Weather Forecast MCP Server

A Model Context Protocol (MCP) server for retrieving weather information using the wttr.in service, with Open-Meteo as fallback (free, no API key required).

Overview

This MCP server provides tools for accessing current weather conditions and forecasts for locations worldwide. It can be easily integrated with MCP clients, including Claude and other LLM applications supporting the MCP protocol.

Related MCP server: Weather MCP Tool

Features

• Get current weather for any location

• Get multi-day weather forecasts (up to 3 days)

• Support for both Chinsee/English and other language location names

• Easy integration with MCP client applications

Installation

From pip

You can install the MCP Weather Server using uv:

uv pip install weather-forecast-server

Or using pip:

pip install weather-forecast-server

From source

git clone https://github.com/shibing624/mcp-server-weather.git
cd weather-forecast-server
pip install -e .

Usage

Python Demo

from weather_forecast_server import get_weather
print(get_weather('baoding')) # can be "baoding" or "保定"

Running as a standalone MCP server

Run the server with the stdio transport:

uvx weather-forecast-server

or

uv run weather-forecast-server

or

python -m weather_forecast_server

Then, you can use the server with any MCP client that supports stdio transport.

Integrating with Cursor

To add the weather MCP server to Cursor, add stdio MCP with command:

uv run weather-forecast-server

Tools available

• get_weather - Get current weather conditions for a location (up to 3 days)

Contact

• Issues and suggestions:

• Email: xuming624@qq.com

• WeChat: Add me (WeChat ID: xuming624) with the message: "Name-Company-NLP" to join our NLP discussion group.

License

This project is licensed under The Apache License 2.0 and can be used freely for commercial purposes. Please include a link to the weather-forecast-server project and the license in your product description.

Contribute

We welcome contributions to improve this project! Before submitting a pull request, please:

1. Add appropriate unit tests in the tests directory

2. Run python -m pytest to ensure all tests pass

3. Submit your PR with clear descriptions of the changes

Acknowledgements

• Weather data provided by wttr.in, fallback by Open-Meteo (free, no API key required)

• Built with MCP Python SDK 2.x (requires mcp>=2.2.0, not compatible with mcp 1.x)