AI-General/MCP-Server

Weather MCP Server

A Python-based Model Context Protocol (MCP) server that provides weather data and alerts for the United States using the National Weather Service (NWS) API.

Features

• Get Active Weather Alerts: Retrieve current weather alerts for any US state by its two-letter abbreviation.
• Get Weather Forecast: Fetch detailed weather forecasts for any location in the US using latitude and longitude.
• FastMCP Integration: Built on top of the FastMCP framework for easy integration with MCP clients.

Requirements

• Python 3.8+
• httpx
• mcp-server (with FastMCP)

Install dependencies with:

pip install -r requirements.txt

Or, if you use pyproject.toml:

pip install .

Usage

Running the Server

You can start the MCP server using:

python weather.py

The server will run using the stdio transport by default.

Tools Provided

1. Get Weather Alerts

Fetches active weather alerts for a given US state.

• Function: get_alerts(state: str)
• Parameters:
  • state: Two-letter state abbreviation (e.g., CA, NY)
• Returns: Formatted string of active alerts or a message if none are active.

2. Get Weather Forecast

Fetches a weather forecast for a given latitude and longitude.

• Function: get_forecast(latitude: float, longitude: float)
• Parameters:
  • latitude: Latitude of the location
  • longitude: Longitude of the location
• Returns: Formatted string with the next 5 forecast periods.

Example

from weather import get_alerts, get_forecast

# Get alerts for California
alerts = await get_alerts('CA')
print(alerts)

# Get forecast for San Francisco, CA
forecast = await get_forecast(37.7749, -122.4194)
print(forecast)

API Reference

This server uses the National Weather Service API for all weather data.

License

This project is licensed under the MIT License.