Weather

A Model Context Protocol (MCP) server for retrieving weather alerts and forecasts using the National Weather Service (NWS) API.

Features

• Get Weather Alerts: Retrieve active weather alerts for any US state
• Get Weather Forecast: Obtain weather forecasts for specific geographic coordinates
• MCP Integration: Built with FastMCP for seamless integration with AI assistants
• Async Support: Non-blocking asynchronous API calls for efficient performance

Requirements

• Python >= 3.13
• httpx >= 0.28.1
• mcp[cli] >= 1.25.0

Installation

1. Clone the repository:

git clone <repository-url>
cd weather

2. Install dependencies:

pip install -e .

Or using uv:

uv sync

Usage

Running the Server

python main.py

Available Tools

get_alerts(state: str) -> str

Get weather alerts for a US state.

Parameters:

• state (str): Two-letter US state code (e.g., CA, NY)

Example:

result = await get_alerts("CA")

get_forecast(latitude: float, longitude: float) -> str

Get weather forecast for a specific location.

Parameters:

• latitude (float): Latitude of the location
• longitude (float): Longitude of the location

Example:

result = await get_forecast(40.7128, -74.0060)

Architecture

The project uses the FastMCP framework to create a Model Context Protocol server that exposes weather-related tools. All API requests go through the National Weather Service API with proper error handling and timeout management.

Components

• weather.py: Main server implementation with tool definitions
• main.py: Entry point for running the server
• pyproject.toml: Project configuration and dependencies

API Information

This server uses the National Weather Service API, which is:

• Free to use
• Public data
• No authentication required
• Covers the United States and its territories

Error Handling

The server includes comprehensive error handling for:

• Network timeouts (30-second limit)
• Invalid API responses
• Missing or unavailable data

Development

To modify or extend the tools:

1. Edit the tool definitions in weather.py
2. Add new async functions with the @mcp.tool() decorator
3. Include proper docstrings with argument descriptions
4. Test with the running server

License

Add license information here.

Contributing

Contributions are welcome! Please feel free to submit a pull request.