weather

The Weather MCP Server provides global weather data for AI systems, combining NOAA's US-focused observations with Open-Meteo for international forecasts and historical data. It exposes a rich set of tools including current conditions for US locations, global weather forecasts (up to 16 days with hourly or daily granularity), location search to convert place names into coordinates, and saved locations for quick queries. Additionally, users can access climate normals for historical context, historical observations, air quality information, weather alerts, and specialized data like snow/ice, sunrise/sunset times, and timezone-aware timestamps. These capabilities enable natural language queries such as “What’s the weather like in Paris this weekend?” or “Show me the 7-day forecast for New York with normals included.” The server also supports per-location context via saved locations and activity tags to tailor forecasts to activities like hiking or skiing. Use the API endpoints or integrated tools to retrieve weather data, set up saved locations, and compare current conditions to long-term normals.

Prerequisites:

• Node.js (v14+ recommended) and npm installed on your system
• Access to install the Weather MCP Server package

Installation steps:

1. Install the MCP server package globally (recommended): npm install -g @dangahagan/weather-mcp

2. Verify installation: weather-mcp --version

3. Run the MCP server locally: weather-mcp start

4. If you prefer to run directly with Node (alternative): npm install --no-audit --no-fund -g @dangahagan/weather-mcp node server.js

5. Optional: configure environment variables (see notes) and persist locations at ~/.weather-mcp/locations.json

6. Access the server API or integrated tools via the provided endpoints or CLI as documented in the registry.

Notes and tips:

• No API keys are required for NOAA or Open-Meteo data in this server.
• If you enable normals, the server may fetch historical climate normals (Open-Meteo defaults or NOAA NCEI if token is provided).
• Saved locations enable natural-language queries like “weather at home” and persist across sessions via ~/.weather-mcp/locations.json.
• Timezone-aware display ensures timestamps reflect the location’s local time with proper DST handling.
• If you encounter rate limiting, consider staggering requests or caching results locally.
• For US-specific normals or premium APIs (NOAA NCEI normals), an optional token can be configured via environment variables as described in the documentation.