Weather MCP Server
An MCP server that provides:
Active US National Weather Service (NWS) alerts by two-letter state code
Short-term point forecasts (next 5 periods) for latitude/longitude coordinates
Data is sourced from the public NWS API at https://api.weather.gov.
Tools
Tool | Description | Inputs |
| Fetch active NWS alerts for a US state |
(string, two-letter code) |
| Fetch short-term forecast (next 5 periods) for coordinates |
(number),
(number) |
Usage (Local)
Install dependencies:
Run the MCP server (stdio transport):
Your MCP client should be configured to launch the server via the package entrypoint or the above module path.
Server JSON Summary
See server.json for registry metadata including name, version, tools, and entrypoint configuration.
Publishing Steps (Overview)
Authenticate with publisher (GitHub namespace):
mcp-publisher login githubCreate and push repo to GitHub (see steps below).
(Optional) Publish to PyPI if distributing as a package.
Publish to MCP registry:
mcp-publisher publishVerify:
curl "https://registry.modelcontextprotocol.io/v0/servers?search=io.github.vtiwari/weather-mcp"
Create & Push GitHub Repository
If this directory is not yet a git repo:
Create repo (GitHub CLI) and push:
If not using GitHub CLI, create the repo manually via the GitHub web UI, then:
Tag version for release consistency:
PyPI Packaging (Optional)
To distribute via PyPI, ensure pyproject.toml includes build backend and metadata (authors, license). Then:
License
MIT (adjust if different).
Disclaimer
This server uses public NOAA/NWS endpoints. Respect API usage guidelines and rate limits.
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
Provides access to US National Weather Service data including active alerts by state and short-term forecasts for specific coordinates.