For Agents
Look up historical weather observations and climate normals for any global station or coordinate, returning hourly, daily, or monthly aggregates suitable for backtesting and analysis.
Use for: I need to pull hourly temperature history for Berlin in January 2024, Find all weather stations within 50 km of these GPS coordinates, Retrieve daily rainfall totals for a vineyard location over the last five years, Get the climate normals for Paris to compare against this year's summer
Not supported: Does not provide forecasts, severe weather alerts, or marine and tidal data - use for historical weather observations and climate normals only.
The Meteostat Weather API provides historical weather and climate data sourced from thousands of public weather stations worldwide. Agents and developers can request hourly, daily, and monthly observations either by station identifier or by latitude and longitude coordinates, and retrieve long-running climate normals for any location. The API is distributed through RapidAPI and is authenticated with a single header-based key.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Meteostat Weather API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fmeteostat.p.rapidapi.com%2Fmeteostat" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fmeteostat.p.rapidapi.com%2Fmeteostat" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Meteostat Weather API.
Retrieve hourly temperature, precipitation, wind, and pressure observations for a specific weather station
Locate the nearest weather stations to a given latitude and longitude with configurable radius and limit
Pull daily and monthly historical aggregates for an arbitrary geographic point using the bundled interpolation model
Request 30-year climate normals to benchmark a date or location against long-term averages
Fetch station metadata including elevation, country, region, timezone, and identifier mappings
Patterns agents use Meteostat Weather API for, with concrete tasks.
★ Backtest Operations Against Historical Weather
Operations and supply chain teams analyse how past weather conditions affected logistics, agriculture yields, or energy demand. Meteostat's daily and monthly point endpoints return interpolated observations for any latitude and longitude, so analysts do not have to manually pick the nearest station. The API covers decades of history in a single call and returns JSON aggregates ready for ingestion into a data warehouse.
Fetch daily mean temperature and precipitation totals for latitude 52.52, longitude 13.405 between 2023-01-01 and 2023-12-31 and aggregate by month.
Weather Station Discovery for Sensor Networks
Researchers and IoT teams need to identify the closest reliable weather stations to a sensor deployment so they can calibrate or cross-check measurements. The /stations/nearby endpoint accepts a coordinate and radius and returns ranked station metadata including elevation and operational period, which can be combined with the station-level hourly endpoints for a precise observation feed.
List the five nearest active weather stations to latitude 40.7128, longitude -74.0060 within 25 km and return their IDs and elevations.
Climate Normals for Risk and Insurance Models
Insurers, climate analysts, and ESG teams require 30-year climate normals to score the typicality of a weather event. Meteostat exposes /point/normals and /stations/normals endpoints that return long-term monthly averages, which feed directly into perils modelling, parametric insurance triggers, and climate disclosure reports without requiring a separate climate data subscription.
Retrieve the 1991-2020 climate normals for latitude 34.05, longitude -118.24 and return monthly mean temperatures.
Agent-Driven Weather Lookups
AI agents that plan trips, reconcile delivery exceptions, or generate reports often need to attach a historical weather snapshot to an event. Through Jentic, an agent searches for the operation by intent, loads the input schema for /point/daily or /point/hourly, and executes the call with a coordinate and date range. The Meteostat RapidAPI key stays in your Jentic One instance - the agent never sees it.
Search Jentic for 'historical weather for a location', load the /point/daily schema, and request observations for latitude 48.85, longitude 2.35 on 2024-07-15.
10 endpoints — the meteostat weather api provides historical weather and climate data sourced from thousands of public weather stations worldwide.
METHOD
PATH
DESCRIPTION
/stations/nearby
Find weather stations near a coordinate
/stations/hourly
Hourly observations for a specific station
/point/hourly
Hourly weather data for a latitude and longitude
/point/daily
Daily weather aggregates for a coordinate
/point/monthly
Monthly weather aggregates for a coordinate
/point/normals
30-year climate normals for a coordinate
/stations/nearby
Find weather stations near a coordinate
/stations/hourly
Hourly observations for a specific station
/point/hourly
Hourly weather data for a latitude and longitude
/point/daily
Daily weather aggregates for a coordinate
/point/monthly
Monthly weather aggregates for a coordinate
/point/normals
30-year climate normals for a coordinate
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Meteostat Weather API by hand means holding a RapidAPI key, sending it in the X-RapidAPI-Key header, and building each point and station query yourself. Through Jentic you install once, import the Meteostat Weather API from the API Directory, store the RapidAPI key once, and your agent calls it.
Permission scoping
This API is read-only historical observations and climate normals with no resource id in the URL path, so limit the agent to the operations it needs, such as a point hourly or point normals query. You choose which operations it may call, and none of them change data on your account.
Credential isolation
Your Meteostat 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.
Intent-based discovery
Agents search Jentic by intent such as 'get historical weather for a coordinate' or 'get climate normals', and Jentic returns the matching Meteostat operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Meteostat Weather API through Jentic.
What authentication does the Meteostat Weather API use?
Meteostat on RapidAPI requires an API key passed in the X-RapidAPI-Key header. When called through Jentic the key is stored encrypted in your Jentic One instance and injected at execution time, so agents never see the raw value.
Can I retrieve weather data for any location, not just stations?
Yes. Use the /point/hourly, /point/daily, /point/monthly, and /point/normals endpoints with a latitude and longitude. Meteostat interpolates from surrounding stations rather than requiring an exact station match.
What are the rate limits for the Meteostat API?
Rate limits are set by the chosen RapidAPI plan rather than the spec - the free tier permits a few hundred requests per day, with higher quotas on paid tiers. Check the RapidAPI listing for the current per-tier numbers before scaling out a backfill.
How do I get hourly history for a coordinate through Jentic?
Search Jentic with the query 'historical hourly weather for a location', load the /point/hourly operation schema, then execute with lat, lon, start, and end parameters. The Jentic SDK handles the X-RapidAPI-Key header from your stored credential.
Does Meteostat return forecast data?
No - this API focuses on historical observations and long-term climate normals. For forecasts you would pair Meteostat with a forecasting API such as OpenWeatherMap or Tomorrow.io.
How far back does the historical data go?
Coverage depends on the station - many European and North American stations go back to the early 1900s, while others have shorter records. The /stations/meta endpoint returns each station's operational period so agents can validate the requested window before issuing a data call.
Can I limit what my agent is allowed to do with the Meteostat Weather API?
Yes. Because your Jentic One instance is self-hosted, your own rules decide which Meteostat operations and credentials the agent may use, so you can allow only the calls it needs, such as /point/hourly or /point/normals, and block the rest. The Meteostat Weather API is read-only historical observations and climate normals with no resource id in the URL path, so nothing an agent calls can change or delete data on your account. You store the RapidAPI key once and it is injected into the X-RapidAPI-Key header at execution time, so the agent can run the permitted queries without ever seeing the raw key.
GET STARTED