Weather MCP Server
Provides US weather alerts and forecasts via the National Weather Service API with no API key required.
README
Weather MCP Server
https://modelcontextprotocol.io/docs/develop/build-server#typescript
Professional TypeScript MCP server that exposes weather tools backed by the US National Weather Service API.
Features
- MCP server over stdio
- TypeScript strict mode
- No required API key
- Safe
.envhandling - CLI client for manual testing
- Automated MCP smoke tests using a local mock NWS server
- Tools:
get-alertsget-forecast
Important:
api.weather.govonly supports locations in the United States and US territories. Forecasts for Italy or other non-US locations will not work with this data source.
Requirements
- Node.js 20 or newer
- npm
Check your versions:
node -v
npm -v
Installation
From the project folder:
npm install
Build
npm run build
This creates compiled JavaScript in build/.
Run the MCP server
npm start
The server communicates over stdio, so when started directly it waits for an MCP client.
Manual CLI testing
First build the project:
npm run build
Then run the included client:
npm run client
Example commands inside the client prompt:
get-alerts { "state": "CA" }
get-forecast { "latitude": 34.05, "longitude": -118.25 }
quit
Automated tests
npm test
The tests do not depend on the live National Weather Service API. They start a local mock weather server and verify that the MCP server lists and executes its tools correctly.
Configuration
No configuration is required for normal use.
Optional environment variables:
NWS_API_BASE=https://api.weather.gov
NWS_USER_AGENT=weather-mcp-server/2.0 your-email@example.com
Do not commit .env files. Use .env.example as a template only.
Claude Desktop configuration example
After running npm run build, add something like this to Claude Desktop's MCP configuration, adjusting the path to your local project folder:
{
"mcpServers": {
"weather": {
"command": "node",
"args": [
"C:/Users/torre/Desktop/myWeather/build/server.js"
]
}
}
}
Project structure
src/
cli.ts Manual MCP client
nws.ts NWS API helpers and formatting
server.ts MCP server entry point
tests/
mcp-smoke.test.js
Available npm scripts
npm run build Compile TypeScript
npm start Start the MCP server
npm run dev Start the server with tsx
npm run client Start the manual CLI client
npm test Build and run automated tests
npm run clean Remove build output
Security note
The original project contained a .env file. This version removes it from the distributable project and ignores all .env files by default. If the previous .env contained a real API key, revoke or rotate that key.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.