About Weather & Geo Intel MCP
Weather & Geo Intel MCP provides US weather, hazard and geospatial data to AI agents from government sources. It covers forecasts, alerts, earthquakes, elevation and address geocoding without API keys.
Key features
- 01Geocode US street addresses
- 02Get hourly and multi-day forecasts
- 03Check current conditions and weather alerts
- 04Search recent earthquakes
- 05Retrieve elevation by coordinates
Use cases
- 01Check a US location’s forecast and current conditions
- 02Find active state weather alerts
- 03Review recent earthquakes near an area
- 04Convert an address to coordinates
MCP support
It exposes weather and geospatial tools to MCP clients, using US government data feeds. No API keys are required.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://weather.selflabbs.com/mcpclaude mcp add --transport http selflabbs-weather-intel https://weather.selflabbs.com/mcp{"mcpServers":{"selflabbs-weather-intel":{"type":"http","url":"https://weather.selflabbs.com/mcp"}}}Open in Cursor{"servers":{"selflabbs-weather-intel":{"type":"http","url":"https://weather.selflabbs.com/mcp"}}}Open in VS Code{"mcpServers":{"selflabbs-weather-intel":{"type":"http","url":"https://weather.selflabbs.com/mcp"}}}{"mcpServers":{"selflabbs-weather-intel":{"serverUrl":"https://weather.selflabbs.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEWeather & Geo Intel MCP — by Datakoot
US weather, hazards and geospatial data for AI agents — as MCP tools your agent can call mid-task for forecasts, alerts, earthquakes and elevation. All from keyless US-government feeds. No API keys.
Tools
| Tool | What it does | Source |
|---|---|---|
geocode | Convert a US street address to latitude/longitude | US Census Bureau |
weather_forecast | Multi-day or hourly forecast for a US point | NWS / NOAA |
weather_current | Latest observed conditions from the nearest station | NWS / NOAA |
weather_alerts | Active warnings, watches and advisories by US state | NWS / NOAA |
earthquakes | Recent earthquakes, filterable by magnitude, time and area | USGS |
elevation | Ground elevation at a latitude/longitude | USGS |
US coverage. Have an address? Call geocode first, then the weather tools. No API keys required.
Quick start
claude mcp add --transport http weather-intel https://weather.datakoot.com/mcp
Or point any MCP client at https://weather.datakoot.com/mcp.
Try it in 10 seconds — no key, no signup
Paste this into a terminal:
curl -s https://weather.datakoot.com/mcp \
-H 'content-type: application/json' \
-H 'accept: application/json, text/event-stream' \
-d '{"jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": {"name": "weather_forecast", "arguments": {"lat": 36.37, "lon": -94.21}}}'
You get the multi-day National Weather Service forecast for Bentonville, AR — no API key, nothing to sign up for.
Or point any MCP client at the URL and just ask your agent, in plain language:
- "What's the weather in Chicago this week?"
- "Are there any active weather alerts in Texas right now?"
Data & attribution
Weather data comes from the National Weather Service / NOAA API; earthquakes and elevation from the USGS; address geocoding from the US Census Bureau geocoder. All are US-government public domain.
Part of Datakoot — keyless intelligence APIs for AI agents.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.