canonical: https://jentic.com/apis/meteostat.net/meteostat # Meteostat JSON API The Meteostat JSON API provides access to a large archive of historical weather and climate data from thousands of weather stations worldwide. Records can be queried by weather station ID or by geographic point and filtered by date range, with hourly, daily, monthly, and climate-normal granularities. The API is hosted on RapidAPI and is suited to backtesting, climate research, agriculture analytics, and any workflow that needs deep historical weather rather than short-range forecasts. ## For AI agents Query historical weather and climate normals from Meteostat by station or geographic point, hourly through monthly granularity. ## Scope Does not handle short-range forecasts, severe weather alerts, or marine-specific data - use for historical weather observations and climate normals only. ## Capabilities - Find the nearest weather stations to a given latitude and longitude for site-specific lookups - Pull hourly historical observations for a station to backfill a research dataset - Retrieve daily aggregated weather records for a station between two dates - Compute climate normals for a station over a multi-decade reference period - Query hourly, daily, or monthly weather for an arbitrary geographic point without a station ID - Inspect a single weather station's metadata before issuing observation queries ## Use cases ### Climate-Aware Agriculture Analytics Agriculture analytics teams backtest yield models against historical weather. Meteostat lets the agent fetch daily and monthly observations for a farm's coordinates and align them with crop calendars. The /point endpoints accept a lat/long directly so the agent does not need to pre-resolve a station ID. Example prompt: GET /point/daily for the farm coordinates and date range, then aggregate the response by month for the yield model ### Insurance Claim Verification Insurance teams validate weather-related claims by retrieving the conditions at the time and place of an incident. The agent calls /stations/nearby for the incident coordinates, picks the closest active station, and then fetches /stations/hourly for the hour in question. Climate normals from /stations/normals provide a baseline for whether the conditions were unusual. Example prompt: GET /stations/nearby for the incident coordinates, then GET /stations/hourly for the chosen station around the incident timestamp ### Climate Normals for Site Planning Real-estate, energy, and infrastructure planning workflows benchmark sites against long-term climate normals. The /stations/normals and /point/normals endpoints return reference-period averages so the agent can compare candidate sites on temperature, precipitation, and other climate dimensions. These rolls forward into a structured comparison report. Example prompt: GET /point/normals for each candidate site coordinate and compare the returned averages on temperature and precipitation ### AI Agent Integration via Jentic An AI agent uses Jentic to discover Meteostat by intent search ('get historical weather'). Jentic returns the relevant /point or /stations operation with its input schema, so the agent fetches observations in a single load-and-execute step. The RapidAPI key sits in your Jentic One instance and never enters the agent's prompt. Example prompt: Use Jentic to search 'get historical weather for a location', load the /point/daily schema, and execute it for the user's chosen coordinates and date range ## Key endpoints | Method | Path | Description | | --- | --- | --- | | GET | /stations/nearby | Find nearby weather stations by geo location | | GET | /stations/meta | Get metadata for a weather station | | GET | /stations/hourly | Get hourly weather data for a station | | GET | /stations/daily | Get daily weather data for a station | | GET | /stations/normals | Get climate normals for a weather station | | GET | /point/daily | Get daily weather for a geographic location | | GET | /point/hourly | Get hourly weather for a geographic location | | GET | /point/normals | Get climate normals for a geographic location | ## Key resources - **Stations** — Weather station metadata and observation queries - nearby search, hourly, daily, monthly, normals - **Point** — Geographic-point queries that synthesise observations across nearby stations - hourly, daily, monthly, normals ## Why Jentic - **Setup:** Wiring the Meteostat JSON API by hand means holding a RapidAPI key, sending it in the X-RapidAPI-Key header, and building each stations or point query yourself. Through Jentic you install once, import the Meteostat JSON API from the API Directory, store the RapidAPI key once, and your agent calls it. - **Permission scoping:** This API is read-only historical weather and climate data, so limit the agent to the operations it needs, such as a point daily query or a station lookup. You choose which operations it may call, and none of them change data on your account. - **Credential handling:** Your RapidAPI key is stored once, encrypted, by your own Jentic One instance and injected into the X-RapidAPI-Key header at execution time. It never enters the agent's prompt, logs, or context. - **Discovery method:** Agents search Jentic by intent such as 'get historical weather for a coordinate' or 'find nearby stations', and Jentic returns the matching /point or /stations operation with its input schema so the agent calls the right endpoint without browsing the reference docs. ## Related APIs - **OpenWeatherMap** — Weather provider with current, forecast, and historical endpoints - **WeatherAPI** — Weather API with forecast, history, and astronomy data - **Weatherbit** — Weather data API with current, forecast, and history endpoints - **Meteosource** — Forecast and air-quality provider that pairs well with Meteostat's historical archive ## FAQ ### What authentication does the Meteostat JSON API use? The API is hosted on RapidAPI and expects an `X-RapidAPI-Key` header (the `rapidApiKey` security scheme in the spec). Through Jentic the key is stored in your Jentic One instance and injected at request time, so it never enters the agent's prompt. ### Can I query weather without knowing a station ID? Yes. The /point/hourly, /point/daily, /point/monthly, and /point/normals endpoints accept latitude and longitude directly and synthesise observations from nearby stations, so the agent does not need to pre-resolve a station. ### How do I find the closest weather station to a location? Call GET /stations/nearby with the latitude and longitude. The response lists stations sorted by distance, which the agent can then drill into via /stations/meta or any of the observation endpoints. ### Are climate normals available? Yes. /stations/normals and /point/normals return long-term reference-period averages, suitable for site planning, climate research, and benchmarking unusual events. ### How do I pull historical weather through Jentic? Search Jentic for `get historical weather for a location`, load the /point/daily operation (or the station-based equivalent), and execute it with coordinates and a date range. Jentic returns the structured response. ### Are there published rate limits? Rate limits are governed by the RapidAPI plan attached to your account, not by the OpenAPI spec. Inspect your RapidAPI dashboard for the per-second and per-month quotas tied to your subscription. ### Can I limit what my agent is allowed to do with the Meteostat JSON API? Yes. Because you run your own self-hosted Jentic One instance, your own rules decide which Meteostat operations the agent may call and which credentials it may use. You can restrict it to just the endpoints it needs, such as GET /point/daily or GET /stations/nearby, and withhold the rest. Every operation here is read-only historical weather and climate data, so nothing the agent calls changes data on your account.