MCP Weather Server
Provides real-time weather forecasts and active weather alerts for US locations using the National Weather Service API. It enables users to retrieve detailed local forecasts via coordinates and monitor state-specific weather warnings.
README
MCP WEATHER SERVER WRITTEN IN TYPESCRIPT
Protocol Map
This weather MCP server implements the Model Context Protocol (MCP) to provide weather data through a standardized interface. Below is the complete protocol mapping showing how the server communicates with MCP clients.
Server Information
- Name:
weather - Version:
1.0.0 - Transport: STDIO (Standard Input/Output)
- Protocol: Model Context Protocol
Capabilities
{
"capabilities": {
"tools": {
"listChanged": true
}
}
}
Tools
The server exposes two tools for weather data retrieval:
1. get_alerts
Retrieves active weather alerts for a US state.
Input Schema:
{
"type": "object",
"properties": {
"state": {
"type": "string",
"description": "Two-letter US state code (e.g. CA, NY)",
"minLength": 2,
"maxLength": 2
}
},
"required": ["state"]
}
Example Request:
{
"method": "tools/call",
"params": {
"name": "get_alerts",
"arguments": {
"state": "CA"
}
}
}
Example Response:
{
"content": [
{
"type": "text",
"text": "Event: Heat Advisory\nArea: Los Angeles County\nSeverity: Moderate\nDescription: Dangerously hot conditions...\nInstructions: Drink plenty of fluids..."
}
]
}
Error Response:
{
"content": [
{
"type": "text",
"text": "Unable to fetch alerts or no alerts found."
}
]
}
2. get_forecast
Retrieves weather forecast for a specific location using latitude and longitude coordinates.
Input Schema:
{
"type": "object",
"properties": {
"latitude": {
"type": "number",
"description": "Latitude of the location",
"minimum": -90,
"maximum": 90
},
"longitude": {
"type": "number",
"description": "Longitude of the location",
"minimum": -180,
"maximum": 180
}
},
"required": ["latitude", "longitude"]
}
Example Request:
{
"method": "tools/call",
"params": {
"name": "get_forecast",
"arguments": {
"latitude": 38.5816,
"longitude": -121.4944
}
}
}
Example Response:
{
"content": [
{
"type": "text",
"text": "Tonight:\nTemperature: 65°F\nWind: 5 mph SW\nForecast: Partly cloudy with a slight chance of showers.\n---\nTomorrow:\nTemperature: 78°F\nWind: 10 mph W\nForecast: Sunny skies throughout the day."
}
]
}
Error Responses:
{
"content": [
{
"type": "text",
"text": "Failed to retrieve grid point data for coordinates: 38.5816, -121.4944. This location may not be supported by the NWS API (only US locations are supported)."
}
]
}
Communication Flow
sequenceDiagram
participant Client as MCP Client (Claude)
participant Server as Weather Server
participant NWS as National Weather Service API
Client->>Server: Initialize Connection (STDIO)
Server->>Client: Server Info + Capabilities
Client->>Server: List Tools
Server->>Client: [get_alerts, get_forecast]
Client->>Server: Call Tool: get_forecast(lat, lon)
Server->>NWS: GET /points/{lat},{lon}
NWS->>Server: Grid Point Data
Server->>NWS: GET {forecast_url}
NWS->>Server: Forecast Data
Server->>Client: Formatted Forecast Text
Client->>Server: Call Tool: get_alerts(state)
Server->>NWS: GET /alerts/active/area/{state}
NWS->>Server: Active Alerts
Server->>Client: Formatted Alerts Text
Protocol Messages
Initialization
Client → Server:
{
"jsonrpc": "2.0",
"id": 1,
"method": "initialize",
"params": {
"protocolVersion": "2024-11-05",
"capabilities": {},
"clientInfo": {
"name": "Claude Desktop",
"version": "1.0.0"
}
}
}
Server → Client:
{
"jsonrpc": "2.0",
"id": 1,
"result": {
"protocolVersion": "2024-11-05",
"capabilities": {
"tools": {
"listChanged": true
}
},
"serverInfo": {
"name": "weather",
"version": "1.0.0"
}
}
}
Tool Discovery
Client → Server:
{
"jsonrpc": "2.0",
"id": 2,
"method": "tools/list"
}
Server → Client:
{
"jsonrpc": "2.0",
"id": 2,
"result": {
"tools": [
{
"name": "get_alerts",
"description": "Get weather alerts for a US state.",
"inputSchema": {
"type": "object",
"properties": {
"state": {
"type": "string",
"description": "Two-letter US state code (e.g. CA, NY)"
}
},
"required": ["state"]
}
},
{
"name": "get_forecast",
"description": "Get weather forecast for a location.",
"inputSchema": {
"type": "object",
"properties": {
"latitude": {
"type": "number",
"description": "Latitude of the location"
},
"longitude": {
"type": "number",
"description": "Longitude of the location"
}
},
"required": ["latitude", "longitude"]
}
}
]
}
}
External API Integration
National Weather Service API
The server integrates with the following NWS API endpoints:
| Endpoint | Purpose | Rate Limit |
|---|---|---|
GET /alerts/active/area/{state} |
Retrieve active alerts for a state | User-Agent required |
GET /points/{latitude},{longitude} |
Get grid point metadata | User-Agent required |
GET {forecast_url} |
Retrieve detailed forecast | User-Agent required |
Required Headers:
User-Agent: weather-app/1.0
Accept: application/geo+json
Error Handling
The server implements graceful error handling for:
- Invalid coordinates: Returns error message for non-US locations
- Network failures: Returns "Unable to fetch..." messages
- Missing data: Returns "No active alerts" or similar user-friendly messages
- API errors: Catches and handles HTTP errors from NWS API
Transport Layer
- Type: STDIO (Standard Input/Output)
- Encoding: UTF-8
- Message Format: JSON-RPC 2.0
- Framing: Newline-delimited JSON
Security Considerations
- Input Validation: All parameters are validated against schema
- Rate Limiting: Respects NWS API rate limits
- Error Sanitization: External API errors are sanitized before returning to client
- No Authentication: Server uses public NWS API (no credentials required)
Logging
- STDIO Servers: All logs written to
stderr(neverstdout) - Log Location: Configured in MCP client (e.g.,
~/Library/Logs/Claude/mcp-server-weather.log) - Log Level: Errors and warnings only (to avoid STDIO corruption)
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.