Brasil.io MCP. Access Brazilian public stats without manual downloads.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Brasil.io lets your AI agent query structured Brazilian public data. You can ask for anything from historical COVID-19 stats and judicial salary records to socio-economic datasets, all without downloading messy CSV files.
Just talk to your agent.
What your AI agents can do
Get table metadata
Retrieves the column names and structure (schema) for a specific table within any dataset.
List datasets
Lists all available public datasets on Brasil.io, supporting navigation through large result sets.
Query table data
Queries and pulls actual data records from a specific table using custom JSON filters (e.g., filter by state or date).
List every public dataset hosted on Brasil.io so you know exactly what data is accessible.
Get the column names, types, and structure for any specific table within a dataset before querying it.
Query data to pull targeted record sets by applying filters like state name, city, or date range.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
Brasil.io: 3 Tools for Data Querying
These tools allow you to discover available datasets, verify data structure, and pull specific record sets from Brazilian public records using structured queries.
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 Brasil.io on Vinkius019e386fget table metadata
Retrieves the column names and structure (schema) for a specific table within any dataset.
019e386flist datasets
Lists all available public datasets on Brasil.io, supporting navigation through large result sets.
019e386fquery table data
Queries and pulls actual data records from a specific table using custom JSON filters (e.g., filter by state or date).
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 Brasil.io, then connect any of our 4,800+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,800+ 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 Brasil.io. 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.
Sifting through government transparency portals is a nightmare.
Today, finding key facts means navigating dozens of clunky websites. You click on data sets, download massive ZIP files, and then spend hours manually opening CSVs in Excel, just to figure out if the column you need is even labeled correctly or if it's duplicated.
With this MCP, your AI agent handles all that overhead. Instead of downloading a file, you simply ask for the data—for example, 'Give me confirmed cases by state and city for Q1 2023.' You get clean JSON output instantly.
Querying Brazilian Public Data with Brasil.io
You skip the manual download, the Excel cleanup, and the cross-referencing of multiple files. The agent manages finding the right dataset, inspecting its schema using `get_table_metadata`, and executing a precise query.
The result is immediate, structured data delivered directly into your workflow. Nothing else compares to this speed.
What you can do with this MCP connector
Need real-world facts about Brazil? This MCP connects your AI client directly to Brasil.io, a massive repository of structured public data. You stop wrestling with government transparency portals and start asking questions. Your agent acts like a specialized data scientist for Brazilian records, letting you discover what datasets exist, check their exact column structures, and pull filtered data using simple natural language prompts.
The power comes from combining sources. If your project requires comparing local health stats with corporate registry information, Vinkius's ability to chain multiple MCPs together lets your agent build that complex automation across different services, all while keeping every transaction secured through a zero-trust proxy. This means the data always flows securely in transit—your keys never sit on disk.
You get clean, actionable intelligence without needing specialized ETL processes or manual scraping.
019e3870-25d9-7307-b2de-6d4689a4f3fc 
How Brasil.io MCP Works
- 1 First, subscribe to this MCP and provide your Brasil.io API Token.
- 2 Use the agent to list available datasets so you can scope out the data needed for your project.
- 3 Finally, tell the agent which table you need details on; it retrieves the schema, then executes a targeted query with filters.
The bottom line is: your AI client treats the entire Brazilian public dataset like one giant, searchable database.
Who Is Brasil.io MCP For?
Journalists and analysts who get stuck on complex government data portals. Or researchers compiling large historical datasets that require specific filtering.
Needs to quickly pull specific, dated records (like COVID-19 stats for a single city) without waiting on a reporter or manual data dump.
Requires access to large socio-economic datasets and needs the ability to filter by multiple variables, like state and industry sector, efficiently.
Wants to build repeatable workflows that combine Brazilian data with other internal company metrics for comparison reports.
What Changes When You Connect
- You don't need to write complex scrapers; simply ask your agent for the data you want, letting it handle the connection and filtering logic using
query_table_data. - Before pulling any records, check the schema first. Using
get_table_metadataconfirms exactly what columns are available so you don't guess at data types or names. - The system handles large volumes of data efficiently with built-in pagination controls for every call to
list_datasets, meaning you can process huge datasets without hitting limits. - It eliminates the need for manual CSV downloads. You get structured, clean JSON output directly into your workflow, ready for analysis.
- Because this MCP runs on Vinkius, if you combine it with a Messaging MCP and an Analytics MCP, your agent can automate alerts based on data findings across platforms.
Real-World Use Cases
Analyzing regional health trends
A journalist needs to compare COVID-19 reports for two specific states over the last six months. They first use list_datasets to find the correct source, then get_table_metadata on the 'caso' table, and finally use query_table_data with filters for both states and date ranges.
Building a compliance report
A researcher needs to pull records of company incorporation dates across several years. They run list_datasets to find the corporate registry, then execute multiple targeted queries using query_table_data against different table schemas.
Tracking salary changes
A policy analyst needs current judicial salaries for a specific state. They use list_datasets, check the schema with get_table_metadata, and then run a targeted query to pull only the relevant records, ensuring accuracy.
The Tradeoffs
Querying without knowing the dataset name
The user just asks for 'COVID stats' but doesn't know which specific dataset table to query against.
→
Always start by asking your agent to run list_datasets first. This tells you all available data sources before attempting a targeted query using query_table_data.
Assuming column names
The user assumes the dataset has a column called 'state' but it might be named something else, causing the query to fail.
→
Use get_table_metadata on the table you plan to use. This shows the exact schema and confirms the correct spelling of every available column.
Overlooking pagination
The user asks for 'all data' but only gets the first 10,000 records because they forget that large datasets need to be paginated.
→ When querying or listing, remember built-in pagination support. The agent can handle this complexity when you ask it to pull full results.
When It Fits, When It Doesn't
Use this MCP if your core requirement is accessing deep, structured public data from Brazilian government and commercial sources. You need the precision of knowing the schema before executing a query. Don't use this if you just need general trend spotting or qualitative analysis; those are better handled by natural language models without external tool calls. If you only have one simple question, sometimes query_table_data is enough, but for any serious work involving multiple variables, always follow the sequence: 1) discover scope (list_datasets), 2) validate structure (get_table_metadata), and 3) run the query (query_table_data).
Common Questions About Brasil.io MCP
How can I filter data for a specific state or city? +
Use the query_table_data tool and provide a JSON string in the filters parameter, such as {"state": "SP", "city": "São Paulo"}. The agent will apply these filters to the Brasil.io API request.
How do I find out what columns are available in a dataset? +
First, use list_datasets to find the slug of the dataset. Then, use get_table_metadata with the dataset and table slugs to see the full list of available fields and their descriptions.
Can I navigate through large amounts of data? +
Yes. Both list_datasets and query_table_data support page and page_size parameters, allowing you to iterate through results without overloading the response.
Before I run `list_datasets`, what credentials do I need to authenticate my agent? +
You must provide a valid Brasil.io API Token during setup. Your AI client passes this key through Vinkius's zero-trust proxy, meaning your private keys are never stored on disk.
If I need to know the precise schema or data types, is `get_table_metadata` better than just looking at a dataset name? +
Yes. While listing datasets gives you names, calling get_table_metadata provides detailed schemas for any specific table, telling you exactly what columns and data types are available.
When using `query_table_data`, how should I structure complex filters (like filtering by date AND state)? +
You must pass all filter criteria as a single JSON string. The format requires specifying the column name and the required value, for example: {"state": "PR", "date": "2023-12-31"}.
What happens if I try to query too much data or exceed usage limits with `query_table_data`? +
Vinkius includes a financial circuit breaker and built-in throttling controls. You set an explicit budget, and the agent cannot execute calls that would overspend your defined limit.
Does `list_datasets` account for pagination if there are many available data sources? +
Yes. The tool supports built-in pagination controls, allowing your AI client to navigate and discover every dataset listed on the platform efficiently without hitting hard limits.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.