A straightforward weather server that wraps the National Weather Service API to pull forecasts and alerts for U.S. locations. You get two tools: one for grabbing active weather alerts by state, another for detailed forecasts by coordinates or location. Built as a homework assignment for MIT's AI Studio course, so it's minimal but functional. The developer added a quirky feature where the LLM can respond in pirate speak if you ask for it, which is more about demonstrating tone control than serious utility. Runs through Smithery's infrastructure, so you'll need an API key from them to deploy it. Good for learning how MCP servers work or prototyping simple weather integrations without setting up your own NWS API calls.
An MCP server built with Smithery CLI
This weather app has two functions: get alert and get forecast. Get alert gets any weather alert within the U.S. state, and get forecast gets the weather forecast for that location.
To make things more interesting, if you ask the it to speak in a pirate like tone, it can answer your requests with such a tone.
Run the server:
uv run dev
Test interactively:
uv run playground
Try saying "Say hello to John" to test the example tool.
Your server code is in src/hello_server/server.py. Add or update your server capabilities there.
Ready to deploy? Push your code to GitHub and deploy to Smithery:
Create a new repository at github.com/new
Initialize git and push to GitHub:
git add .
git commit -m "Hello world 👋"
git remote add origin https://github.com/YOUR_USERNAME/YOUR_REPO.git
git push -u origin main
Deploy your server to Smithery at smithery.ai/new