Access real-time Swiss weather forecasts, measurements, and pollen data via MeteoSwiss APIs. Built for developers integrating weather intelligence into AI assistants and applications.
io.github.eins78/meteoswiss-mcp
https://meteoswiss-mcp.ars.is/mcp
HTTP
No auth required
How models use it and what it is built for.
Access real-time Swiss weather forecasts, measurements, and pollen data via MeteoSwiss APIs. Built for developers integrating weather intelligence into AI assistants and applications.
Hosted endpoint — paste into any MCP client.
Where to find authoritative docs and source for MeteoSwiss.
Paste any of these into Agent Studio after connecting MeteoSwiss.
Common questions about connecting and running MeteoSwiss.
What weather data does this MCP server provide?
It provides access to Swiss MeteoSwiss data including forecasts, real-time measurements from weather stations, station metadata, and pollen information. Data is sourced directly from MeteoSwiss APIs.
Do I need authentication to use the MeteoSwiss MCP server?
The server is hosted at https://meteoswiss-mcp.ars.is/mcp and can be used via HTTP transport. Check the server documentation for any required API keys or authentication headers for MeteoSwiss data access.
How do I install and run this server?
Install via npm with `npx meteoswiss-mcp@2.0.2`. The server runs as an HTTP endpoint and connects to your AI assistant via the Model Context Protocol.
Is this limited to Switzerland only?
Yes, this server provides weather data specifically for Switzerland and uses MeteoSwiss as its data source. It includes Swiss-specific features like regional pollen forecasts.
Can I query historical weather data or only forecasts?
The server provides both real-time measurements from weather stations and forecasts. For historical data availability, consult the MeteoSwiss API documentation or the server's tool definitions.
Connect MeteoSwiss to Claude, GPT, Gemini, DeepSeek and 30+ AI models in MCP Agent Studio. Compare answers side-by-side, save reusable agent presets, share runs — all in your browser, no install required.
Open Agent Studio