MCP server giving AI assistants 17 weather tools with zero API keys: global forecasts, current conditions, alerts, air quality, marine conditions
MCP server giving AI assistants 17 weather tools with zero API keys: global forecasts, current conditions, alerts, air quality, marine conditions, lightning
Weather MCP is a Model Context Protocol server that connects AI assistants (Claude, Cursor, Cline, Zed, and any other MCP client) to live weather data: forecasts, current conditions, alerts, air quality, marine conditions, lightning, radar, rivers, wildfires, and 85+ years of historical weather. It's built entirely on free public data sources — NOAA, Open-Meteo, USGS, NIFC, RainViewer, and Blitzortung.org — so there is nothing to sign up for and no key to paste in.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| get_forecast | Daily/hourly forecasts up to 16 days by coordinates, saved location, or city name; sunrise/sunset, UV, precipitation probability, optional climate-normals comparison |
| get_current_conditions | Current weather: temperature, wind, humidity, pressure; NOAA station observations in the US (plus heat index/wind chill, snow depth, optional fire-weather indices), Open-Meteo model data elsewhere |
| get_alerts | Active watches, warnings, and advisories sorted by severity |
| get_historical_weather | Hourly/daily observations from 1940 to present |
| get_weather_summary | One-call overview combining current conditions, forecast, and alerts (optionally air quality and lightning) |
| search_location | Geocode place names to coordinates ("Paris" → 48.85, 2.35) |
| get_air_quality | AQI (US/European scales), pollutants, UV index, health guidance; optional day-grouped forecast up to 7 days with per-day peak AQI and UV |
| get_marine_conditions | Wave height, swell, ocean currents, Douglas Sea Scale — includes Great Lakes and major US bays; forecast up to 16 days |
| get_weather_imagery | Precipitation radar (static or 2-hour animated loops) + GOES satellite imagery |
| get_lightning_activity | Real-time strike detection with 4-level proximity safety assessment |
| get_river_conditions | River gauge levels, flood stages, streamflow, rise/fall trends, NWPS forecast series |
| get_wildfire_info | Active fires, containment, size, proximity-based safety guidance |
| check_service_status | Health checks for all upstream APIs plus cache statistics |
| save_location | Save places as aliases ("home", "cabin") with optional activity tags |
claude mcp add server-weather --env ENABLED_TOOLS=your-value --env CACHE_MAX_SIZE=your-value --env LOG_LEVEL=your-value --env NCEI_API_TOKEN=your-value -- npx -y @dangahagan/weather-mcp| Variable | Description | Required |
|---|---|---|
| ENABLED_TOOLS | Configuration value read at startup. | Optional |
| CACHE_MAX_SIZE | Configuration value read at startup. | Optional |
| LOG_LEVEL | Configuration value read at startup. | Optional |
| NCEI_API_TOKEN | Credential the server authenticates with. | Yes |
Provides a command-line and API-based coding assistant utilizing OpenAI APIs, function calling, and streaming.
Provides a production-ready template for building Model Context Protocol (MCP) servers with TypeScript.
Jaeger MCP — search traces, inspect spans, map service dependencies (read-only).
Swiss weather data for AI agents — MeteoSwiss open data exposed two ways: MCP server and agent skill
The purpose of this repo is to demonstrate how easy it is to leverage workflows as tools for MCP servers by taking modelcontext.io's weather example
AI-powered web research MCP server for agents. Supports web search, browse page, extract article. By MEOK AI Labs.