Summary
Pulls GFS ensemble weather data for 12 cities with a focus on finding edges in prediction markets. You get access to probabilistic forecasts that can reveal when consensus weather predictions might be off, which matters if you're trading on weather-dependent outcomes or trying to spot mispriced contracts on platforms like Polymarket or Kalshi. The server surfaces ensemble spread and model agreement metrics rather than just point forecasts. Reach for this when you need programmatic access to weather uncertainty data for quantitative trading strategies, not for general weather lookups where a standard API would do fine.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Tools
Public tool metadata for what this MCP can expose to an agent.
5 tools
get_weather_signalsGet GFS ensemble weather signals for one or more cities on a given date. Returns model probability of daily high exceeding various thresholds, derived from the 31-member GFS ensemble forecast. Requires cities (list of city names) and forecast_date (YYYY-MM-DD). Optional: thres...5 params
Get GFS ensemble weather signals for one or more cities on a given date. Returns model probability of daily high exceeding various thresholds, derived from the 31-member GFS ensemble forecast. Requires cities (list of city names) and forecast_date (YYYY-MM-DD). Optional: thres...
Parameters* required
citiesarrayList of city names e.g. ["NYC", "Chicago"]. Call get_city_info to see supported cities.
directionstringDirection to evaluate: 'above' or 'below' the threshold.one of
above · belowdefault: aboveforecast_datestringForecast date in YYYY-MM-DD format.
market_typestringWeather variable: 'high' (daily max), 'low' (daily min), 'rain' (precipitation).one of
high · low · raindefault: highthreshold_fnumberTemperature threshold in Fahrenheit (default 70).default: 70
get_ensemble_forecastFetch the raw GFS 31-member ensemble forecast for a city on a given date. Returns per-member daily high temperatures, low temperatures, and precipitation. Useful for custom probability calculations or verifying signal generation.2 params
Fetch the raw GFS 31-member ensemble forecast for a city on a given date. Returns per-member daily high temperatures, low temperatures, and precipitation. Useful for custom probability calculations or verifying signal generation.
Parameters* required
citystringCity name e.g. 'NYC', 'Chicago', 'London'.
forecast_datestringForecast date in YYYY-MM-DD format.
detect_edgesScan weather markets for edges — cases where the GFS model probability differs significantly from the market-implied probability. Requires a list of (signal, market) pairs. Returns all EdgeResults, or only tradeable ones if tradeable_only=True.9 params
Scan weather markets for edges — cases where the GFS model probability differs significantly from the market-implied probability. Requires a list of (signal, market) pairs. Returns all EdgeResults, or only tradeable ones if tradeable_only=True.
Parameters* required
citystringCity name for the signal.
directionstringSignal direction.one of
above · belowdefault: aboveforecast_datestringForecast date YYYY-MM-DD.
market_pricenumberMarket YES price as probability (0-1).
market_typestringMarket type.one of
high · low · raindefault: highmin_edge_pctnumberMinimum edge in percent to flag tradeable (default 5).default: 5
platformstringPlatform the market is on.one of
kalshi · polymarketdefault: kalshithreshold_fnumberTemperature threshold in Fahrenheit.
tickerstringMarket ticker (optional, for identification).default:
list_active_marketsList active weather markets on Polymarket or Kalshi. Optionally filter by city. Returns market tickers, prices, volumes, and metadata. Kalshi requires api_key to be provided.3 params
List active weather markets on Polymarket or Kalshi. Optionally filter by city. Returns market tickers, prices, volumes, and metadata. Kalshi requires api_key to be provided.
Parameters* required
citiesarrayOptional city filter.
kalshi_api_keystringKalshi API key (required for Kalshi markets).
platformstringWhich platform to query.one of
polymarket · kalshi · alldefault: polymarketget_city_infoGet coordinates and metadata for a supported city, or list all supported cities if no city is provided.1 params
Get coordinates and metadata for a supported city, or list all supported cities if no city is provided.
Parameters* required
citystringCity name or alias. Leave empty to list all cities.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →