Unofficial MCP server for the Windy Point Forecast API
Project description
windy-mcp-server
Unofficial MCP server for the Windy Point Forecast API. This project is not affiliated with or endorsed by Windy.com.
An MCP (Model Context Protocol) server that exposes weather, ocean wave, and air quality forecasts to AI assistants via the Windy Point Forecast API.
Tools
get_weather_forecast
Fetch atmospheric weather data for any coordinates.
- Parameters: temperature, dewpoint, relative humidity, pressure, geopotential height, precipitation (total/snow/convective), wind, wind gusts, cloud cover (low/mid/high), cloud base, visibility, CAPE, precipitation type, weather warnings
- Models: GFS, ICON, ICON-EU, ICON-D2, AROME (France, Antilles, Réunion), NAM (CONUS/Hawaii/Alaska), HRRR (CONUS/Alaska), HRDPS
- Pressure levels: surface through 150 hPa (14 levels)
- Temperature units: Celsius or Kelvin
get_wave_forecast
Fetch ocean wave data for any coastal or open-water coordinates.
- Parameters: significant wave height, wind waves, wave power, swell 1 & 2
- Models: GFS Wave, ICON Wave, ICON-EU Wave, RDWPS (Canada)
get_air_quality_forecast
Fetch air quality and pollen forecasts for any location.
- Parameters: AQI, SO₂, dust, CO, O₃, NO₂, PM10, PM2.5, pollen (alder, birch, grass, mugwort, olive, ragweed)
- Models: CAMS (global), CAMS-EU (higher-resolution European data)
Setup
Prerequisites: Python 3.12+, uv, a Windy API key
-
Clone the repository and install dependencies:
git clone https://github.com/yourusername/windy-mcp-server.git cd windy-mcp-server uv sync
-
Create a
.envfile with your API key:cp .env.example .env # Edit .env and set WINDY_API_KEY=your_api_key_here
-
Add to your MCP client config (e.g.
claude_desktop_config.json):{ "mcpServers": { "windy": { "command": "uv", "args": ["run", "python", "server/server.py"], "cwd": "/path/to/windy-mcp-server", "env": { "WINDY_API_KEY": "your_api_key_here" } } } }
License
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file windy_mcp_server-0.2.2.tar.gz.
File metadata
- Download URL: windy_mcp_server-0.2.2.tar.gz
- Upload date:
- Size: 92.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: uv/0.11.17 {"installer":{"name":"uv","version":"0.11.17","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
36a89221f4a8ae4d850269345f5c40b85243f1a2b3ad806980388ac1908afebb
|
|
| MD5 |
6960f444544a57ac4c1bdb778ad8cb14
|
|
| BLAKE2b-256 |
a032ad1aefaa2bb5568e4339a6f49929801810d0f7f76823d46cf0bd43feb5e9
|
File details
Details for the file windy_mcp_server-0.2.2-py3-none-any.whl.
File metadata
- Download URL: windy_mcp_server-0.2.2-py3-none-any.whl
- Upload date:
- Size: 10.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: uv/0.11.17 {"installer":{"name":"uv","version":"0.11.17","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
369cb0136a6512446a6178031d13478e7f702600c9a5aa8c41d93a45561e7bb8
|
|
| MD5 |
daea10f006cf5d060682676294668113
|
|
| BLAKE2b-256 |
494898e0229055822aa0951137cc1728e19187594b975bdfdeb80548a42830e6
|