Open-Meteo Historical Weather MCP. Run climate forensics on 84 years of global weather data.
Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Open-Meteo Historical Weather provides access to 84 years of global weather records. Query temperature, wind, precipitation, and snow data for any specific location and date range from 1940 to today.
Use it when you need precise, long-term climate forensics.
What your AI agents can do
Get historical daily
Retrieves aggregated daily weather summaries, including min/max temperatures and total precipitation for a location.
Get historical temperature
Gets historical data points focused on temperature trends, like apparent temperature and dewpoint, useful for climate modeling.
Get historical weather
Provides a comprehensive weather record spanning 84 years by accepting coordinates and a specific date range (1940–present).
Queries all major metrics (wind, humidity, precipitation) for a defined latitude/longitude and date range.
Retrieves summary data points like maximum/minimum temperatures and total precipitation totals over multiple days.
Generates time-series data focused specifically on apparent temperature, dewpoint, and historical temperature readings for trend analysis.
Ask AI about this MCP
Supported MCP Clients
Waiting for input…
Open-Meteo Historical Weather MCP Server: 3 Tools
Retrieve historical daily weather aggregates, specialized temperature trend analysis, or comprehensive global records spanning eight decades.
019d75e8get historical daily
Retrieves aggregated daily weather summaries, including min/max temperatures and total precipitation for a location.
019d75e8get historical temperature
Gets historical data points focused on temperature trends, like apparent temperature and dewpoint, useful for climate modeling.
019d75e8get historical weather
Provides a comprehensive weather record spanning 84 years by accepting coordinates and a specific date range (1940–present).
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Open-Meteo Historical Weather, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
Open-Meteo Historical Weather gives you access to 84 years of global weather records. You can run queries across any coordinate pair from 1940 through today.
To pull full historical weather records, the get_historical_weather tool accepts coordinates and a specific date range spanning decades. This single function retrieves all major metrics you need: wind patterns, humidity levels, precipitation amounts, and general weather codes for that location and time period. It gives you a comprehensive view of what's been happening over those years.
If you only need summary data points, the get_historical_daily tool aggregates daily weather summaries. You can pull figures like minimum and maximum temperatures, plus total precipitation totals over multiple days. This is perfect when you're modeling trends that rely on day-to-day averages rather than hourly readings.
For deep climate analysis, the get_historical_temperature tool focuses specifically on temperature metrics. It pulls data points like apparent temperature and dewpoint, which are critical for sophisticated climate modeling. These historical readings let you track how specific thermal conditions have shifted over long periods of time.
You use this server when you need precise, long-term climate forensics. You can study environmental changes by defining a latitude/longitude pair and running the query against the 1940–present date range to get all metrics at once using get_historical_weather. If your analysis requires understanding extreme daily shifts, you'll use get_historical_daily for min/max temp data alongside total precipitation records.
When you need to track subtle but crucial changes in thermal conditions—like how dewpoint shifted over three decades—you run the specialized temperature query via get_historical_temperature. This gives you time-series data focused exclusively on apparent temperature, dewpoint readings, and historical temperatures. You're checking for specific climate trends that simple averages won't catch.
This tool set lets you analyze how global weather patterns have changed by giving you three distinct approaches: the full 84-year record of every metric (get_historical_weather), the summarized daily extremes (get_historical_daily), and specialized temperature trend data (get_historical_temperature). You're working with decades of raw, quantitative environmental data for anywhere on Earth.
How Open-Meteo Historical Weather MCP Works
- 1 You provide the tool with a set of parameters: latitude, longitude, a start date, and an end date.
- 2 The server sends this request to Open-Meteo's historical API endpoint, filtering by the specific data type (daily summary, temperature trend, or general record).
- 3 Your AI client receives structured JSON data containing the requested weather metrics for every day in the specified range.
The bottom line is: you input a location and a time window, and you get back clean, structured historical climate data.
Who Is Open-Meteo Historical Weather MCP For?
This server is for anyone whose job depends on understanding the past. Think agronomists predicting drought risk, insurance adjusters calculating flood exposure, or real estate developers vetting a plot's long-term climate viability. If your work requires looking back decades to understand patterns, this is what you need.
Uses the server to compare historical rainfall and temperature trends over 30 years to determine ideal planting windows or predict drought severity.
Runs get_historical_weather for specific coastal properties, checking records from decades ago to estimate risk associated with past severe storms and flooding.
Uses the dedicated temperature tool (get_historical_temperature) to model long-term warming trends and calculate apparent temperature shifts across different regions.
What Changes When You Connect
- You stop relying on surface-level averages. By using
get_historical_weather, you get full daily records—including humidity and wind patterns—for any location, making your analysis robust. - Need to prove a warming trend? The dedicated
get_historical_temperaturetool lets you pull specific data like apparent temperature over decades, providing metrics that general tools miss. - Predicting crop yields requires more than just rainfall. Using
get_historical_daily, you can cross-reference total precipitation with max/min temperatures to build accurate risk models. - Forget querying multiple APIs for different time spans. This MCP Server handles the entire 1940–present window, giving your agent one place to get massive, consistent datasets.
- You eliminate guesswork about data scope. The general
get_historical_weathertool ensures you capture every detail—from snow depth to weather codes—in a single request.
Real-World Use Cases
Validating historical flood damage
An underwriter needs to assess the risk of a property that flooded in 2005. Instead of manual research, they ask their agent: 'What was the weather like at these coordinates from July 1 to July 31, 2005?' The server runs get_historical_weather, providing daily precipitation totals and wind speeds for an accurate assessment.
Modeling agricultural yield decline
An agronomist suspects a long-term drop in corn yields. They instruct their agent to use the dedicated temperature tool, get_historical_temperature, comparing apparent temperatures between 1980 and 2020. The resulting trend data pinpoints when warming became significant.
Researching wartime conditions
A historian wants to know the exact weather on D-Day for a specific city. They use get_historical_weather, providing the precise coordinates and date (1944-06-06). The agent returns max/min temps, precipitation, and wind speed needed for their paper.
Comparing regional climate shifts
A researcher wants to see if a pattern in extreme heat has changed over time. They use get_historical_daily and compare the average maximum temperatures of two different regions (A vs B) across three distinct decades.
The Tradeoffs
Over-calling for basic data
Asking the agent to use all three tools (get_historical_daily, get_historical_temperature, and get_historical_weather) sequentially, believing it's necessary to cover all bases.
→
You usually don't need all three. If you want a general look at rainfall and wind, stick with the comprehensive data from get_historical_weather. Only use the other tools if your goal is strictly temperature trends or daily aggregates.
Mixing up time granularity
Thinking that running get_historical_daily will give you hourly detail, leading to an incomplete picture of peak storm intensity.
→
If you need the highest resolution data, check the tool documentation. For basic daily summaries, use get_historical_daily. If you must model specific temperature shifts, use get_historical_temperature.
Ignoring date format requirements
Passing dates like 'June 6th' or 'Around the year 1944' to the server.
→
The tools require strict YYYY-MM-DD formatting. Always pass the start and end dates as strings in that specific format.
When It Fits, When It Doesn't
Use this MCP Server if your project is fundamentally about climate science, historical forensics, or long-term pattern analysis. Your question must involve comparing conditions across years, decades, or even a century.
Don't use it if you need to know the weather for tomorrow; these tools are read-only archives. If you only care about today's forecast, look at a dedicated real-time forecasting service. Furthermore, don't use it if your query is too specific (e.g., 'What was the temperature in my backyard last Tuesday?'). You must provide coordinates and date ranges for any search.
To summarize: If time depth > 1 year, this server works. Otherwise, find a different tool.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Open-Meteo. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 3 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Gathering historical weather data used to take hours of cross-referencing.
Before having access to this kind of MCP Server, figuring out the climate conditions for a specific date—say, comparing rainfall in London across three different decades—meant opening dozens of academic papers, navigating multiple government archives, and manually inputting data into spreadsheets. It was slow, error-prone work that required specialized knowledge just to compile the initial dataset.
Now, you ask your agent directly. You provide the location (lat/lon) and the time window, then specify whether you need a daily summary or temperature trends. The server runs `get_historical_weather` and returns all the data points structured for immediate use. It’s that simple.
Open-Meteo Historical Weather MCP Server: Get 84 Years of Data.
You don't have to worry about which tool is best for what. The server handles the complexity, whether you are running a broad query with `get_historical_weather` or need to narrow your focus specifically to temperature using `get_historical_temperature`. You just ask for the data type and the range.
What’s different now is that your agent isn't just pulling data; it's doing research. It lets you conduct full-scale climate modeling right from your chat interface, without ever touching an external API key or a complex script.
Common Questions About Open-Meteo Historical Weather MCP
How do I use `get_historical_weather` for a single day? +
You provide the latitude, longitude, and set both the start date and end date to that specific day in YYYY-MM-DD format. This gives you all available metrics for that single 24-hour period.
Is `get_historical_temperature` better than `get_historical_daily`? +
It depends on your goal. Use get_historical_temperature if you only care about tracking apparent temperature, dewpoint, or specific warming trends. Use get_historical_daily when you need a comprehensive daily summary including wind and total precipitation.
Can I get data for 1940 using any of the tools? +
Yes. All three tools are capable of retrieving data going back to 1940, as this is the minimum recorded year covered by the system.
What coordinates should I provide for global weather data? +
You must provide precise latitude and longitude coordinates (e.g., -33.8688, 151.2093). These are required by all three historical tools.
If I use `get_historical_weather` for a date range with gaps, how does the service handle missing data? +
The tool doesn't guess or interpolate. If records are unavailable for certain dates, it returns explicit null values or an error message detailing the gap. This keeps your analysis accurate by forcing you to account for known data voids.
Can `get_historical_weather` provide specialized metrics beyond standard weather, like air quality indexes? +
No. The tool is limited strictly to established meteorological records: temperature, precipitation, wind speed, and snow. For specific environmental data sets, you'll need a different API designed for atmospheric chemistry.
What are the performance limits or rate restrictions when calling `get_historical_daily` repeatedly? +
Vinkius manages usage quotas for this server. You can make frequent calls, but rapid-fire requests may trigger temporary throttling. Always check your account dashboard for real-time service status and current request limits.
Does `get_historical_temperature` provide data in a structured format that my AI client agent can easily parse? +
Yes, it returns well-structured JSON output. This includes max/min temperatures, apparent temperature, and dewpoint readings, allowing your AI client to reliably ingest these metrics directly into code or analysis.
How far back does the historical data go? +
All the way to January 1, 1940 — that's 84 years of continuous, hourly global weather data powered by ERA5 reanalysis from ECMWF.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
IBKR (Interactive Brokers)
Manage your Interactive Brokers account — execute trades, monitor portfolio ledgers, and fetch real-time market data via the Client Portal API.
Open-Meteo Full Access
The ultimate weather Mega-Server: 15 tools covering forecast, historical (84 years), marine, air quality, pollen, climate projections (to 2100), flood, geocoding, and elevation — all in one zero-auth integration.
Robolytix
Monitor robotic process automation performance with analytics that track bot execution times, success rates, and exceptions.
You might also like
Groq
Empower LLM applications via Groq — perform ultra-fast LPU-accelerated chat completions, handle audio transcription and translation, and use JSON mode directly from any AI agent.
OneLocal LocalReviews
Boost your local business visibility with automated review collection, reputation monitoring, and response management tools.
Oracle NetSuite
Manage financials, sales orders, inventory, and customer records on Oracle NetSuite — the leading cloud ERP.