Meteostat MCP. Model climate patterns from decades of historical weather.

You need historical weather data for your project? This Meteostat server connects your AI agent to one of the biggest databases out there. Forget building complex scrapers or juggling multiple API endpoints; you just let your agent use specific tools to pull precise meteorological records for any time scale and location type.

Querying Specific GPS Points: When You Don't Know a Station ID

If you only have coordinates—latitude and longitude—and no known weather station nearby, you can still get solid data. The server gives your agent tools that extrapolate historical observations for that exact spot on Earth. To pull hourly records, use point_hourly to retrieve granular measurements like temperature or wind speed hour by hour.

If you need the whole day summarized, point_daily gets those full daily statistics. For a broader view of seasonality, point_monthly pulls aggregated monthly weather stats for any given point.

Accessing Established Weather Stations: Real Records Only

When you know an established station ID (like one from the national network), your agent reads actual recorded measurements—no guessing involved. If you're looking at detailed records, stations_hourly retrieves hourly observations for that specific station; just remember it’s limited to thirty days per request. For a full day summary, use stations_daily, keeping in mind that this tool caps requests at ten years of data.

Need the monthly rundown from a known station? stations_monthly gives you those summarized historical statistics.

Finding Stations and Checking Metadata

You don't always know the ID you need. The server helps you figure it out first. If your target location is unknown, use stations_nearby. You just give it GPS coordinates and a radius, and it spits back a list of all operational weather stations within that zone. Once you have an ID, you can check its background using stations_meta; this tool looks up detailed descriptive info about the station, including whether it uses WMO or ICAO identifiers.

Calculating Climate Normals: Long-Term Baselines

For long-term research, your agent needs baseline data. The server gives you two ways to calculate the 30-year average climate normals. You can run point_normals on an arbitrary coordinate to get a general area's baseline temperature and precipitation figures. Alternatively, if you want the official historical normal for a known station, use stations_normals with that station’s ID.

Summary of Capabilities

• Interpolation: Get extrapolated hourly, daily, or monthly weather records using coordinates via point_hourly, point_daily, and point_monthly.
• Direct Station Query: Pull recorded historical data (hourly/daily/monthly) tied to specific station IDs through stations_hourly, stations_daily, and stations_monthly.
• Station Discovery: Find the closest monitoring sites using GPS coordinates via stations_nearby, then check details with stations_meta.
• Climate Baseline: Determine 30-year averages—either for a specific point (point_normals) or an established station (stations_normals).

Your AI agent uses these tools to handle everything from basic daily averages to complex, multi-decade climate normals. You just tell it what you need.