Weather MCP

🚀 Weather MCP Server

An MCP server that offers active US National Weather Service (NWS) alerts by state code and short - term point forecasts for specific coordinates.

This MCP server provides the following features:

• Active US National Weather Service (NWS) alerts based on two - letter state codes.
• Short - term point forecasts (for the next 5 periods) for given latitude and longitude coordinates.

The data is sourced from the public NWS API at https://api.weather.gov.

✨ Features

Tools

🚀 Quick Start

📦 Installation

Install the necessary dependencies:

pip install .

Run the Server

Run the MCP server using stdio transport:

python -m weather.weather

Your MCP client should be configured to launch the server via the package entrypoint or the above module path.

📚 Documentation

Server JSON Summary

Refer to server.json for registry metadata, including the name, version, tools, and entrypoint configuration of the server.

Publishing Steps (Overview)

1. Authenticate with the publisher (GitHub namespace):

mcp - publisher login github

2. Create and push the repository to GitHub (see detailed steps below).
3. (Optional) Publish to PyPI if you plan to distribute the server as a package.
4. Publish to the MCP registry:

mcp - publisher publish

5. Verify the publication:

curl "https://registry.modelcontextprotocol.io/v0/servers?search=io.github.vtiwari/weather - mcp"

Create & Push GitHub Repository

If the current directory is not a Git repository yet:

git init
git add .
git commit -m "Initial commit: Weather MCP server"

Create the repository using the GitHub CLI and push it:

gh repo create vtiwari/weather - mcp --public --source . --remote origin --push

If you're not using the GitHub CLI, create the repository manually via the GitHub web UI, then:

git remote add origin https://github.com/vtiwari/weather - mcp.git
git branch -M main
git push -u origin main

Tag the version for consistent releases:

git tag v0.1.0
git push origin v0.1.0

PyPI Packaging (Optional)

To distribute the server via PyPI, make sure pyproject.toml includes the build backend and metadata (such as authors and license). Then:

pip install build twine
python -m build
twine upload dist/*

📄 License

This project is licensed under the MIT license (adjust if different).

⚠️ Important Note

This server uses public NOAA/NWS endpoints. Please respect the API usage guidelines and rate limits.