Back to Browse

Swiss Weather MCP Server

by Cuolm
Developer ToolsLow Risk9.0MCP RegistryLocal
Free

Server data from the Official MCP Registry

Weather forecasts, measurements and sun and moon times for places in Switzerland, from MeteoSwiss

About

Weather forecasts, measurements and sun and moon times for places in Switzerland, from MeteoSwiss

Security Report

9.0
Low Risk9.0Low Risk

Valid MCP server (2 strong, 2 medium validity signals). 2 known CVEs in dependencies Package registry verified. Imported from the Official MCP Registry.

5 files analyzed · 3 issues found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

file_system

Check that this permission is expected for this type of plugin.

env_vars

Check that this permission is expected for this type of plugin.

Shell Command Execution

Runs commands on your machine. Be cautious — only use if you trust this plugin.

How to Install

Add this to your MCP configuration file:

{
  "mcpServers": {
    "swiss-weather-mcp": {
      "command": "uvx",
      "args": [
        "swiss-weather-mcp==0.4.0"
      ]
    }
  }
}

Some servers take additional arguments. See the repository for details.

Documentation

View on GitHub

From the project's GitHub README.

Swiss Weather MCP Server

Logo PyPI License Release Tests

An MCP server that gives AI applications weather information for places across Switzerland:

  • Forecasts for today and the next 8 days: temperature, rain, sunshine, wind, clouds and freezing level
  • Measurements from about 160 MeteoSwiss and 200 SLF mountain stations: now, on past days, and where in Switzerland it is warmest, coldest, windiest, wettest or sunniest
  • Snow and avalanches: snow depth, new snow and the SLF avalanche bulletin
  • Sun and Moon: rise and set times, civil twilight and the Moon's phase

Not an official product of MeteoSwiss, SLF or swisstopo. See Data Sources.

Answers pass through an AI model and can be wrong. Before going into the mountains, check the official avalanche bulletin and the MeteoSwiss forecast.

Quick Start

Install uv, then add this to your AI app's MCP config file:

{
  "mcpServers": {
    "swiss-weather": {
      "command": "uvx",
      "args": ["swiss-weather-mcp@latest"]
    }
  }
}

uvx downloads the server on first use, and @latest makes it check for a new release on each start. If your app cannot find uvx, replace uvx with the full path that which uvx prints. If the file already has content, add only the "swiss-weather" entry inside its "mcpServers".

In Claude Desktop, you can alternatively download the Swiss Weather desktop extension, double-click it and select Install.

Installation

Install the server once with uv, instead of starting it with uvx on each start as in Quick Start:

uv tool install swiss-weather-mcp

Over stdio

Your AI app starts the server itself. Add this to its MCP config file:

{
  "mcpServers": {
    "swiss-weather": {
      "command": "swiss-weather-mcp"
    }
  }
}

If your app cannot find swiss-weather-mcp, use the full path that which swiss-weather-mcp prints.

Over Streamable HTTP

The server runs on its own, and your AI app connects to it by URL. Start it with:

swiss-weather-mcp --transport=streamable-http --host=localhost --port=8050

Then add its URL to your AI app's MCP config file:

{
  "mcpServers": {
    "swiss-weather": {
      "url": "http://localhost:8050/mcp/"
    }
  }
}

To use another port, change 8050 in --port and in the URL. --help lists all flags. Where the server keeps its files, and --cache-all-forecast-points: see Cache and Downloads.

With Docker

The image runs the server over streamable HTTP and needs no uv:

docker run -p 127.0.0.1:8050:8050 ghcr.io/cuolm/swiss-weather-mcp:latest

Then add its URL to your AI app's MCP config file:

{
  "mcpServers": {
    "swiss-weather": {
      "url": "http://localhost:8050/mcp/"
    }
  }
}

To use another port, change the first 8050 in -p and the one in the URL.

The Docker images are built and published automatically by GitHub Actions to the project's GitHub Container Registry, tagged :latest (newest release) and by version. Each docker run starts a new container with an empty cache. Mount a volume to keep it, for example -v swiss-weather-cache:/home/app/.cache/swiss-weather-mcp.

Available Tools

Times are Swiss local time (see Times). Every tool with a location also takes an optional near, needed only when several places share the name (see Locations). Answers name the forecast point when it is not next to the place (see Forecast Points).

ToolAnswer
forecast_daily(location, start_date, days)1 to 9 days: lowest and highest temperature, rain, weather with an emoji
forecast_rain(location, start, end)Chance and amount of rain, and the weather, in 3-hour blocks
forecast_temperature(location, start, end)Temperature and its likely range, hour by hour or for one hour
forecast_sunshine(location, start, end)Hours of sunshine over a period, or in one hour
forecast_wind(location, when)Mean speed, gusts and direction
forecast_cloud_cover(location, when)Total cloud cover and its low, medium and high layers
forecast_freezing_level(location, when)Height of the 0 °C line
measurements_current(location)What a station near the place measures now (see Measurements)
measurements_history(location, start_date, days, values)1 to 366 past days: lowest, mean and highest temperature, rain, sunshine, strongest gust, snow depth and new snow
measurements_snow(location)Snow depth now, and new snow of the last 24 hours and 3 days (see Measurements)
measurements_extremes(extreme)Where it is warmest, coldest, windiest, wettest or sunniest now
avalanche_bulletin(location)SLF avalanche bulletin valid now: danger level, avalanche problems and texts (see Avalanche Bulletin)
astronomy_sun(location, date)Sunrise, sunset and civil twilight
astronomy_moon(location, date)Moonrise, moonset, phase and how much is lit
current_date_and_time()Today's weekday and the Swiss time now

Details

  • How It Works: times, places, forecast points, each tool in detail, forecast medians, cache and downloads
  • Development: running from source, the test client and the project structure

Data Sources

Support

Questions and bugs: GitHub Issues.

License

Licensed under the Apache License 2.0.

Reviews

No reviews yet

Be the first to review this server!