INMET Weather MCP for AI. Analyze official Brazilian weather data instantly.
Works with every AI agent you already use
…and any MCP-compatible client








Connect to your AI in seconds.
INMET (Apitempo - Meteorologia) MCP provides direct access to Brazil's official meteorological data from INMET. Use this MCP to query historical and real-time atmospheric measurements, fetch detailed city forecasts using IBGE codes, or analyze regional weather patterns across the country.
It also gives you URLs for the latest GOES-16 satellite imagery metadata. Ideal for anyone needing precise climate intelligence.
What your AI can do
Get all forecasts
Retrieves weather predictions for every supported city in Brazil.
Get forecast by city
Gets the detailed weather forecast when you specify a single city's code or name.
Get meteorological data by date
Pulls daily measurements for a specific monitoring station ID on a given date.
Fetch current and predicted weather conditions for multiple cities across Brazil.
Retrieve hourly or daily measurements (temp, humidity) for specific monitoring stations over time.
Query and aggregate all available weather readings for a defined geographical region on a single date.
Pull the latest GOES-16 satellite metadata, giving you direct URLs for visual monitoring tools.
Ask an AI about this
Waiting for input…
INMET (Apitempo - Meteorologia) - 8 Tools
These eight tools let you query everything from general regional weather patterns to hourly measurements at specific monitoring stations.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using INMET (Apitempo - Meteorologia) on VinkiusGet All Forecasts
Retrieves weather predictions for every supported city in Brazil.
Get Forecast By City
Gets the detailed weather forecast when you specify a single city's code or name.
Get Meteorological Data By Date
Pulls daily measurements for a specific monitoring station ID on a given date.
Get Meteorological Data By Region
Collects data from every station within a defined Brazilian region for a single day.
Get Satellite Images
Fetches links to the newest GOES-16 satellite imagery metadata available for review.
Get Station Data Daily
Retrieves comprehensive daily weather metrics for one specific station ID.
Get Station Data Hourly
Grabs highly detailed hourly readings (temp, pressure) for a single station and time period.
List Stations
Lists all available meteorological stations across Brazil, letting you identify the...
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
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 INMET (Apitempo - Meteorologia), then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ 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
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by INMET. 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 connection provides 8 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Tracking Weather Used to Be a Manual Pain Point
Today, checking weather means jumping between multiple government sites. You might copy-paste station IDs into one dashboard to check daily readings, then switch tabs to manually pull forecast data for five different cities, and finally download separate spreadsheets just to compare temperature anomalies over time.
With this MCP, the whole process is a single call. Your agent doesn't need multiple tabs or copies. It executes `get_meteorological_data_by_region` and returns all that structured comparison data instantly.
Using get_satellite_images to Visualize Data
Manually, getting satellite imagery means navigating complicated government portals, finding the right GOES-16 channel (Visible vs. Infrared), and downloading a separate file for each view you want to inspect.
Now, calling `get_satellite_images` gives your agent direct metadata links for different channels. You get the necessary URLs immediately, letting your workflow proceed without manual download steps.
What your AI can actually do with this
Need to know what's happening with the weather in Brazil? This connector lets your AI client pull official data straight from INMET, bypassing messy manual API calls. You can query specific stations—whether they're automatic or manually monitored—to get hourly or daily measurements like temperature and pressure. Want a regional view? Just specify an area, and the MCP gathers all station data points for that region on a given date.
It handles forecasts too; you don't need to guess which city code to use. Plus, it gives you metadata links for GOES-16 satellite imagery, so your agent can pull visual context alongside numerical reports. Connecting this via Vinkius makes sure all these complex data sources are available through a single point in your AI workflow.
019e38ad-e0ec-7154-87c8-d16298d08643 Here's how it actually works
The bottom line is your AI client gets standardized access to complex, government-grade weather datasets without writing custom integration code.
First, tell your agent if you need general forecasts or historical readings. You might start by listing stations to find the correct ID.
Next, provide the required parameters: a date range for history, a specific city code for forecasts, or a region name for regional analysis.
The MCP executes the query and returns structured data packages containing measurements, forecast details, or image metadata URLs.
Who is this actually for?
This MCP targets operations managers and analysts who can't afford guesswork. If you're the logistics planner constantly cross-referencing routes with predicted severe weather, or the researcher tracking long-term climate trends in Brazil, this is for you.
Needs to check real-time and forecasted conditions before dispatching teams. They use forecasts and regional data to adjust routes instantly.
Analyzes decades of historical patterns, using functions like get_meteorological_data_by_date to model climate change trends over specific regions or stations.
Requires hyper-local data. They check hourly station readings and forecast details to advise on optimal planting or harvesting windows.
What Changes When You Connect
You stop guessing which API endpoint to hit. Instead, you use list_stations first. This gives your agent a definitive list of all automatic and manual stations before requesting any data, guaranteeing accuracy.
The MCP handles time complexity. You don't write separate logic for hourly vs. daily data; whether you need the granular details from get_station_data_hourly or an overview from get_meteorological_data_by_date, the tool call is straightforward.
It links visual and numerical data. Beyond just numbers, you can use get_satellite_images to pull GOES-16 metadata URLs. This allows your agent to correlate visible cloud cover with measured atmospheric pressure changes.
Regional analysis becomes a single step. Instead of running queries for dozens of individual station IDs, calling get_meteorological_data_by_region aggregates all necessary data points for the entire area you care about.
Forecasts are comprehensive. You can get immediate predictions for an entire region using get_all_forecasts, or narrow it down precisely to a single city's predicted conditions with get_forecast_by_city.
See it in action
Planning for Disaster Relief
A field manager needs to know the expected weather across three different states over the next 72 hours. They use get_meteorological_data_by_region multiple times, followed by get_all_forecasts to build a complete, actionable picture for resource allocation.
Researching Historical Drought Patterns
A climate researcher needs to compare humidity levels across the Northeast region from 2018 versus 2023. They use get_meteorological_data_by_region for both years, allowing them to analyze historical variations in a structured way.
Optimizing Farming Schedules
A farm manager must determine the best day for planting based on rain predictions. They use get_forecast_by_city and then verify the expected conditions over the next week using get_station_data_daily from a local station.
Validating Equipment Needs
An engineer needs to know if an outdoor site can handle high winds. They check the latest GOES-16 data via get_satellite_images, then use get_station_data_hourly to find recent peak wind speed readings for validation.
The honest tradeoffs
Querying by general area name
Asking the agent: 'What's the weather in the Southeast?' This is too vague and usually fails because it needs specific codes or regions.
First, use list_stations to see available monitoring points. Then specify the data using a region call like get_meteorological_data_by_region, which uses official geographical groupings.
Assuming all stations are active
Sending a direct query for historical data without knowing if the station ID is correct or operational, leading to empty results.
Always run list_stations first. This verifies the exact type and ID of the station you intend to check before calling get_station_data_daily or get_station_data_hourly.
Missing temporal context
Just asking for 'weather data.' This doesn't tell the agent if you mean today, last week, or a forecast.
You must specify time. Use get_forecast_by_city for predictions, or provide a specific date to use get_meteorological_data_by_date for history.
When It Fits, When It Doesn't
Use this MCP if your decision hinges on official, granular Brazilian weather data (e.g., logistics planning, scientific modeling, high-stakes operations). You need access to historical trends or current station readings, not just general summaries.
Don't use it if you only need a generic global forecast—there are simpler tools for that. Also, don't try to correlate this data with non-meteorological inputs (like stock prices); this MCP is pure weather intelligence. If your goal requires integrating multiple data types (e.g., combining weather forecasts with traffic flow), treat the output of the get_forecast_by_city tool as a structured input for another agent or process.
Questions you might have
How do I find out which station IDs are valid in Brazil? (list_stations) +
Run list_stations first. This tool compiles a list of all automatic and manual stations across the country, letting you verify correct identifiers before attempting to pull data.
Can I get hourly temperature changes for a specific location? (get_station_data_hourly) +
Yes. Use get_station_data_hourly. You just need the station ID and the time window, and it returns granular readings like temperature and pressure hour-by-hour.
Is there a tool to get forecasts for all cities at once? (get_all_forecasts) +
Yes, get_all_forecasts retrieves weather predictions for every supported city. This is faster than calling get_forecast_by_city dozens of times.
What if I need to analyze data from a specific time period last year? (get_meteorological_data_by_date) +
Use get_meteorological_data_by_date. You must provide the station ID and the exact date you want measurements for. This keeps your historical analysis focused.
How does using `get_meteorological_data_by_region` help when I need to compare weather across several adjacent Brazilian areas? +
It gathers data for every station within the specified region. You give it a predefined group code, and it pulls all relevant measurements (temperature, humidity, pressure) for that area on your chosen date.
What kind of information do I get when I call `get_satellite_images`? +
You access the latest GOES-16 satellite data. This tool returns metadata and direct URLs, allowing you to view visual weather monitoring channels like infrared or visible spectrums.
If I only need daily averages instead of hourly readings, is `get_station_data_daily` the right tool? +
Yes, use get_station_data_daily. While get_station_data_hourly gives granular measurements, this function provides aggregated or averaged data for a specific station across an entire 24-hour period.
How do I get a precise forecast just for one city using the `get_forecast_by_city` tool? +
This tool focuses the retrieval on a single location. You supply the unique IBGE code or city identifier, and your agent immediately fetches the detailed weather forecast for that specific municipality.
How can I get the weather forecast for a specific city in Brazil? +
You can use the get_forecast_by_city tool by providing the city's IBGE code. The agent will return detailed forecast information including temperature and conditions.
Can I access real-time satellite imagery of Brazil? +
Yes! Use the get_satellite_images tool to retrieve the latest metadata and URLs for GOES-16 satellite images covering the Brazilian territory.
How do I find the ID of a meteorological station? +
Use the list_stations tool with the type 'T' for automatic or 'M' for manual stations. This will provide a list of all stations and their respective IDs.
We've already built the connector for INMET Weather. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 8 tools are live and waiting.
You're up and running in seconds.
Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.