Open-Meteo

You can run the Open-Meteo MCP Server to expose Open-Meteo weather data via a lightweight MCP interface that you can connect to from your MCP client or AI workflow. It provides a wide range of weather, air quality, marine, and climate data, with options to tailor requests and units for your applications.

How to use

You run the MCP server locally and connect to it from your MCP client. Start by launching the server using the standard runtime method shown in the install steps, then configure your client to point at the local MCP instance. Use the available tools to request weather forecasts, historical data, air quality, marine conditions, and climate projections. You can select specific models, time ranges, and output units to fit your use case.

How to install

Prerequisites: you need Node.js and npm installed on your system.

Option 1: Run directly with npx (recommended) with no local installation.

Option 2: Global installation via npm.

Option 3: Install from source for development.

Configuration and usage notes

Configure how you start and where the server points by using MCP client configuration. The simple setup runs the MCP server via npx without any extra environment, while the full setup specifies API endpoints as environment variables.

The server can be started through a local development workflow or via a standard runtime environment, and you can supply environment variables to override default API URLs as needed.

Additional sections

Here are practical configuration examples you can adapt for your setup. The following snippets show how to configure a local stdio MCP entry that runs the MCP server using npx.

{
  "mcpServers": {
    "open_meteo": {
      "command": "npx",
      "args": ["open-meteo-mcp-server"]
    }
  }
}

If you prefer to pass environment variables to customize the base API URLs, use the full configuration variant shown here.

{
  "mcpServers": {
    "open_meteo": {
      "command": "npx",
      "args": ["open-meteo-mcp-server"],
      "env": {
        "OPEN_METEO_API_URL": "https://api.open-meteo.com",
        "OPEN_METEO_AIR_QUALITY_API_URL": "https://air-quality-api.open-meteo.com",
        "OPEN_METEO_MARINE_API_URL": "https://marine-api.open-meteo.com",
        "OPEN_METEO_ARCHIVE_API_URL": "https://archive-api.open-meteo.com",
        "OPEN_METEO_SEASONAL_API_URL": "https://seasonal-api.open-meteo.com",
        "OPEN_METEO_ENSEMBLE_API_URL": "https://ensemble-api.open-meteo.com",
        "OPEN_METEO_GEOCODING_API_URL": "https://geocoding-api.open-meteo.com"
      }
    }
  }
}

Security and reliability notes

Keep your environment secure by not exposing the MCP server to untrusted networks. Use network restrictions, proper access controls, and monitor API usage to avoid rate limits or abuse. Consider caching frequent queries to reduce external API load and improve response times.

Troubleshooting

If requests fail, verify that the MCP server is running, the command line arguments are correct, and the environment variables are set as expected. Check for network connectivity issues and ensure you are using valid coordinates and date ranges in your requests.

Notes

The server provides access to a wide set of Open-Meteo endpoints, including weather forecasts, archives, air quality, marine data, geocoding, and climate-related projections. You can leverage ensemble and seasonal features for uncertainty quantification and long-range planning.

Available tools

weather_forecast

7-day forecasts with hourly and daily resolution from the core Weather Forecast API.

weather_archive

Historical ERA5 data from 1940 to present.

air_quality

Forecasts for PM2.5, PM10, ozone, NO2 and other pollutants.

marine_weather

Wave height, direction, period and sea surface temperature.

elevation

Digital elevation model data for given coordinates.

geocoding

Search locations by name or postal code and return coordinates and details.

dwd_icon_forecast

High-resolution European model from the German DWD ICON family.

gfs_forecast

Global NOAA GFS model with high-resolution North America data.

meteofrance_forecast

Météo-France models AROME/ARPEGE for France.

ecmwf_forecast

ECMWF model data for Europe.

jma_forecast

JMA high-resolution model for Asia.

metno_forecast

MET Norway model data for Nordic regions.

gem_forecast

Environment Canada GEM model.

flood_forecast

GloFAS river discharge and flood forecasts.

seasonal_forecast

Long-range forecasts up to 9 months ahead.

climate_projection

CMIP6 climate projections for warming scenarios.

ensemble_forecast

Ensemble forecasts showing forecast uncertainty.