDELT DOC 2.0 API timelinetone (api.gdeltproject.org/api/v2/doc/doc, keyless)", "GDELT DOC 2.0 API timelinevolraw (api.gdeltproject.org/api/v2/doc/doc, keyless)" ], "mcp_description": "Returns a 0-100 global news stress gauge (inverted GDELT DOC 2.0 average tone, 14d global English firehose, keyless, daily) with score, calm/tense/crisis regime, trend, latest_tone, tone_change, article_volume, and a 14-day timeline. Call when the user asks how negative or tense world news feels right now, whether media stress is rising, or when timing announcements, launches, or risk-monitoring escalation around the news cycle." }, { "id": "ADW-563", "name": "Solar Flare Activity Index", "domain": "Geophysics", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-563", "mcp_tool": "adw.adw_563", "sample": "https://alpinedataworks.com/showcase/adw-563", "description": "Live 0-100 index of solar X-ray flare activity from NOAA SWPC GOES: current 0.1-0.8nm flux + strongest 24h flare mapped through a log-flux ramp (B~11,C~38,M~65,X~92+), with flux class, recent flares, and NOAA R-scale blackout level. Complements ADW-550 (Kp). Keyless.", "agent_question": "How intense is current solar X-ray flare activity, and what radio-blackout risk does it pose?", "history_start": "1975-09-01", "history_years": 50.9, "product_class": "time-series", "tier": "Gold", "refresh": "hourly", "source_apis": [ "NOAA SWPC GOES primary X-ray flux 6-hour (services.swpc.noaa.gov/json/goes/primary/xrays-6-hour.json, keyless)", "NOAA SWPC GOES X-ray flares 7-day (services.swpc.noaa.gov/json/goes/primary/xray-flares-7-day.json, keyless)", "NOAA SWPC GOES latest X-ray flare (services.swpc.noaa.gov/json/goes/primary/xray-flares-latest.json, keyless)" ], "mcp_description": "Returns a 0-100 solar X-ray flare activity index (hourly, keyless; NOAA SWPC GOES 0.1-0.8nm flux plus strongest 24h flare on a log-flux ramp \u2014 B~11, C~38, M~65, X~92+) with flux_class, recent_flares, and the NOAA R-scale radio-blackout level. Call when the user asks about solar flares, space weather, HF radio blackouts, or GNSS degradation, or when timing polar flight dispatch, maritime HF communications, or RTK-precision survey work." }, { "id": "ADW-564", "name": "Major-Currency FX Volatility Index", "domain": "Markets", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-564", "mcp_tool": "adw.adw_564", "sample": "https://alpinedataworks.com/showcase/adw-564", "description": "Realized-vol macro/risk gauge across 7 major USD pairs (EUR/GBP/JPY/CHF/CAD/AUD/CNY): annualized stdev of 30 business days of daily log returns (ECB rates via Frankfurter), cross-pair mean mapped 0-100. Includes per-pair vol ranking + regime. Keyless.", "agent_question": "How volatile are the major USD currency pairs right now \u2014 macro calm or stress?", "history_start": "1999-03-07", "history_years": 27.3, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Frankfurter \u2014 ECB daily foreign-exchange reference rates (api.frankfurter.dev, keyless)" ], "mcp_description": "Returns a 0-100 major-currency FX volatility index (annualized 30-day realized vol of daily log returns across 7 USD pairs \u2014 EUR, GBP, JPY, CHF, CAD, AUD, CNY \u2014 from ECB reference rates, cross-pair mean) with score, trend, regime, per-pair vol ranking, freshness, and methodology_version. Call when the user asks about currency-market stress, FX volatility, dollar-pair turbulence, or macro risk-on/risk-off, or when timing hedging, carry, or forward-contract decisions." }, { "id": "ADW-565", "name": "Consumer Product Recall Index", "domain": "Health", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-565", "mcp_tool": "adw.adw_565", "sample": "https://alpinedataworks.com/showcase/adw-565", "description": "0-100 index of US consumer-product recall pressure from the CPSC Recall API: trailing-90d volume weighted toward recalls citing reported injuries/deaths, vs prior 90d. Includes hazard-type breakdown + recent recalls. Distinct from drug/food/device recalls.", "agent_question": "How elevated is US consumer-product recall activity right now, and which hazard types drive it?", "history_start": "2002-07-06", "history_years": 24.0, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "CPSC Recall REST API (saferproducts.gov/RestWebServices/Recall)" ], "mcp_description": "Returns a 0-100 US consumer-product recall pressure index (trailing-90d CPSC recall volume, injury/death-weighted, vs the prior 90d) with score, trend, hazard-type top_drivers, recent recalls, confidence, and methodology_version. Call when the user asks about product recalls, CPSC activity, or consumer-product safety hazards, or when timing compliance testing, liability underwriting, or marketplace listing-risk decisions. Distinct from drug/food/device recalls." }, { "id": "ADW-566", "name": "Medical Device Safety Index", "domain": "Health", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-566", "mcp_tool": "adw.adw_566", "sample": "https://alpinedataworks.com/showcase/adw-566", "description": "0-100 index of US medical-device recall enforcement from openFDA: 90d recall count severity-weighted by FDA class (I=3/II=2/III=1) vs prior 90d, with class breakdown, top reason, and recent Class I/II recalls. Distinct from ADW-552 (drugs).", "agent_question": "How elevated is US medical-device recall/enforcement pressure right now?", "history_start": "2013-01-05", "history_years": 13.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "api.fda.gov/device/enforcement.json (keyless, daily refresh)" ], "mcp_description": "Returns a 0-100 US medical-device recall-enforcement pressure index (openFDA 90-day recall count, severity-weighted by FDA class I=3/II=2/III=1, vs the prior 90 days) with score, trend, confidence, top_drivers, class breakdown, top recall reason, and recent Class I/II recalls. Call when the user asks about medical-device recalls, FDA device enforcement, or device safety risk, or when timing supplier reviews, procurement holds, or med-tech exposure. For drug recalls use ADW-552." }, { "id": "ADW-568", "name": "Insider Trading Activity Index", "domain": "Markets", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-568", "mcp_tool": "adw.adw_568", "sample": "https://alpinedataworks.com/showcase/adw-568", "description": "Velocity of US insider reporting: last-7d SEC Form 4 filing pace vs the trailing-28d daily baseline, mapped 0-100. Includes Form 144 (planned-sale pipeline) + Form 3 (new insiders). Keyless SEC EDGAR FTS. Distinct from ADW-555 (8-K disclosure).", "agent_question": "Is US insider-transaction activity (SEC Form 4) surging or quiet vs its trailing-month norm?", "history_start": "2001-02-11", "history_years": 25.4, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "SEC EDGAR full-text search API (efts.sec.gov/LATEST/search-index, keyless, descriptive User-Agent required)" ], "mcp_description": "Returns a 0-100 US insider-trading activity index (last-7d SEC Form 4 filing pace vs trailing-28d baseline, plus Form 144 planned-sale pipeline and Form 3 new insiders; keyless EDGAR FTS) with score, trend, confidence, top_drivers, methodology_version, freshness. Call when the user asks about insider buying/selling waves, Form 4 velocity, or insider sentiment, or when timing offerings, buybacks, or exposure shifts against insider-supply pressure. 8-K disclosure pace is ADW-555." }, { "id": "ADW-569", "name": "Humanitarian Crisis Index", "domain": "Geopolitics", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-569", "mcp_tool": "adw.adw_569", "sample": "https://alpinedataworks.com/showcase/adw-569", "description": "Severity-weighted 0-100 index of active humanitarian emergencies tracked by UN OCHA ReliefWeb (ongoing+alert): epidemics/floods/droughts/complex emergencies/cyclones, with crisis-type mix + countries affected. Response-side lens complementing ADW-559 (GDACS). Keyless.", "agent_question": "How many humanitarian emergencies are active worldwide right now, and how heavy is the global crisis load?", "history_start": "1990-01-31", "history_years": 36.4, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "ReliefWeb \u2014 UN OCHA humanitarian information service (reliefweb.int/disasters, keyless public HTML; RSS fallback reliefweb.int/disasters/rss.xml)" ], "mcp_description": "Returns a 0-100 global humanitarian-crisis load index (severity-weighted count of active UN OCHA ReliefWeb emergencies: complex emergencies x3, epidemics x2.5, droughts x2) with crisis_level, trend, ongoing_count, new_30d, by_type mix, countries_affected, and a recent-crises list. Call when the user asks about active humanitarian emergencies, global crisis load, or disaster-response demand, or when timing NGO surge staffing, sovereign-risk reviews, or supply-chain exposure checks." }, { "id": "ADW-570", "name": "US Extreme Heat Forecast Index", "domain": "Climate", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-570", "mcp_tool": "adw.adw_570", "sample": "https://alpinedataworks.com/showcase/adw-570", "description": "Forward-looking national heat-stress burden across 12 major US metros over 7 days: mean forecast peak apparent temp + share of metros hitting the 100F+ danger threshold. Per-metro table with peak apparent/actual temps. Open-Meteo forecast, keyless.", "agent_question": "How severe and widespread is dangerous heat forecast across major US metros over the next 7 days?", "history_start": "2026-07-12", "history_years": 0.0, "product_class": "live", "tier": "Gold", "refresh": "hourly", "source_apis": [ "Open-Meteo Forecast API \u2014 daily temperature_2m_max/apparent_temperature_max, 7-day horizon (api.open-meteo.com/v1/forecast, keyless)" ], "mcp_description": "Returns a 0-100 US extreme-heat forecast index (mean 7-day peak apparent temperature across 12 major metros plus share of metros forecast at 100\u00b0F+, Open-Meteo, hourly) with heat_level, mean_peak_apparent_f, metros_over_100f, hottest_metro, and a hottest-first per-metro table (peak_apparent_f, days_over_90f). Call when the user asks about heat waves, dangerous heat, or metro heat risk, or when timing staffing, energy hedging, or logistics decisions for the week ahead." }, { "id": "ADW-571", "name": "Public Attention Index", "domain": "Novelty", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-571", "mcp_tool": "adw.adw_571", "sample": "https://alpinedataworks.com/showcase/adw-571", "description": "Daily 0-100 news-cycle intensity gauge from English Wikipedia pageview velocity: how concentrated pageviews are in trending articles vs a quiet-day baseline (utility pages filtered), with day-over-day velocity + top-15 trending topics. Keyless Wikimedia.", "agent_question": "What is the public paying attention to right now, and how intense is the news cycle?", "history_start": "2015-07-01", "history_years": 11.0, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Wikimedia REST pageviews/top (wikimedia.org/api/rest_v1, en.wikipedia.org all-access, keyless)" ], "mcp_description": "Returns a 0-100 news-cycle intensity gauge (English Wikipedia pageview concentration in trending articles vs a quiet-day baseline, utility pages filtered, daily since 2015) with attention_score, dod_velocity, top_topics (top 15), percentile, trend, and methodology_version. Call when the user asks what the public is paying attention to, how loud the news cycle is, or what's trending \u2014 or when timing announcements, launches, or media spend around cycle saturation." }, { "id": "ADW-572", "name": "US Respiratory Illness Activity Index", "domain": "Health", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-572", "mcp_tool": "adw.adw_572", "sample": "https://alpinedataworks.com/showcase/adw-572", "description": "Current US respiratory-illness activity (0-100) from CDC NSSP emergency-department ARI visit share: latest weekly national ARI% mapped to an activity band, with WoW trend, 4-week comparison, ~12 weeks history, and COVID/flu/RSV component split. Keyless CDC.", "agent_question": "How high is US respiratory-illness (flu/COVID/RSV) activity right now, and is it rising or falling?", "history_start": "2022-10-01", "history_years": 3.8, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "CDC NSSP Emergency Department Visits - Respiratory Daily (data.cdc.gov resource vjzj-u7u8, geography=\"United States\", pathogen=\"ARI\", keyless Socrata)" ], "mcp_description": "Returns a 0-100 US respiratory-illness activity score (latest weekly national ARI share of ED visits, CDC NSSP, keyless) with trend, season_high_low band, vs_4wk_avg, ~12-week recent_weeks history, and COVID/flu/RSV component_pathogens_pct split. Call when the user asks about flu, COVID, RSV, or \"sick season\" levels right now, or when timing healthcare staffing, OTC/test-kit inventory, or absenteeism planning." }, { "id": "ADW-573", "name": "US Treasury Fiscal Pulse", "domain": "Finance", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-573", "mcp_tool": "adw.adw_573", "sample": "https://alpinedataworks.com/showcase/adw-573", "description": "Fiscal-stress/debt-growth momentum for the US federal balance sheet: YoY growth of total public debt (Treasury Debt to the Penny, daily) mapped 0-100 and adjusted for the trend in the average interest rate on the debt. Includes latest total debt, YoY, 30d change, 12mo history. Keyless Treasury Fiscal Data.", "agent_question": "How fast is US federal debt growing right now, and is the interest burden rising?", "history_start": "1994-01-31", "history_years": 32.4, "product_class": "time-series", "tier": "Gold", "refresh": "quarterly", "source_apis": [ "US Treasury Fiscal Data \u2014 Debt to the Penny (api.fiscaldata.treasury.gov, keyless)", "US Treasury Fiscal Data \u2014 Average Interest Rates on U.S. Treasury Securities (keyless)" ], "mcp_description": "Returns a 0-100 US fiscal-stress score (YoY growth of total public debt from Treasury Debt to the Penny, adjusted for the trend in the average interest rate on the debt) with total_debt, debt_yoy, change_30d, interest_rate_trend, and 12-month history. Call when the user asks about federal debt growth, fiscal sustainability, deficits, or the US interest burden, or when timing duration, Treasury-supply, or fixed-vs-floating funding decisions." }, { "id": "ADW-574", "name": "US Labor Market Momentum", "domain": "Labor", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-574", "mcp_tool": "adw.adw_574", "sample": "https://alpinedataworks.com/showcase/adw-574", "description": "0-100 US labor-market health index from the keyless BLS API: unemployment-rate level (45%) + 3-month direction (25%) + nonfarm payroll MoM job growth (30%). Includes 12mo unemployment + payroll series and strength band. Monthly.", "agent_question": "How strong is the US labor market right now, and is it strengthening or weakening?", "history_start": "1948-04-01", "history_years": 78.3, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "BLS Public Data API v1 (api.bls.gov, keyless): LNS14000000 civilian unemployment rate (SA), CES0000000001 total nonfarm payrolls (SA)" ], "mcp_description": "Returns a 0-100 US labor-market health score (45% unemployment-rate level, 25% 3-month unemployment direction, 30% nonfarm payroll MoM job growth, from keyless BLS data) with trend, strength_band, top_drivers, and 12-month unemployment and payrolls series. Call when the user asks about US labor-market strength, jobs reports, unemployment, or hiring conditions, or when timing hiring plans, wage budgets, consumer-credit exposure, or macro allocation decisions." }, { "id": "ADW-575", "name": "AI Research Momentum Index", "domain": "Tech", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-575", "mcp_tool": "adw.adw_575", "sample": "https://alpinedataworks.com/showcase/adw-575", "description": "Daily 0-100 velocity index of AI/ML research on arXiv: papers/day across the 200 most-recent cs.AI/cs.LG/cs.CL submissions scaled by 7d momentum. Includes per-category counts + 8 most-recent titles. Leading attention signal for AI-sector strategy. Keyless.", "agent_question": "How fast is AI/ML research output moving right now \u2014 is the pace of new arXiv submissions accelerating?", "history_start": "1994-01-01", "history_years": 32.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "arXiv API \u2014 Cornell University (export.arxiv.org/api/query, keyless Atom XML; cat:cs.AI OR cs.LG OR cs.CL, sortBy=submittedDate)" ], "mcp_description": "Returns a 0-100 AI research velocity index (papers/day across the 200 most-recent arXiv cs.AI/cs.LG/cs.CL submissions, scaled by 7d momentum) with per-category counts and the 8 most-recent paper titles. Call when the user asks about AI/ML research pace, arXiv submission trends, or whether AI attention is accelerating, or when timing AI-sector launches, content, hiring, or allocation decisions. Daily, keyless, history to 1994." }, { "id": "ADW-576", "name": "Open-Source Momentum Index", "domain": "Tech", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-576", "mcp_tool": "adw.adw_576", "sample": "https://alpinedataworks.com/showcase/adw-576", "description": "Daily 0-100 index of open-source creation momentum from the GitHub Search API: count of repos created in the last 30d with >10 stars, scored vs a ~6,000-repo baseline and tilted by breakout (>100-star) share. Includes language mix + 8 hottest new repos. Keyless.", "agent_question": "How much momentum is flowing into new open-source projects right now?", "history_start": "2026-07-12", "history_years": 0.0, "product_class": "live", "tier": "Gold", "refresh": "daily", "source_apis": [ "GitHub Search API (api.github.com/search/repositories, keyless)" ], "mcp_description": "Returns a 0-100 open-source creation momentum index (new GitHub repos from the last 30 days with >10 stars, scored against a ~6,000-repo baseline and tilted by breakout >100-star share; keyless, daily) with momentum_score, breakout_share, language_mix, and the 8 hottest new repos. Call when the user asks about open-source momentum, GitHub trends, hot new repos, or language shifts, or when timing devtools launches, DevRel spend, or OSS deal sourcing." }, { "id": "ADW-577", "name": "Tech Community Pulse", "domain": "Tech", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-577", "mcp_tool": "adw.adw_577", "sample": "https://alpinedataworks.com/showcase/adw-577", "description": "Live 0-100 tech-community engagement gauge from the Hacker News front page (keyless Firebase API): point/comment velocity of the top-30 stories + share of high-engagement stories, with top-10 stories + a theme tally (AI/crypto/security/hardware...). Hourly.", "agent_question": "What is the tech community engaged with right now, and how intense is that engagement?", "history_start": "2007-03-03", "history_years": 19.4, "product_class": "time-series", "tier": "Gold", "refresh": "hourly", "source_apis": [ "Hacker News Firebase API (hacker-news.firebaseio.com/v0, topstories + item, keyless)" ], "mcp_description": "Returns a 0-100 tech-community engagement score (point/comment velocity of the Hacker News top-30 plus share of high-engagement stories; hourly, keyless Firebase source) with theme_tally, top_stories, high_engagement_share, and methodology_version. Call when the user asks what the tech community is talking about, how intense Hacker News engagement is right now, or whether AI/crypto/security dominates, or when timing a launch post, Show HN, or developer announcement." }, { "id": "ADW-578", "name": "Stablecoin Market Index", "domain": "Crypto", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-578", "mcp_tool": "adw.adw_578", "sample": "https://alpinedataworks.com/showcase/adw-578", "description": "Health/growth gauge (0-100) for the USD-stablecoin market from DeFiLlama (keyless): 30d total mcap growth (50%) + peg health = share of major (>=$1B) USD stablecoins within +/-0.5% of $1 (50%). Ships total mcap, top-8 stablecoins w/ prices, off-peg count, 30d history. Distinct from ADW-003/567.", "agent_question": "Is the stablecoin market growing and are the major pegs holding?", "history_start": "2021-03-02", "history_years": 5.4, "product_class": "time-series", "tier": "Gold", "refresh": "hourly", "source_apis": [ "DeFiLlama stablecoins API /stablecoins?includePrices=true \u2014 circulating supply + prices (stablecoins.llama.fi, keyless)", "DeFiLlama stablecoins API /stablecoincharts/all \u2014 daily total circulating history (stablecoins.llama.fi, keyless)" ], "mcp_description": "Returns a 0-100 USD-stablecoin market health score (50% 30-day total-mcap growth + 50% peg health \u2014 share of $1B+ stablecoins within +/-0.5% of $1; DeFiLlama, hourly) with total_mcap, top-8 stablecoin prices, off_peg_count, and 30-day history. Call when the user asks about stablecoin market growth, USDT/USDC peg stability, or depeg risk, or when timing stablecoin float sizing, collateral rotation, or settlement-rail decisions." }, { "id": "ADW-579", "name": "Global River Flood Risk Forecast", "domain": "Climate", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-579", "mcp_tool": "adw.adw_579", "sample": "https://alpinedataworks.com/showcase/adw-579", "description": "7-day forward river-flood risk across 12 major world rivers (Mississippi/Amazon/Ganges/Yangtze/Mekong/Nile/Rhine/Danube/Niger/Brahmaputra/Congo/Missouri): each river's GloFAS forecast peak discharge vs its climatological mean (>1.5x elevated, >2x high). Riskiest-first river table. Open-Meteo Flood, keyless.", "agent_question": "Which major world rivers are forecast to run above their flood-risk norms over the next 7 days?", "history_start": "2026-07-12", "history_years": 0.0, "product_class": "live", "tier": "Gold", "refresh": "daily", "source_apis": [ "Open-Meteo Flood API \u2014 GloFAS daily river_discharge/river_discharge_mean, 7-day horizon (flood-api.open-meteo.com/v1/flood, keyless)" ], "mcp_description": "Returns a 0-100 river-flood risk forecast (7-day GloFAS peak-discharge vs climatological norms at 12 major world rivers \u2014 Mississippi, Amazon, Ganges, Yangtze, Mekong, Rhine, more) with flood_level, rivers_elevated, max_discharge_ratio, highest_risk_river, and a riskiest-first per-river table. Call when the user asks about flooding, river levels, or discharge anomalies, or when timing barge logistics, commodity-shipping, or disaster-response decisions." }, { "id": "ADW-580", "name": "US Dollar Strength Index", "domain": "Markets", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-580", "mcp_tool": "adw.adw_580", "sample": "https://alpinedataworks.com/showcase/adw-580", "description": "DXY-style trade-weighted USD strength gauge from ECB reference rates (Frankfurter, keyless): geometric index over the classic DXY basket. Score 0-100 blends trailing-90d level percentile (60%) + 30d momentum (40%). Includes 30d history + per-currency basket. Distinct from ADW-564 (FX vol).", "agent_question": "How strong is the US dollar right now, and is it strengthening or weakening?", "history_start": "1999-03-07", "history_years": 27.3, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Frankfurter \u2014 ECB daily foreign-exchange reference rates (api.frankfurter.dev, keyless)" ], "mcp_description": "Returns a 0-100 US dollar strength score (geometric index over the classic DXY basket from daily keyless ECB reference rates; 60% trailing-90d level percentile + 40% 30d momentum) with per-currency basket contributions, 30-day history, and methodology_version. Call when the user asks about dollar strength, USD strengthening or weakening, or DXY-style direction, or when timing FX hedges, import/export pricing, or dollar-sensitive allocation." }, { "id": "ADW-581", "name": "ENSO Climate Regime Index", "domain": "Climate", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-581", "mcp_tool": "adw.adw_581", "sample": "https://alpinedataworks.com/showcase/adw-581", "description": "El Nino / La Nina climate-regime state from NOAA CPC's official Oceanic Nino Index (Nino 3.4 SST anomaly, keyless). 0-100 score (50=neutral, ->100 El Nino, ->0 La Nina) with NOAA state label, episode strength, 3-season trend, last 12 seasonal ONI. Drives global weather/ag/energy/commodity risk.", "agent_question": "Are we in El Nino, La Nina, or neutral right now, and how strong is the episode?", "history_start": "1950-01-31", "history_years": 76.4, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "NOAA Climate Prediction Center ONI (cpc.ncep.noaa.gov oni.ascii.txt, 3-month running SST anomaly, keyless)" ], "mcp_description": "Returns a 0-100 ENSO climate-regime score (NOAA CPC Oceanic Nino Index, Nino 3.4 SST anomaly; 50=neutral, higher=El Nino, lower=La Nina) with official NOAA state label, episode_strength, 3-season trend, and last 12 seasonal ONI values. Call when the user asks about El Nino, La Nina, ENSO state or strength, or when timing weather-sensitive agriculture, energy, commodity, or catastrophe-risk decisions." }, { "id": "ADW-582", "name": "Near-Earth Object Activity Index", "domain": "Novelty", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-582", "mcp_tool": "adw.adw_582", "sample": "https://alpinedataworks.com/showcase/adw-582", "description": "Daily 0-100 index of near-Earth asteroid activity from NASA NeoWs (keyless): every known close approach in the next 7 days weighted by proximity (inside 1 lunar distance = very close), size, and hazard flag, vs a typical week. Includes 8 most notable approaches + per-day count.", "agent_question": "How much asteroid close-approach activity is Earth seeing in the next 7 days?", "history_start": "2000-01-03", "history_years": 26.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "NASA NeoWs \u2014 Near Earth Object Web Service feed (api.nasa.gov/neo/rest/v1/feed, keyless via DEMO_KEY)" ], "mcp_description": "Returns a 0-100 index of near-Earth asteroid activity over the next 7 days (NASA NeoWs close approaches weighted by proximity, size, and hazard flag vs a typical week) with score, trend, confidence, and top_drivers naming the 8 most notable approaches plus per-day counts. Call when the user asks about asteroid flybys, close approaches, or hazardous objects near Earth, or when timing space-themed content or programming around peak activity." }, { "id": "ADW-583", "name": "Federal Regulatory Activity Index", "domain": "Public Sector", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-583", "mcp_tool": "adw.adw_583", "sample": "https://alpinedataworks.com/showcase/adw-583", "description": "Daily 0-100 velocity index of US federal rulemaking: Federal Register documents published in the last 7 days vs the trailing-28-day daily baseline (50 = normal pace). Includes a by-type split (final rules, proposed rules, notices, presidential documents) and the EO 12866 significant-document count. Computed live from the official keyless Federal Register API v1.", "agent_question": "Is US federal rulemaking accelerating or slowing right now, and how much of it is significant regulation?", "history_start": "1994-02-13", "history_years": 32.4, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Federal Register API v1 (federalregister.gov/api/v1/documents.json, keyless, official GPO/NARA)" ], "mcp_description": "Returns a 0-100 US federal rulemaking velocity index (last-7-day Federal Register publications vs a trailing-28-day baseline; 50 = normal pace) with activity_level, trend, by_type split (rules, proposed_rules, notices, presidential), and the EO 12866 significant_docs_7d count. Call when the user asks about regulatory surges, slowdowns, midnight rulemaking, or deregulation waves, or when timing compliance staffing, comment-period responses, or policy-sensitive positioning." }, { "id": "ADW-584", "name": "US Patent Activity Index", "domain": "Tech", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-584", "mcp_tool": "adw.adw_584", "sample": "https://alpinedataworks.com/showcase/adw-584", "description": "Velocity index of US patent grants (USPTO): recent grant volume vs a trailing baseline, mapped 0-100. Includes recent representative grants. Computed live from a keyless USPTO/PatentsView endpoint.", "agent_question": "Is the pace of US patent grants accelerating or slowing right now?", "history_start": "1976-01-01", "history_years": 49.8, "product_class": "live", "tier": "Gold", "refresh": "weekly", "source_apis": [ "USPTO PatentsView API (api.patentsview.org/patents/query)" ], "mcp_description": "Returns a 0-100 US patent grant velocity index (recent USPTO grant volume vs a trailing baseline, computed live from keyless PatentsView data) with score, trend, confidence, top_drivers, recent representative grants, freshness, and methodology_version. Call when the user asks about patent activity, USPTO grant pace, innovation output, or R&D cycles, or when timing patent-landscape refreshes, prosecution staffing, or competitive IP monitoring." }, { "id": "ADW-587", "name": "Crypto Fear & Greed Index", "domain": "Crypto", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-587", "mcp_tool": "adw.adw_587", "sample": "https://alpinedataworks.com/showcase/adw-587", "description": "Daily crypto market-sentiment gauge (0 = extreme fear, 100 = extreme greed) passing through the alternative.me Fear & Greed composite (volatility, momentum/volume, social media, BTC dominance, search trends), with classification label, 7d change, 30d average, and 30-day daily history. The crowd-emotion axis - complements ADW-567 market breadth and the on-chain whale products.", "agent_question": "What is the emotional sentiment of the crypto market right now - fear or greed, and which way is it moving?", "history_start": "2018-02-01", "history_years": 8.4, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "alternative.me Crypto Fear & Greed Index \u2014 third-party composite sentiment index, passed through as-is (api.alternative.me/fng, keyless)" ], "mcp_description": "Returns a 0-100 crypto market sentiment score (alternative.me Fear & Greed composite of volatility, momentum/volume, social media, BTC dominance, and search trends) with classification label, 7-day change, 30-day average, and 30-day daily history. Call when the user asks about crypto market mood, fear vs. greed, sentiment extremes, or contrarian signals, or when timing crypto entries, exits, or rebalancing around emotional peaks and troughs." }, { "id": "ADW-588", "name": "Python Ecosystem Activity Index", "domain": "Tech", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-588", "mcp_tool": "adw.adw_588", "sample": "https://alpinedataworks.com/showcase/adw-588", "description": "Real-time 0-100 momentum index for the Python package ecosystem. Blends PyPI release velocity (updates RSS feed time span vs a 250/h baseline, 60% weight), brand-new package registration pace (newest-packages RSS vs 30/h baseline, 25% weight), and best-effort download momentum of 5 bellwether packages (numpy, pandas, requests, boto3, torch) via pypistats (15% weight). 50 = typical pace; each leg capped at 2x baseline. Includes the 10 most recent releases and bellwether download counts. Keyless sources; hourly cadence.", "agent_question": "How active is the Python package ecosystem right now vs its typical pace?", "history_start": "2026-07-12", "history_years": 0.0, "product_class": "live", "tier": "Gold", "refresh": "hourly", "source_apis": [ "PyPI recent-updates RSS (pypi.org/rss/updates.xml, keyless)", "PyPI newest-packages RSS (pypi.org/rss/packages.xml, keyless)", "pypistats recent downloads (pypistats.org/api, keyless, best-effort)" ], "mcp_description": "Returns a 0-100 Python package ecosystem activity index (PyPI release velocity vs a 250/h baseline, new-package registration pace, bellwether download momentum for numpy/pandas/requests/boto3/torch; 50 = typical, hourly) with score, per-leg drivers, 10 most-recent releases, and bellwether download counts. Call when the user asks about PyPI activity, Python ecosystem momentum, or release surges, or when timing dependency refreshes, mirror syncs, or package launches." }, { "id": "ADW-589", "name": "US Drug Overdose Mortality Index", "domain": "Health", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-589", "mcp_tool": "adw.adw_589", "sample": "https://alpinedataworks.com/showcase/adw-589", "description": "Trajectory of US drug-overdose deaths from CDC NCHS VSRR provisional counts (keyless, resource xkb8-kh2a). Score 0-100 positions the latest 12-month-ending national overdose death count within its trailing 5-year range (70%) blended with year-over-year direction (30%); higher = heavier/worsening burden. Includes latest and prior-year 12-month counts, YoY change, CDC lag-adjusted predicted count, 12-month recent_months series, and explicit provisional reporting-period disclosure (~4-6 month lag). Monthly cadence. Distinct from ADW-572 (respiratory ED activity).", "agent_question": "How heavy is the current US drug-overdose mortality burden and is it rising or falling?", "history_start": "2016-01-31", "history_years": 10.4, "product_class": "time-series", "tier": "Gold", "refresh": "monthly", "source_apis": [ "CDC NCHS VSRR Provisional Drug Overdose Death Counts (data.cdc.gov resource xkb8-kh2a, state='US', indicator='Number of Drug Overdose Deaths', keyless Socrata)" ], "mcp_description": "Returns a 0-100 US drug-overdose mortality index (latest 12-month CDC NCHS VSRR death count in its trailing 5-year range, 70/30 with YoY direction; higher = worsening) with latest/prior-year counts, yoy_change, lag-adjusted predicted_count, recent_months, and provisional reporting_period (~4-6mo lag). Call when the user asks about overdose deaths, the opioid crisis, or drug-mortality trends, or when timing behavioral-health capacity, naloxone supply, or settlement-fund decisions." }, { "id": "ADW-590", "name": "Global Marine Heat Index", "domain": "Climate", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-590", "mcp_tool": "adw.adw_590", "sample": "https://alpinedataworks.com/showcase/adw-590", "description": "Daily 0-100 snapshot of sea-surface warmth across 12 climate-relevant ocean regions (Nino 3.4, North Atlantic, Gulf Stream, Coral Sea, Mediterranean, Caribbean, Bering Sea, Arabian Sea, Bay of Bengal, California Current, Gulf of Mexico, Tasman Sea). Blends breadth (share of regions >= +0.5C above a rough embedded seasonal reference, 0-60 pts) with intensity (mean anomaly mapped 0->+2C, 0-40 pts) from Open-Meteo Marine SST. Warmth snapshot with an approximate sinusoid baseline - a screening signal, not a validated marine-heatwave climatology.", "agent_question": "How much of the global ocean surface is running notably warm right now, and which regions are hottest vs seasonal normal?", "history_start": "2026-07-12", "history_years": 0.0, "product_class": "live", "tier": "Gold", "refresh": "daily", "source_apis": [ "Open-Meteo Marine API \u2014 daily sea_surface_temperature_max at 12 hardcoded ocean points (marine-api.open-meteo.com/v1/marine, keyless)", "Seasonal reference: embedded rough climatological sinusoid per region (annual-mean SST + seasonal amplitude + peak month, approximated from public SST climatology)" ], "mcp_description": "Returns a 0-100 global marine heat score (share of 12 ocean regions \u2265 +0.5\u00b0C above seasonal normal plus mean-anomaly intensity, daily Open-Meteo SST) with marine_heat_score, warmth_level, warmest_region, and a per-region anomaly table. Call when the user asks about ocean warmth, SST anomalies, marine heatwaves, or coral-bleaching risk, or when timing hurricane-exposure reviews or aquaculture harvests. Screening signal, not validated MHW climatology." }, { "id": "ADW-591", "name": "Cyber Threat Activity Index", "domain": "Tech", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-591", "mcp_tool": "adw.adw_591", "sample": "https://alpinedataworks.com/showcase/adw-591", "description": "Active-exploitation pressure index from the CISA Known Exploited Vulnerabilities catalog: pace of CVEs added to KEV in the last 30 days vs the trailing 90-day baseline, weighted for ransomware-linked share, with top-vendor breakdown and the 10 most recent exploited-in-the-wild additions. Daily cadence, keyless federal source.", "agent_question": "How fast are new actively-exploited software vulnerabilities appearing right now, and which vendors are driving the surge?", "history_start": "2022-03-04", "history_years": 4.4, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "CISA Known Exploited Vulnerabilities catalog (cisa.gov JSON feed)" ], "mcp_description": "Returns a 0-100 active-exploitation pressure index (30-day pace of CISA KEV catalog additions vs the trailing 90-day baseline, weighted for ransomware-linked share) with threat_activity_score, ransomware_linked_share, top_vendors, and recent_additions (10 newest exploited-in-the-wild CVEs). Call when the user asks about vulnerability exploitation surges, KEV additions, ransomware pressure, or which vendors are driving CVE activity, or when timing emergency patch windows or patch-SLA escalation." }, { "id": "ADW-592", "name": "Global Volcanic Activity Index", "domain": "Geophysics", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-592", "mcp_tool": "adw.adw_592", "sample": "https://alpinedataworks.com/showcase/adw-592", "description": "Weekly 0-100 index of current worldwide volcanic activity from the Smithsonian Global Volcanism Program / USGS Weekly Volcanic Activity Report (count of volcanoes with ongoing or new eruptions/unrest vs a typical week of ~15-25), boosted by new-activity flags and US volcanoes at USGS WATCH/WARNING alert. Includes the full active-volcano list with per-volcano activity summaries and US elevated-alert detail.", "agent_question": "How much volcanic unrest and eruptive activity is happening worldwide right now, and which volcanoes are escalating?", "history_start": "2026-07-12", "history_years": 0.0, "product_class": "live", "tier": "Gold", "refresh": "weekly", "source_apis": [ "Smithsonian Global Volcanism Program / USGS \u2014 Weekly Volcanic Activity Report RSS (volcano.si.edu/news/WeeklyVolcanoRSS.xml, keyless)", "USGS Volcano Hazards Program \u2014 HANS elevated-volcanoes API (volcanoes.usgs.gov/hans-public/api/volcano/getElevatedVolcanoes, keyless)" ], "mcp_description": "Returns a 0-100 global volcanic activity index (count of volcanoes erupting or in unrest in this week's Smithsonian GVP/USGS report vs a typical week's 15-25, boosted for new activity and US WATCH/WARNING alerts) with score, trend, activity_level, new_this_week, per-volcano active list, and us_alerts. Call when the user asks about volcanic eruptions, unrest, ash risk, or which volcanoes are escalating, or when timing aviation-routing, travel, or catastrophe-exposure reviews." }, { "id": "ADW-593", "name": "JavaScript Ecosystem Activity Index", "domain": "Tech", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-593", "mcp_tool": "adw.adw_593", "sample": "https://alpinedataworks.com/showcase/adw-593", "description": "Momentum of the JavaScript/npm ecosystem from the keyless npm downloads API: aggregate weekly downloads of 8 bellwether packages (react, express, lodash, axios, typescript, next, vue, webpack), most recent 7 days vs the average of the 3 prior weekday-aligned 7-day windows to neutralize weekly seasonality. 0-100 score (50 = flat WoW; rising downloads = healthy, growing ecosystem) with per-package weekly volumes and WoW changes, total weekly downloads, top package, and fastest grower. Distinct from ADW-588 (Python/PyPI).", "agent_question": "Is the JavaScript/npm package ecosystem growing or cooling right now, and which bellwether packages are driving the move?", "history_start": "2015-03-07", "history_years": 11.3, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "npm downloads API (api.npmjs.org/downloads/range/last-month, keyless)" ], "mcp_description": "Returns a 0-100 JavaScript/npm ecosystem momentum score (weekly downloads of 8 bellwether packages \u2014 react, express, lodash, axios, typescript, next, vue, webpack \u2014 vs 3 prior weekday-aligned weeks; 50 = flat) with per-package volumes and WoW changes, total weekly downloads, top_package, and fastest_grower. Call when the user asks whether the JS/npm ecosystem is growing or cooling or which packages are moving, or when timing devtools launches or developer-marketing spend. Python: ADW-588." }, { "id": "ADW-594", "name": "Space Weather Event Index", "domain": "Geophysics", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-594", "mcp_tool": "adw.adw_594", "sample": "https://alpinedataworks.com/showcase/adw-594", "description": "Unified space-weather EVENT stream from NASA DONKI: counts and severity-weights significant events (CMEs, M/X-class flares, geomagnetic storms) over the trailing 14 days into a 0-100 activity index calibrated against a typical fortnight, with per-type counts and the 8 most recent events. Complements ADW-550 (current Kp storm level) and ADW-563 (current X-ray flux) with the discrete event-notification view.", "agent_question": "How eventful has space weather been recently - how many significant CMEs, M/X-class solar flares, and geomagnetic storms in the last 14 days?", "history_start": "2010-04-01", "history_years": 16.3, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "NASA DONKI CME catalog (api.nasa.gov/DONKI/CME, DEMO_KEY keyless)", "NASA DONKI solar-flare catalog (api.nasa.gov/DONKI/FLR, DEMO_KEY keyless)", "NASA DONKI geomagnetic-storm catalog (api.nasa.gov/DONKI/GST, DEMO_KEY keyless)" ], "mcp_description": "Returns a 0-100 space-weather event index (severity-weighted counts of significant CMEs, M/X-class flares, and geomagnetic storms from NASA DONKI, trailing 14 days calibrated to a typical fortnight) with activity_index, per-type event counts, and recent_events (latest 8). Call when the user asks how eventful space weather has been recently or how many flares, CMEs, or storms occurred, or when timing satellite maneuvers, HF communications, or GNSS-precision fieldwork." }, { "id": "ADW-595", "name": "Federal Campaign Finance Activity", "domain": "Public Sector", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-595", "mcp_tool": "adw.adw_595", "sample": "https://alpinedataworks.com/showcase/adw-595", "description": "Measures the velocity of US federal political money on a 0-100 scale: combined contributions and spending across all FEC-registered candidate, PAC, and party committees over the last three lag-safe months, scored against the same window of the prior same-type election cycle and the current cycle's trailing six-month pace. Above 58 = accelerating; below 42 = decelerating.", "agent_question": "How fast is US federal political money moving right now compared to the prior election cycle?", "history_start": "1980-01-01", "history_years": 45.5, "product_class": "live", "tier": "Gold", "refresh": "weekly", "source_apis": [ "FEC Federal Election Commission API (api.open.fec.gov/v1)" ], "mcp_description": "Returns a 0-100 US federal political-money velocity score (contributions and spending across all FEC-registered candidate, PAC, and party committees, last three lag-safe months vs prior same-type cycle; >58 accelerating, <42 decelerating) with score, vs_prior_cycle, vs_trailing_pace, drivers, confidence, and methodology_version. Call when the user asks how fast campaign money is moving, about fundraising or PAC spending pace, or when timing political-ad inventory or government-affairs budgets." }, { "id": "ADW-596", "name": "US Chronic Disease Burden Index", "domain": "Health", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-596", "mcp_tool": "adw.adw_596", "sample": "https://alpinedataworks.com/showcase/adw-596", "description": "Composite 0-100 index of major US chronic-disease mortality burden and trajectory from CDC NCHS VSRR quarterly estimates: the age-adjusted 12-month-ending death rates for heart disease, diabetes, and stroke, positioned within the trailing quarterly range (70%) and blended with year-over-year direction (30%); higher = heavier or worsening burden.", "agent_question": "How heavy is the US chronic-disease mortality burden (heart disease, diabetes, stroke) right now, and is it rising or falling?", "history_start": "1999-01-01", "history_years": 26.5, "product_class": "live", "tier": "Gold", "refresh": "quarterly", "source_apis": [ "CDC WONDER Multiple Cause of Death + NCHS Vital Statistics (wonder.cdc.gov/wonder/help/mcd.html)" ], "mcp_description": "Returns a 0-100 US chronic-disease mortality burden index (CDC NCHS VSRR age-adjusted 12-month-ending death rates for heart disease, diabetes, stroke; 70% trailing-range position + 30% year-over-year direction; higher = worse) with score, per-cause drivers, direction, confidence, and methodology_version. Call when the user asks about US chronic-disease burden or heart-disease, diabetes, or stroke mortality trends, or when timing population-health, actuarial, or care-market decisions." }, { "id": "ADW-597", "name": "US Severe Storm Activity Index", "domain": "Natural Hazard", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-597", "mcp_tool": "adw.adw_597", "sample": "https://alpinedataworks.com/showcase/adw-597", "description": "Recent US severe convective storm activity on a 0-100 scale from NOAA Storm Prediction Center ground-truth reports of tornadoes, hail, and damaging wind over the last 7 complete convective days, blending absolute report volume with anomaly versus the trailing 21-day baseline.", "agent_question": "How much severe storm activity (tornadoes, hail, damaging wind) has the US actually experienced in the last week versus the recent norm?", "history_start": "1955-01-01", "history_years": 70.5, "product_class": "live", "tier": "Gold", "refresh": "daily", "source_apis": [ "NOAA SPC storm reports + Storm Events Database (www.spc.noaa.gov/climo/reports)" ], "mcp_description": "Returns a 0-100 US severe storm activity index (NOAA Storm Prediction Center ground-truth tornado, hail, and damaging-wind reports over the last 7 convective days, blending report volume with anomaly versus a trailing 21-day baseline) with score, per-hazard drivers, confidence, and methodology_version. Call when the user asks about recent tornado, hail, or wind activity versus the norm, or when timing claims staffing, catastrophe logistics, or storm-repair inventory decisions." }, { "id": "ADW-598", "name": "Global Knowledge Production Index", "domain": "Tech", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-598", "mcp_tool": "adw.adw_598", "sample": "https://alpinedataworks.com/showcase/adw-598", "description": "0-100 index of global Wikipedia editing velocity: recent worldwide daily edits across all Wikimedia projects and en.wikipedia active editors compared against their trailing 180-day baselines. 50 = at baseline; higher = knowledge production surging. Measures editing activity, distinct from reading attention.", "agent_question": "How fast is the world producing and maintaining encyclopedic knowledge right now?", "history_start": "2001-01-15", "history_years": 24.5, "product_class": "live", "tier": "Gold", "refresh": "daily", "source_apis": [ "Wikimedia Foundation Recent Changes Stream + Wikipedia Statistics (stream.wikimedia.org/v2/stream/recentchange)" ], "mcp_description": "Returns a 0-100 global knowledge-production index (worldwide daily edits across all Wikimedia projects plus en.wikipedia active editors vs trailing 180-day baselines; 50 = baseline; editing activity, not pageviews) with score, trend, top_drivers, confidence, freshness, and methodology_version. Call when the user asks about Wikipedia editing velocity, encyclopedic knowledge growth, or open-knowledge community health, or when timing corpus refreshes, dataset snapshots, or knowledge-base sync runs." }, { "id": "ADW-599", "name": "Federal Litigation Activity Index", "domain": "Public Sector", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-599", "mcp_tool": "adw.adw_599", "sample": "https://alpinedataworks.com/showcase/adw-599", "description": "Velocity index (0-100) of new US federal court case filings: last-7-day docket filing pace versus the trailing-28-day daily norm from CourtListener, where 50 is normal, above 50 signals a litigation surge, and below 50 a lull; published-opinion velocity is a secondary decide-side signal.", "agent_question": "Is US federal court litigation activity surging or quiet right now versus its recent norm?", "history_start": "2004-01-01", "history_years": 21.5, "product_class": "live", "tier": "Gold", "refresh": "weekly", "source_apis": [ "CourtListener PACER free-tier federal court filings (www.courtlistener.com/api/rest/v3)" ], "mcp_description": "Returns a 0-100 US federal litigation activity index (last-7-day new-case filing pace vs the trailing-28-day daily norm from CourtListener dockets; 50 = normal, above = surge, below = lull) with value, drivers, confidence, and methodology_version. Call when the user asks about federal court filing volume, litigation surges or lulls, or when timing litigation staffing, case intake, or legal-exposure decisions." }, { "id": "ADW-600", "name": "UK Power Price Volatility Pulse", "domain": "Energy", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-600", "mcp_tool": "adw.adw_600", "sample": "https://alpinedataworks.com/showcase/adw-600", "description": "Tracks UK half-hourly dynamic electricity tariff prices (Octopus Agile, London region) and scores the trailing 24 hours against the trailing-month baseline. A live cost-pressure gauge for energy-intensive UK operations: spikes flag procurement stress and load-shifting opportunity windows, dips flag cheap-power windows.", "agent_question": "How stressed are UK real-time retail electricity prices versus the trailing month?", "history_start": "2024-10-01", "history_years": 1.8, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Octopus Energy API \u2014 Agile tariff standard unit rates (api.octopus.energy/v1/products/AGILE-24-10-01/..., keyless)" ], "mcp_description": "Returns a 0-100 UK retail electricity price-stress score (trailing 24h of Octopus Agile half-hourly London rates scored against a trailing-month baseline, refreshed daily) with trend, z_score, momentum_vs_baseline_pct, recent vs baseline averages, and peak/trough dates and values. Call when the user asks about UK power price spikes, cheap-electricity windows, or energy cost pressure, or when timing load-shifting, EV charging, or flexible industrial runs." }, { "id": "ADW-601", "name": "US Mortgage Complaint Stress", "domain": "Finance", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-601", "mcp_tool": "adw.adw_601", "sample": "https://alpinedataworks.com/showcase/adw-601", "description": "Scores CFPB mortgage-product complaint velocity (rolling 90-day count vs 8 trailing 90-day windows). Rising complaint flow is an early borrower-distress and servicing-friction signal that leads delinquency data; useful for housing-credit risk desks, mortgage servicers, and housing-market analysts.", "agent_question": "Is US mortgage-borrower complaint volume accelerating versus its 2-year baseline?", "history_start": "2011-12-01", "history_years": 14.6, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "CFPB Consumer Complaint Database search API (consumerfinance.gov/data-research/consumer-complaints/search/api/v1/, keyless)" ], "mcp_description": "Returns a 0-100 US mortgage complaint stress score (rolling 90-day CFPB mortgage-complaint count scored against 8 trailing 90-day windows, a 2-year baseline; daily, history to 2011) with trend, z_score, recent_window_count, baseline_window_mean/std, and per-window counts. Call when the user asks about mortgage borrower distress, servicing friction, CFPB complaint trends, or housing-credit stress, or when timing delinquency forecasts, loss-mitigation staffing, or mortgage-credit risk positioning." }, { "id": "ADW-602", "name": "Biotech Preprint Velocity", "domain": "Health", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-602", "mcp_tool": "adw.adw_602", "sample": "https://alpinedataworks.com/showcase/adw-602", "description": "Measures the velocity of new bioRxiv preprint postings (rolling 90-day new-paper count vs 8 trailing windows). Preprints lead peer-reviewed publication by months, making this an early gauge of life-science R&D output momentum for pharma strategy, biotech investors, and research-intelligence teams.", "agent_question": "Is the flow of new biology preprints accelerating versus the trailing 2-year baseline?", "history_start": "2013-11-01", "history_years": 12.7, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "bioRxiv API \u2014 details endpoint interval counts (api.biorxiv.org/details/biorxiv/{from}/{to}/, keyless)" ], "mcp_description": "Returns a 0-100 biotech preprint-velocity score (rolling 90-day bioRxiv new-paper count vs 8 trailing 90-day windows) with trend, z_score, recent_window_count, baseline_window_mean, baseline_window_std, per_variant_w0, and window_counts. Call when the user asks whether life-science R&D output or new-biology preprint flow is accelerating, or when timing pharma horizon-scanning, biotech investment, or research-intelligence decisions against a trailing 2-year baseline." }, { "id": "ADW-603", "name": "US Food & Supplement Adverse-Event Pulse", "domain": "Health", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-603", "mcp_tool": "adw.adw_603", "sample": "https://alpinedataworks.com/showcase/adw-603", "description": "Scores FDA CAERS adverse-event report velocity for foods, dietary supplements, and cosmetics (90-day report count vs 8 trailing windows). A brand-safety and product-liability early-warning gauge for CPG brands, supplement makers, insurers, and retail category managers \u2014 distinct from drug-safety (FAERS) coverage.", "agent_question": "Are FDA food, dietary-supplement, and cosmetic adverse-event reports surging versus baseline?", "history_start": "2004-01-01", "history_years": 22.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "openFDA Food Adverse Event API \u2014 CAERS (api.fda.gov/food/event.json, keyless)" ], "mcp_description": "Returns a 0-100 US food, dietary-supplement, and cosmetic adverse-event pulse (FDA CAERS 90-day report velocity vs 8 trailing baseline windows, daily, history to 2004) with score, trend, z_score, recent_window_count, baseline_window_mean/std, and window_counts. Call when the user asks about food or supplement safety surges, CAERS report spikes, or brand-safety risk, or when timing recall preparedness, ad pauses, quality investigations, or liability reserving." }, { "id": "ADW-604", "name": "US Clean-Air Enforcement Pressure", "domain": "Climate", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-604", "mcp_tool": "adw.adw_604", "sample": "https://alpinedataworks.com/showcase/adw-604", "description": "Scores EPA ECHO federal Clean Air Act enforcement-case velocity (90-day case count vs 12 trailing windows). Rising air-enforcement pressure signals regulatory-compliance cost risk for manufacturers, utilities, refiners, and their insurers \u2014 the air-program sibling of the water-enforcement index (ADW-432).", "agent_question": "Is federal Clean Air Act enforcement-case velocity rising versus its 3-year baseline?", "history_start": "2001-01-01", "history_years": 25.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "EPA ECHO case REST services (echodata.epa.gov/echo/case_rest_services.get_cases, keyless)" ], "mcp_description": "Returns a 0-100 US federal Clean Air Act enforcement-pressure score (EPA ECHO 90-day case velocity z-scored against 12 trailing windows, daily refresh, history to 2001) with trend, z_score, recent_window_count, and baseline_window_mean/std. Call when the user asks about EPA air enforcement intensity, Clean Air Act compliance risk, or regulatory heat on manufacturers, utilities, or refiners, or when timing compliance spend, audit scheduling, or environmental-liability underwriting." }, { "id": "ADW-605", "name": "US Small-Business Credit Tightening Index", "domain": "Finance", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-605", "mcp_tool": "adw.adw_605", "sample": "https://alpinedataworks.com/showcase/adw-605", "description": "Scores the Fed Senior Loan Officer Survey net-percentage of banks tightening C&I lending standards for small firms (FRED DRTSCIS), latest two quarters vs a 15-year baseline. A leading SMB credit-crunch gauge for lenders, B2B credit desks, and SMB-exposed suppliers; historically leads small-business defaults and formation slowdowns.", "agent_question": "Are US banks tightening C&I lending standards for small firms versus the trailing norm?", "history_start": "1990-04-01", "history_years": 36.2, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "FRED API \u2014 DRTSCIS, Net Percentage of Banks Tightening Standards for C&I Loans to Small Firms (api.stlouisfed.org, registered key)" ], "mcp_description": "Returns a 0-100 US small-business credit tightening score (Fed Senior Loan Officer Survey net percentage of banks tightening C&I standards for small firms, FRED DRTSCIS, latest two quarters vs a 15-year baseline) with trend, z_score, composite_latest_value/date, and baseline stats. Call when the user asks about SMB lending conditions, bank credit standards, or credit-crunch risk, or when timing SMB lending, trade-credit terms, or small-business-exposed revenue decisions." }, { "id": "ADW-606", "name": "US Construction Labor-Cost Divergence", "domain": "Economy", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-606", "mcp_tool": "adw.adw_606", "sample": "https://alpinedataworks.com/showcase/adw-606", "description": "Scores the spread between construction and manufacturing average-hourly-earnings growth (BLS CES 2000000003 vs 3000000003, year-over-year). A widening spread flags construction-specific labor scarcity that pressures homebuilder margins and forward housing starts; relevant to builders, developers, and housing-market analysts.", "agent_question": "Is construction wage growth outrunning manufacturing wage growth, signaling building-trades labor scarcity?", "history_start": "2006-03-01", "history_years": 20.3, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "BLS Public Data API v2 \u2014 CES2000000003 (construction AHE) + CES3000000003 (manufacturing AHE) (api.bls.gov, registered key)" ], "mcp_description": "Returns a 0-100 construction labor-cost divergence score (spread between year-over-year construction and manufacturing average-hourly-earnings growth, BLS CES CES2000000003 vs CES3000000003) with score, trend, z_score, and 20-year baseline composites. Call when the user asks about construction wage pressure, building-trades labor scarcity, or homebuilder margin risk, or when timing bid escalation contingencies, subcontractor rate locks, or housing-starts exposure." }, { "id": "ADW-607", "name": "US Gasoline Crack-Spread Pressure", "domain": "Energy", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-607", "mcp_tool": "adw.adw_607", "sample": "https://alpinedataworks.com/showcase/adw-607", "description": "Scores a daily Gulf Coast gasoline crack-spread proxy (conventional gasoline spot x 42 minus WTI spot, $/bbl) \u2014 the refining margin that transmits crude moves into pump prices. Widening spreads flag downstream cost shocks for fuel buyers, fleets, airlines, and CPI watchers; compression flags refining-margin pain.", "agent_question": "Is the US gasoline-over-crude refining spread widening versus its trailing norm?", "history_start": "1986-06-02", "history_years": 40.1, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "FRED API \u2014 DGASUSGULF (Gulf Coast conventional gasoline spot) + DCOILWTICO (WTI spot) (api.stlouisfed.org, registered key)" ], "mcp_description": "Returns a 0-100 US gasoline crack-spread pressure score (daily Gulf Coast conventional-gasoline spot x 42 minus WTI spot, $/bbl, scored against its trailing baseline on 40 years of FRED history) with trend, z_score, composite_latest_value, and baseline averages. Call when the user asks about refining margins, gasoline-versus-crude spreads, pump-price pass-through, or fuel-cost inflation, or when timing fuel purchases, hedges, or CPI energy calls." }, { "id": "ADW-608", "name": "US Manufacturing-Construction Boom Index", "domain": "Economy", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-608", "mcp_tool": "adw.adw_608", "sample": "https://alpinedataworks.com/showcase/adw-608", "description": "Scores year-over-year growth of private manufacturing construction put-in-place (Census via FRED PRMFGCON) \u2014 the fab/factory-buildout pulse behind reshoring and CHIPS-era capex. Leads equipment orders and industrial hiring; relevant to industrial suppliers, construction firms, logistics planners, and regional developers.", "agent_question": "Is US private manufacturing-construction spending accelerating versus its trailing norm?", "history_start": "1993-01-01", "history_years": 33.5, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "FRED API \u2014 PRMFGCON, Total Private Construction Spending: Manufacturing (api.stlouisfed.org, registered key)" ], "mcp_description": "Returns a 0-100 US manufacturing-construction boom score (YoY growth of private manufacturing construction put-in-place, Census via FRED PRMFGCON, z-scored against a 33.5-year baseline) with trend, z_score, and composite baseline stats. Call when the user asks about fab/factory buildout, reshoring, CHIPS-era capex, or industrial construction momentum, or when timing equipment-supply, construction-bid, or logistics-capacity decisions \u2014 it leads equipment orders and industrial hiring." }, { "id": "ADW-609", "name": "US Wage vs Business-Formation Divergence", "domain": "Economy", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-609", "mcp_tool": "adw.adw_609", "sample": "https://alpinedataworks.com/showcase/adw-609", "description": "Scores the spread between private wage growth (FRED CES0500000003 YoY) and business-application growth (Census BFS via FRED BABATOTALSAUS YoY). When labor costs accelerate while new-business formation stalls, SMB unit economics compress \u2014 an early SMB-liquidity-crunch flag for lenders, B2B SaaS, and payroll/benefits providers.", "agent_question": "Is wage inflation outpacing new-business formation, squeezing small-business viability?", "history_start": "2007-03-01", "history_years": 19.4, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "FRED API \u2014 CES0500000003 (avg hourly earnings, total private) + BABATOTALSAUS (business applications) (api.stlouisfed.org, registered key)" ], "mcp_description": "Returns a 0-100 US wage-vs-business-formation divergence score (YoY spread of FRED avg hourly earnings CES0500000003 vs Census business applications BABATOTALSAUS, z-scored on a 2007 baseline) with trend, z_score, composite_recent_avg, composite_baseline_avg, and points_analyzed. Call when the user asks about wage inflation, SMB viability, labor-cost squeeze, or new-business formation, or when timing SMB credit tightening, payroll-segment forecasts, or small-business exposure decisions." }, { "id": "ADW-610", "name": "US Battery-Supply Import Concentration", "domain": "Energy", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-610", "mcp_tool": "adw.adw_610", "sample": "https://alpinedataworks.com/showcase/adw-610", "description": "Annual Herfindahl index of US electric-accumulator (HS 8507) imports across partner countries (UN Comtrade), scored against the trailing decade. High concentration = single-source fragility in the battery supply chain feeding EVs, grid storage, and electronics; complements ADW-398's mineral price-pressure gauge with a structural sourcing-risk view.", "agent_question": "How concentrated are US battery imports across supplier countries versus the trailing decade?", "history_start": "2010-01-01", "history_years": 16.5, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "UN Comtrade public preview API \u2014 US imports, HS 8507 by partner (comtradeapi.un.org, keyless preview tier)" ], "mcp_description": "Returns a 0-100 US battery-import concentration score (annual Herfindahl index of HS 8507 imports by partner country, UN Comtrade, z-scored against the trailing decade) with trend, z_score, latest_hhi_0_10000, latest_total_imports_usd, and top_partners. Call when the user asks about battery supply-chain risk, single-source dependence, or EV/grid-storage sourcing fragility, or when timing supplier-diversification, offtake, or inventory-hedging decisions." }, { "id": "ADW-611", "name": "US Semiconductor Import Concentration", "domain": "Tech", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-611", "mcp_tool": "adw.adw_611", "sample": "https://alpinedataworks.com/showcase/adw-611", "description": "Annual Herfindahl index of US integrated-circuit (HS 8542) imports across partner countries (UN Comtrade), scored against the trailing decade. Measures chip-sourcing fragility \u2014 the structural exposure behind every hardware BOM \u2014 for electronics OEMs, industrial buyers, and supply-chain risk teams.", "agent_question": "How concentrated are US semiconductor imports across supplier countries versus the trailing decade?", "history_start": "2010-01-01", "history_years": 16.5, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "UN Comtrade public preview API \u2014 US imports, HS 8542 by partner (comtradeapi.un.org, keyless preview tier)" ], "mcp_description": "Returns a 0-100 US chip-import concentration score (Herfindahl index of HS 8542 imports by partner country, UN Comtrade, z-scored vs the trailing decade) with trend, z_score, latest_hhi_0_10000, top_partners, and latest_total_imports_usd. Call when the user asks about semiconductor supply-chain fragility or US chip-sourcing dependence on Taiwan or Malaysia, or when timing dual-sourcing, buffer-stock, or supplier-qualification decisions." }, { "id": "ADW-612", "name": "US Industrial Electricity-Cost Squeeze", "domain": "Energy", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-612", "mcp_tool": "adw.adw_612", "sample": "https://alpinedataworks.com/showcase/adw-612", "description": "Scores the spread between industrial electric-power PPI growth (FRED WPU0542 YoY) and manufacturing output growth (IPMAN YoY). A positive, widening spread means power costs are outrunning production \u2014 margin compression for energy-intensive manufacturing (metals, chemicals, data-center-adjacent industry).", "agent_question": "Are industrial power costs rising faster than manufacturing output, squeezing energy-intensive producers?", "history_start": "1973-01-01", "history_years": 53.5, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "FRED API \u2014 WPU0542 (PPI: industrial electric power) + IPMAN (Industrial Production: Manufacturing) (api.stlouisfed.org, registered key)" ], "mcp_description": "Returns a 0-100 US industrial electricity-cost squeeze score (spread of industrial electric-power PPI growth, FRED WPU0542 YoY, over manufacturing output growth, IPMAN YoY; weekly, 53 years of history) with trend, z_score, composite_latest_value, and baseline stats. Call when the user asks about industrial power costs, manufacturer energy margins, or electricity-driven margin compression, or when timing power procurement hedges, energy surcharges, or energy-intensive capacity decisions." }, { "id": "ADW-613", "name": "EU Legislative Output Velocity", "domain": "Government", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-613", "mcp_tool": "adw.adw_613", "sample": "https://alpinedataworks.com/showcase/adw-613", "description": "Scores the velocity of adopted EU secondary legislation (regulations, directives, decisions) from the EUR-Lex/CELLAR SPARQL endpoint \u2014 90-day act count vs 8 trailing windows. Rising output flags regulatory-burden build-up for firms operating in or selling into the EU; a compliance-planning early signal.", "agent_question": "Is the EU's flow of adopted secondary legislation accelerating versus its 2-year baseline?", "history_start": "1990-01-01", "history_years": 36.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "EU Publications Office CELLAR SPARQL endpoint (publications.europa.eu/webapi/rdf/sparql, keyless)" ], "mcp_description": "Returns a 0-100 EU legislative output velocity score (90-day adopted-act count from EUR-Lex/CELLAR \u2014 regulations, directives, decisions \u2014 vs 8 trailing windows) with trend, z_score, recent_window_count, baseline_window_mean, and per_variant_w0 breakdown. Call when the user asks about EU regulatory activity, rule-making pace, or compliance-burden build-up, or when timing EU compliance staffing, budget, or market-entry decisions." }, { "id": "ADW-614", "name": "US Significant-Rulemaking Velocity", "domain": "Government", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-614", "mcp_tool": "adw.adw_614", "sample": "https://alpinedataworks.com/showcase/adw-614", "description": "Scores the velocity of economically significant (EO 12866) federal rules plus proposed rules in the Federal Register \u2014 the major-rule flow that carries real compliance cost \u2014 90-day count vs 8 trailing windows. Sharper than raw regulatory volume: it isolates the rules that trigger material spend. For compliance, government-affairs, and policy-risk teams.", "agent_question": "Is the flow of economically significant US federal rules and proposals accelerating?", "history_start": "1994-01-01", "history_years": 32.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Federal Register API v1 \u2014 documents.json, significant=1, RULE + PRORULE (federalregister.gov, keyless)" ], "mcp_description": "Returns a 0-100 US significant-rulemaking velocity score (90-day count of economically significant EO 12866 rules plus proposed rules in the Federal Register, vs 8 trailing windows) with trend, z_score, recent_window_count, baseline_window_mean, and per-variant counts. Call when the user asks about regulatory acceleration, federal rulemaking pace, or the compliance-cost pipeline, or when timing compliance staffing, comment-period capacity, or policy-risk positioning." }, { "id": "ADW-615", "name": "US Hazardous-Waste Enforcement Velocity", "domain": "Climate", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-615", "mcp_tool": "adw.adw_615", "sample": "https://alpinedataworks.com/showcase/adw-615", "description": "Scores EPA ECHO federal RCRA (hazardous-waste) enforcement-case velocity \u2014 90-day case count vs 12 trailing windows. An early chemical/industrial compliance-pressure flag for manufacturers, waste handlers, logistics operators and their insurers; the hazardous-waste sibling of the water (ADW-432) and air (ADW-604) enforcement indexes.", "agent_question": "Is federal RCRA hazardous-waste enforcement-case velocity rising versus its 3-year baseline?", "history_start": "2001-01-01", "history_years": 25.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "EPA ECHO case REST services (echodata.epa.gov/echo/case_rest_services.get_cases, keyless)" ], "mcp_description": "Returns a 0-100 US federal RCRA hazardous-waste enforcement-velocity score (EPA ECHO 90-day case count vs 12 trailing windows, 3-year baseline, daily, history to 2001) with trend, z_score, recent_window_count, baseline_window_mean/std, and window_counts. Call when the user asks about EPA hazardous-waste enforcement, RCRA compliance pressure, or chemical-industry regulatory risk, or when timing compliance audits, waste-handler due diligence, or environmental-liability underwriting." }, { "id": "ADW-616", "name": "Advanced-Therapeutics Research Pulse", "domain": "Health", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-616", "mcp_tool": "adw.adw_616", "sample": "https://alpinedataworks.com/showcase/adw-616", "description": "Scores publication velocity across four advanced-therapeutic modalities \u2014 gene therapy, CAR-T, mRNA vaccines, GLP-1 \u2014 via Europe PMC search counts (90-day windows vs 2-year baseline, summed across modalities). A pipeline-innovation intensity gauge for pharma strategy, biotech investors, and competitive-intelligence teams.", "agent_question": "Is published research on advanced therapeutic modalities (gene therapy, CAR-T, mRNA, GLP-1) accelerating?", "history_start": "1995-01-01", "history_years": 31.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Europe PMC REST search API \u2014 hitCount per modality query x FIRST_PDATE window (ebi.ac.uk/europepmc, keyless)" ], "mcp_description": "Returns a 0-100 advanced-therapeutics research-velocity score (Europe PMC publication counts across gene therapy, CAR-T, mRNA, and GLP-1 \u2014 recent 90-day window vs. two-year baseline) with trend, z_score, recent_window_count, baseline_window_mean, and per_variant_w0 modality breakdown. Call when the user asks whether biotech research is accelerating, which modality is heating up, or when timing pharma R&D, licensing, or biotech allocation decisions." }, { "id": "ADW-617", "name": "Software CVE Publication Surge Index", "domain": "Tech", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-617", "mcp_tool": "adw.adw_617", "sample": "https://alpinedataworks.com/showcase/adw-617", "description": "Scores NIST NVD CVE publication velocity \u2014 90-day published-CVE count vs 4 trailing windows. A macro software-risk load gauge: surges flag rising patch-management burden and cyber-insurance exposure. Complements the exploited-vuln index (CISA KEV, ADW-591) and package-level OSV indexes with the full national-vulnerability-database publication flow.", "agent_question": "Is the flow of newly published CVEs surging versus the trailing year?", "history_start": "1999-01-01", "history_years": 27.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "NIST NVD CVE API v2.0 (services.nvd.nist.gov/rest/json/cves/2.0, keyless)" ], "mcp_description": "Returns a 0-100 software CVE publication surge score (90-day NIST NVD published-CVE count z-scored against the trailing year's four 90-day windows) with trend, z_score, recent_window_count, and baseline window statistics. Call when the user asks about CVE volume surges, vulnerability disclosure rates, patch-management load, or software-risk exposure, or when timing patch-ops capacity, scan cadence, or cyber-insurance reviews." }, { "id": "ADW-618", "name": "Emerging-Tech Research Momentum", "domain": "Tech", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-618", "mcp_tool": "adw.adw_618", "sample": "https://alpinedataworks.com/showcase/adw-618", "description": "Scores publication velocity across three frontier-technology topics \u2014 quantum computing, solid-state batteries, neuromorphic computing \u2014 via Semantic Scholar bulk-search counts (90-day windows vs baseline, summed). Spots R&D acceleration before it reaches the patent stage; for deep-tech VCs, corporate R&D strategy, and technology scouts.", "agent_question": "Is peer-indexed research on frontier hardware technologies (quantum, solid-state batteries, neuromorphic) accelerating?", "history_start": "1990-01-01", "history_years": 36.5, "product_class": "time-series", "tier": "Gold", "refresh": "daily", "source_apis": [ "Semantic Scholar Academic Graph API \u2014 paper/search/bulk totals (api.semanticscholar.org, keyless shared pool)" ], "mcp_description": "Returns a 0-100 frontier-hardware research-momentum score (Semantic Scholar publication counts for quantum computing, solid-state batteries, and neuromorphic computing \u2014 90-day windows vs. baseline, summed) with trend, z_score, per_variant_w0, and window_counts. Call when the user asks about emerging-tech R&D acceleration, quantum/battery/neuromorphic research trends, or pre-patent signals, or when timing deep-tech investment, corporate R&D strategy, or technology-scouting decisions." }, { "id": "ADW-619", "name": "US Pharmaceutical Import Concentration", "domain": "Health", "rest": "https://api.alpinedataworks.com/v1/intelligence/adw-619", "mcp_tool": "adw.adw_619", "sample": "https://alpinedataworks.com/showcase/adw-619", "description": "Annual Herfindahl index of US packaged-medicament (HS 3004) imports across partner countries (UN Comtrade), scored against the trailing decade. Measures drug-supply sourcing fragility \u2014 the structural risk behind shortage and COGS-shock exposure \u2014 for payers, PBMs, health systems, and pharma supply-chain teams.", "agent_question": "How concentrated are US medicament imports across supplier countries versus the trailing decade?", "history_start": "2010-01-01", "history_years": 16.5, "product_class": "time-series", "tier": "Gold", "refresh": "weekly", "source_apis": [ "UN Comtrade public preview API \u2014 US imports, HS 3004 by partner (comtradeapi.un.org, keyless preview tier)" ], "mcp_description": "Returns a 0-100 US pharmaceutical import-concentration score (annual HHI of HS 3004 medicament imports by partner country, UN Comtrade, z-scored against the trailing decade) with trend, z_score, latest_hhi_0_10000, latest_total_imports_usd, and top_partners. Call when the user asks about drug-supply concentration, pharma sourcing fragility, shortage or COGS-shock exposure, or supplier-country dependence, or when timing formulary diversification, safety-stock, or supplier-contract decisions." } ] }