weather
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@weather What's the forecast for Chicago?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-weather-ts
TypeScript MCP server that exposes US weather from the National Weather Service API to hosts such as Cursor.
The host starts node build/index.js and talks JSON-RPC over stdio. The model never calls NWS itself; it calls this server’s tools (and can read a resource or use a prompt).
How MCP works (tools, resources, prompts, transport): docs/create-mcp.readme.md.
Requirements
Node.js 22+ (this repo uses ESM and
fetch)npm
Network access to
https://api.weather.gov(US locations only)
Related MCP server: weather
Setup
npm install
npm run buildtsc writes JavaScript to build/. Cursor must run the built file, not src/index.ts.
Scripts
Command | What it does |
| Compile |
| Smoke-test NWS: |
Mount in Cursor
Build (
npm run build).Add
.cursor/mcp.jsonin this project:
{
"mcpServers": {
"weather": {
"type": "stdio",
"command": "node",
"args": ["${workspaceFolder}/build/index.js"]
}
}
}For all Cursor projects, use %USERPROFILE%\.cursor\mcp.json and a full path to build\index.js instead of ${workspaceFolder}.
Open Customize → MCP (or Cursor Settings → MCP) and enable weather.
After you change
src/, runnpm run buildagain and toggle the server off/on so Cursor restarts the process.
Do not console.log after the server connects: stdout is the MCP wire. Use console.error for logs.
What you can call
Tools
The model (or you, by asking in Agent chat) invokes these with tools/call.
Name | Inputs | What it does |
|
| Active alerts for that state |
|
| 12-hour forecast (NWS |
|
| Practice: |
Example chat:
“Any weather alerts for CA?”
“Forecast for 39.7456, -97.0892”
Example arguments:
{ "state": "CA" }{ "latitude": 39.7456, "longitude": -97.0892 }Resource
Name | URI | What it does |
|
| Short static note on tools and the NWS lookup flow |
Ask the agent to read weather://nws-guide, or use resources/read in a client.
Prompt
Name | Args | What it does |
|
| User-message template that tells the model to use |
In Cursor, pick the Check weather prompt and fill place.
Project layout
src/index.ts Create McpServer, register, connect stdio
src/tools.ts get_alerts, get_forecast, test_tool
src/resources.ts weather://nws-guide
src/prompts.ts check_weather
src/weather-api-call.ts NWS fetch + types + alert formatting
src/createTransport.ts StdioServerTransport + connect
tests/weather-api-call.test.ts
docs/create-mcp.readme.md How to design MCP serversStartup order in src/index.ts:
new McpServer({ name: "weather", version: "1.0.0" })registerWeatherTools/registerWeatherResources/registerWeatherPromptsconnectStdioTransport(server)
NWS notes
Forecasts are not at
/points/{lat},{lon}/forecast. Load/points/{lat},{lon}(four decimal places), then followproperties.forecastorproperties.forecastHourly.NWS requires a
User-Agentheader (set inweather-api-call.ts).Coverage is US (and some territories). Other coordinates often fail.
Troubleshooting
Symptom | What to try |
Server red / no tools | Rebuild, confirm |
Handshake fails | Make sure you |
Empty or failed forecast | US lat/lon only; check MCP Logs |
| Network / NWS outage |
Cursor: Output → MCP Logs.
License
ISC
Available Tools
3 toolsget_alertsWeather AlertsB
Get weather alerts for a US state
Inputs: state (required).
get_forecastWeather ForecastC
Get weather forecast for a location
Inputs: latitude (required), longitude (required).
test_toolTest ToolD
Test tool
Inputs: name (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
get_alerts and get_forecast are clearly distinct in purpose, but test_tool is ambiguous and could be mistaken for a generic utility, though it doesn't overlap with the weather tools. An agent can easily differentiate the two weather tools, and test_tool is separate enough to avoid confusion.
Two tools follow a consistent 'get_<noun>' pattern (get_alerts, get_forecast), but test_tool breaks this convention with a different verb and structure. The naming is still readable, but the inconsistency is noticeable given only three tools.
Three tools is borderline for a weather server, which typically needs more operations like current conditions or location search. The presence of test_tool, which does not serve a core weather purpose, makes the count feel less purposeful and slightly thin.
The server covers alerts and forecasts but lacks fundamental weather operations like current conditions or historical data. The test_tool is irrelevant to the domain, leaving notable gaps that would require agents to work around missing functionality.
Maintenance
Related MCP Connectors
Current weather and forecast lookup as an agent tool.
Official NWS forecasts and alerts, as one MCP tool through Apify
US NWS weather alerts and 5-day forecasts for AI agents. $0.01 per call.
Hosted MCP server for Xweather weather data: conditions, forecasts, alerts, and more.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceExposes tools for retrieving weather forecasts and alerts using the National Weather Service API.-
- FlicenseCqualityDmaintenanceExposes US weather data as MCP tools, resources, and prompts via the National Weather Service API, enabling clients like Claude Desktop to get alerts, forecasts, and weather briefings.21-
- FlicenseNot gradedqualityDmaintenanceThis MCP server provides tools to get current weather, forecasts, and weather alerts from the US National Weather Service via REST APIs, enabling AI agents to query live weather data.1-
- FlicenseNot gradedqualityDmaintenanceEnables natural-language weather queries for U.S. states and coordinates, returning real-time alerts and forecasts from the National Weather Service API via MCP tools.-