mcpField
W
Weather & Geo Intel MCP

Weather & Geo Intel MCP

Remote
github.com/datakootMaps & Travel0Updated 5d ago
Repository

About Weather & Geo Intel MCP

Weather & Geo Intel MCP provides AI agents with US weather, hazard, and geospatial data from government sources. Its tools cover forecasts, alerts, earthquakes, elevation, and address geocoding without API keys.

Key features

  1. 01US address geocoding
  2. 02Hourly and multi-day forecasts
  3. 03Current conditions and weather alerts
  4. 04Earthquake lookup with filters
  5. 05Elevation lookup by coordinates

Use cases

  1. 01Get a forecast for a US location
  2. 02Check active state weather alerts
  3. 03Look up earthquakes near an area
  4. 04Convert a street address to coordinates

MCP support

Exposes geocoding, weather, earthquake, and elevation tools to MCP clients over HTTP, using US government data sources.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://weather.datakoot.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

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

6
ParameterTypeRequiredDescription
addressstringYesA US street address ('1600 Pennsylvania Ave NW, Washington DC') or a city or town ('Chicago, IL', 'Springdale, Arkansas')

Details

From the project README

Weather & 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

ToolWhat it doesSource
geocodeConvert a US street address to latitude/longitudeUS Census Bureau
weather_forecastMulti-day or hourly forecast for a US pointNWS / NOAA
weather_currentLatest observed conditions from the nearest stationNWS / NOAA
weather_alertsActive warnings, watches and advisories by US stateNWS / NOAA
earthquakesRecent earthquakes, filterable by magnitude, time and areaUSGS
elevationGround elevation at a latitude/longitudeUSGS

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

Markdown supported

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.