groundhog.markets
Server Details
groundhog.markets: free weather forecasts in one call, plus Kalshi and Polymarket market rules.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 9 tools
The core tools (forecast, history, markets, coverage, receipts, sources) target clearly distinct resources, but two pairs are near-duplicates: fetch is explicitly a 'connector form of forecast' and search a 'connector form of places'. Descriptions do steer agents ('otherwise prefer forecast/places'), which keeps it usable, but an agent seeing all nine tools must actively resolve the overlap.
All names are single lowercase words with no style mixing (no camelCase/snake_case clashes), so the set reads predictably. The only deviation is that fetch and search are verbs among otherwise noun-named tools, a minor inconsistency rather than a real problem.
Nine tools is a well-scoped set for a weather-market data service, with each domain concept (places, forecast, markets, history, sources, receipts) earning a slot. The two connector-form duplicates (fetch, search) are the only slight padding.
The surface covers the full read-only lifecycle: place lookup, forecasts, market-to-station mapping, as-issued history for backtests, source provenance, and settlement accuracy via receipts. It is essentially complete for a data/verification domain; only minor gaps remain, such as no dedicated schema or alert-only endpoint (both reachable via forecast or the published schema URL).
Available Tools
9 toolscoverageMarket coverageARead-onlyIdempotentInspect
Which Kalshi and Polymarket weather series groundhog tracks (key, family, kind, city, station, product), which it sees at the venue but does not support and why, and when each venue was last read. The REST body of /api/v1/markets/coverage. No prices. format=json also returns structuredContent; the JSON Schema is at https://groundhog.markets/api/v1/schema.json
Inputs: venue, fields, format, compact.
fetchFetch a placeARead-onlyIdempotentInspect
Connector form of forecast: the 7-day forecast of a place id from search as {id, title, text, url, metadata}. Otherwise prefer forecast, or markets for a market city. Keep the credits and link the url when you repeat numbers.
Inputs: id (required).
forecastForecast blendARead-onlyIdempotentInspect
Daily high/low for any place from every free forecast: median, spread, rain, current obs and active alerts, with credits and the page URL. line ≈321 tok, week ≈566, table ≈1,567, series ≈1,564. Keep the credits and link the page when you repeat numbers. size=runs: one place, each source's newest runs by day with run_utc and fetched_at; NBM adds XND, P12, Q12. variable=rain: members' share of 0.01 in or more and heavier (n = model families), NBM calibrated, amounts by source, so far today, month to date; rain line ≈647 tok, table ≈1,955. format=json also returns structuredContent; the JSON Schema is at https://groundhog.markets/api/v1/schema.json
Inputs: place (required), all, stn, win, +13 more.
historyAs-issued historyARead-onlyIdempotentInspect
As-issued history for backtests (no look-ahead): kind=daily (every source's daily hi/lo/rain per run at a place), nbm (NBM text columns: TXN, XND, P12, Q12; view=day = the books' day view), obs (settlement truth: CLI, routine-METAR max/min) or markets (what the markets tool served, each change; asof = as it stood then). from/to (<= 366 days, 1 unit per 31 days); run=ISO | lead=N (+cycle=H: the run issued N days before) | asof=ISO (what was known then). Rows carry fetched_at and origin (bf:* = backfilled). TSV by default. format=json also returns structuredContent; the JSON Schema is at https://groundhog.markets/api/v1/schema.json
Inputs: from (required), to, els, run, +13 more.
marketsWeather marketsARead-onlyIdempotentInspect
Kalshi and Polymarket weather markets (high, low, rain) in a place: settlement station and rule, the value so far under that rule, forecast daily max/min (or rain) at the station, our value and the official result once settled. No prices: read them from the venue (each row's event and event_url). Needs place, family or venue. line ≈526 tok, table ≈1,757; every city ≈36,291. With none: the list of market cities. format=json also returns structuredContent; the JSON Schema is at https://groundhog.markets/api/v1/schema.json
Inputs: date, size, place, venue, +5 more.
placesFind a placeBRead-onlyIdempotentInspect
Find a place slug by name, City, ST, airport code or lat,lon; says full blend or grid only. format=json also returns structuredContent; the JSON Schema is at https://groundhog.markets/api/v1/schema.json
Inputs: q (required), limit, fields, format, +1 more.
receiptsMarket receiptsBRead-onlyIdempotentInspect
How often our settle value matched the venue's result, with every miss. No prices. format=json also returns structuredContent; the JSON Schema is at https://groundhog.markets/api/v1/schema.json
Inputs: days, venue, family, fields, +2 more.
searchSearch placesARead-onlyIdempotentInspect
Connector form of places, for clients that only call search and fetch: places by name, City, ST, airport code or lat,lon as {results: [{id, title, url, text}]}; pass an id to fetch. Otherwise prefer places, forecast or markets.
Inputs: query (required).
sourcesSourcesCRead-onlyIdempotentInspect
Open sources groundhog uses: licence, latest run, age, status. format=json also returns structuredContent; the JSON Schema is at https://groundhog.markets/api/v1/schema.json
Inputs: fields, format, compact.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Kalshi weather markets: daily-high board beside the NWS forecast, live edges, EV, Kelly, base rates.
Risk-scores Polymarket/Kalshi settlement rules; Kalshi weather settlements. Not advice.
Live prediction markets: Polymarket + Kalshi prices, odds, order books. Pay-per-call USDC, no key.
Calibrated world model for AI agents. 40 tools: world state, markets, trading. Kalshi + Polymarket.
Related MCP Servers
- AlicenseAqualityDmaintenanceProvides calibrated weather probability signals for Kalshi prediction markets by combining dual-model forecasting (NWS + GFS ensemble) to identify mispriced temperature markets. Enables AI agents to access bias-corrected forecasts and edge signals for weather prediction market intelligence.5MIT
- AlicenseAqualityDmaintenancePrediction market probability oracle for AI agents. 26 tools across 500+ live markets from Kalshi and Polymarket. Cross-source arbitrage detection, structured TPF signals, Kelly Criterion sizing, agent performance tracking, and webhook alerts.983 npm1MIT
- AlicenseNot gradedqualityFmaintenanceUnified access to prediction market data from Kalshi and Polymarket, enabling natural language queries for real-time odds, orderbooks, and trade history.40 npm11MIT
- FlicenseNot gradedqualityDmaintenanceTrade and monitor prediction markets across Polymarket, Kalshi, Opinion, Limitless, and PredictFun from any AI agent. Unified real-time data, live orderbook streaming, and order execution — one API key, one interface, five exchanges.-
Glama MCP Gateway
Add one secure layer between your agents and this server.