Skip to main content
Glama
gaurigshankar

Weather MCP Server

Weather MCP Server

A Model Context Protocol (MCP) server that provides weather information and alerts using the National Weather Service (NWS) API. This server enables AI assistants to access real-time weather data for US locations.

Features

  • Weather Forecasts: Get detailed weather forecasts for any US location using latitude/longitude coordinates

  • Weather Alerts: Retrieve active weather alerts for any US state

  • NWS Integration: Uses the official National Weather Service API for reliable, up-to-date weather data

  • MCP Compatible: Works with any MCP-compatible AI assistant or application

Related MCP server: Weather MCP Server

Available Tools

get_forecast

Get weather forecast for a specific location.

Parameters:

  • latitude (number): Latitude of the location (-90 to 90)

  • longitude (number): Longitude of the location (-180 to 180)

Returns: Detailed weather forecast including temperature, wind conditions, and weather descriptions for multiple periods.

get_alerts

Get active weather alerts for a US state.

Parameters:

  • state (string): Two-letter state code (e.g., "CA", "NY", "TX")

Returns: List of active weather alerts including severity, affected areas, and descriptions.

Prerequisites

  • Node.js (version 14 or higher)

  • npm or yarn

  • An MCP-compatible client (like VS Code with GitHub Copilot)

Installation

  1. Clone the repository:

    git clone <repository-url>
    cd weather-mcp-server
  2. Install dependencies:

    npm install

Building the Server

Build the TypeScript code to JavaScript:

npm run build

This will:

  • Compile TypeScript files from src/ to build/

  • Make the main executable file executable (chmod 755 build/index.js)

Usage with VS Code GitHub Copilot

To use this weather MCP server with VS Code GitHub Copilot, you need to update your MCP configuration:

Step 1: Update MCP Configuration

Edit your mcp.json file (usually located in your VS Code settings directory) and add the weather server:

{
  "mcpServers": {
    "weather": {
      "command": "node",
      "args": ["/Users/gshanka/Documents/ReactDev/weather-mcp-server/build/index.js"]
    }
  }
}

Note: Replace the path in args with the absolute path to your built index.js file.

Step 2: Restart VS Code

After updating the configuration, restart VS Code to load the new MCP server.

Step 3: Use Weather Tools

Once configured, you can ask GitHub Copilot for weather information:

  • "What's the weather forecast for San Francisco?" (Copilot will ask for coordinates or you can provide: latitude 37.7749, longitude -122.4194)

  • "Are there any weather alerts in California?" (Use state code "CA")

  • "Get me the forecast for latitude 40.7128, longitude -74.0060" (New York City)

Example Usage

Getting Weather Forecast

User: "What's the weather forecast for Seattle?"
Assistant: I'll get the weather forecast for Seattle (latitude: 47.6062, longitude: -122.3321).

[The server will return a detailed forecast with temperature, wind, and conditions for multiple periods]

Getting Weather Alerts

User: "Are there any weather alerts in Florida?"
Assistant: I'll check for weather alerts in Florida.

[The server will return any active weather alerts for the state of FL]

Development

Project Structure

weather-mcp-server/
├── src/
│   ├── index.ts          # Main MCP server implementation
│   └── weather-utils.ts  # Weather API utilities and types
├── build/                # Compiled JavaScript output
├── package.json
├── tsconfig.json
└── README.md

Running in Development

# Build and run
npm run build
node build/index.js

Debugging

The server logs errors to stderr, which you can monitor when running the server directly or check in your MCP client's logs.

API Limitations

  • US Only: The National Weather Service API only provides data for US locations

  • Rate Limiting: The NWS API has rate limits; avoid making excessive requests

  • Data Availability: Some remote or maritime locations may not have forecast data available

Contributing

  1. Fork the repository

  2. Create a feature branch

  3. Make your changes

  4. Build and test the server

  5. Submit a pull request

License

ISC License - see package.json for details.

Troubleshooting

Server Not Loading

  • Ensure the path in mcp.json points to the correct build/index.js file

  • Verify the server was built successfully with npm run build

  • Check VS Code's MCP logs for error messages

No Weather Data

  • Verify you're using valid US coordinates

  • Check that the NWS API is accessible from your network

  • Ensure you're using valid two-letter state codes for alerts

Permission Errors

  • Make sure the build/index.js file is executable

  • The build script should handle this automatically with chmod 755

Install Server
A
security – no known vulnerabilities
F
license - not found
A
quality - confirmed to work

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/gaurigshankar/weather-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server