MCP Weather Server logo

MCP Weather Server

by michael7736

The MCP Weather Server provides USA weather information using the National Weather Service API. It allows MCP-compatible AI assistants to access real-time weather data.

View on GitHub

Last updated: N/A

MCP Weather Server

An MCP (Model Context Protocol) server providing USA weather information using the National Weather Service API. This server allows Claude and other MCP-compatible AI assistants to access real-time weather data.

Features

  • Weather Alerts: Get current weather alerts for any US state
  • Weather Forecasts: Get detailed weather forecasts for any location in the US using latitude and longitude

Installation

For Users

To use this MCP server with Claude or other MCP-compatible AI assistants:

# Install from PyPI
pip install mcp-weather

# Or install with uv
uv pip install mcp-weather

For Developers

To set up the development environment:

# Clone the repository
git clone https://github.com/michael7736/mcp-weather.git
cd mcp-weather

# Create a virtual environment
python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

# Install dependencies
pip install -e ".[dev]"

Configuration

Cline (VS Code Extension)

Add the following to your Cline MCP settings file (cline_mcp_settings.json):

{
  "mcpServers": {
    "weather": {
      "command": "mcp-weather",
      "disabled": false,
      "autoApprove": []
    }
  }
}

Claude Desktop App

Add the following to your Claude Desktop config file (claude_desktop_config.json):

{
  "mcpServers": {
    "weather": {
      "command": "mcp-weather",
      "disabled": false,
      "autoApprove": []
    }
  }
}

Usage

Once configured, you can ask Claude or other MCP-compatible AI assistants questions about the weather:

  • "What are the current weather alerts in CA?"
  • "What's the weather forecast for San Francisco?" (The assistant will use coordinates for San Francisco)

Publishing

To publish this package to PyPI:

  1. Make sure you have the latest build tools:

    pip install --upgrade build twine
    
  2. Build the package:

    python -m build
    
  3. Upload to PyPI:

    python -m twine upload dist/*
    

License

This project is licensed under the MIT License - see the LICENSE file for details.