Weather MCP Server
A Model Context Protocol server that provides real-time US weather alerts and forecasts via the NOAA National Weather Service API.
README
Weather MCP Server
A TypeScript Model Context Protocol (MCP) Streamable HTTP server that provides real-time US weather data using the NOAA National Weather Service (NWS) API.
Tools
| Tool | Description |
|---|---|
get_alerts |
Get active weather alerts for a US state (two-letter state code, e.g. CA) |
get_forecast |
Get weather forecast for a US location by latitude and longitude |
Note: Only US locations are supported by the NWS API.
Prerequisites
- Node.js v18 or later
- npm
Setup
-
Clone the repository and install dependencies:
git clone <repository-url> cd custom-mcp-server npm install -
Build the TypeScript source:
npm run build -
Run the server:
npm start
The MCP endpoint is available at http://127.0.0.1:3010/mcp.
Set HOST and PORT to change the listening address. For example:
HOST=0.0.0.0 PORT=8080 npm start
Development
To watch for changes and recompile automatically:
npm run dev
Connecting to an MCP Client
To use this server with an MCP client such as VS Code Copilot, start the server and add its URL to your MCP configuration:
{
"servers": {
"weather": {
"type": "http",
"url": "http://127.0.0.1:3010/mcp"
}
}
}
Container
Build and run the server locally:
docker build -t weather-mcp .
docker run --rm -p 3010:3010 weather-mcp
The health endpoint is available at http://127.0.0.1:3010/healthz.
Deploy to Azure Container Apps
The deployment creates an Azure Container Registry, a Consumption-plan Container Apps environment, Log Analytics, and an externally accessible Container App. The app uses a managed identity with the AcrPull role; registry admin credentials are disabled.
Prerequisites:
- Azure CLI
- An Azure account with permission to create resources and role assignments
Sign in and run the deployment:
az login
./scripts/deploy.sh
Customize the deployment with environment variables:
RESOURCE_GROUP=my-weather-rg \
LOCATION=westus2 \
APP_NAME=my-weather-mcp \
IMAGE_TAG=v1 \
./scripts/deploy.sh
Set AZURE_SUBSCRIPTION_ID when the signed-in account has access to multiple subscriptions. The script builds and publishes the image with ACR Tasks, so local Docker is not required.
Project Structure
src/
index.ts # Server entry point and tool definitions
build/
index.js # Compiled output (generated by npm run build)
infra/
registry.bicep # Azure Container Registry
main.bicep # Container Apps resources
scripts/
deploy.sh # Build, publish, and deploy workflow
Dockerfile
package.json
tsconfig.json
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.