Brasil.io MCP for AI. Query Structured Public Data Records From Brazil
Works with every AI agent you already use
…and any MCP-compatible client








Connect to your AI in seconds.
Brasil.io provides direct access to structured public data from Brazil's government records. Your AI agent connects and lets you query datasets—including COVID-19 stats, corporate filings, and socio-economic reports—using plain language.
This MCP turns massive amounts of raw Brazilian intelligence into usable facts for your report or research.
What your AI can do
List datasets
Lists all available public datasets hosted on Brasil.io so you can see what kind of data is accessible.
Query table data
Queries and retrieves actual records from a specified table using structured filters like state or city name.
Get table metadata
Retrieves the column names and data types for a specific table, letting you know exactly how to filter your query.
List every available dataset on the Brasil.io platform so you know exactly what records are out there.
Fetch detailed metadata for any specific dataset to confirm which fields, dates, or states are tracked.
Retrieve actual records from a specific table, applying complex filters like state codes or city names in one go.
Ask an AI about this
Waiting for input…
Brasil.io: 3 Data Query Tools
Use these three tools—list datasets, get metadata, and run queries—to pull specific records from Brazilian public tables via your AI client.
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 VinkiusList Datasets
Lists all available public datasets hosted on Brasil.io so you can see what kind of data is accessible.
Query Table Data
Queries and retrieves actual records from a specified table using structured filters...
Get Table Metadata
Retrieves the column names and data types for a specific table, letting you know...
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 Brasil.io, 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 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 connection provides 3 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Manually gathering public records takes forever.
Today, pulling facts from Brazilian government sources means navigating a dozen different portals. You download a PDF here, find a spreadsheet there, and then you have to cross-reference the dates and figures manually in Excel. It's copy-pasting data between five tabs just to build one chart.
With this MCP, your agent handles the heavy lifting. You simply tell it what you need—say, all confirmed cases for PR last quarter—and it pulls that structured data directly from Brasil.io into your workflow. The result is clean, reliable data without a single manual download or spreadsheet merge.
Brasil.io MCP: Structured Data Querying
The biggest time-saver is how you interact with the schema. You don't need to read dense technical documentation; running `get_table_metadata` tells you exactly what columns exist and if they are dates, strings, or numbers.
It moves your process from 'data assembly'—the tedious job of collecting files—to 'intelligence generation'. You get immediate access to the facts, structured right inside your chat window.
What your AI can actually do with this
Stop wrestling with confusing government transparency portals or manually downloading dozens of CSV files just to find one figure. This connection lets you talk directly to Brazil's public data records and get structured answers back. You can ask complex questions—like 'What were the confirmed cases in Curitiba, PR, during March 2023?'—and your agent handles the filtering and retrieval.
It’s like having a dedicated data scientist who only knows Brazilian municipal codes, right inside your workflow. This capability is available through Vinkius's catalog, letting you access this power from any MCP-compatible client. Whether you need to check historical salary figures or track regional health trends, this MCP makes the process conversational and reliable.
019e3870-25d9-7307-b2de-6d4689a4f3fc Here's how it actually works
The bottom line is that your AI client handles all the API calls; you just ask questions like talking to a human analyst.
First, subscribe to this MCP and provide your Brasil.io API token.
Next, ask your AI agent a question—for example, 'Show me the metadata for the COVID-19 table' or 'What were the deaths in PR last month?'.
The agent uses the tools to fetch and filter the records, presenting you with clean data directly in the chat.
Who is this actually for?
Anyone who needs verifiable, structured facts from Brazilian government sources. This is for data analysts tired of manual spreadsheet compilation, journalists chasing leads on corporate records, and academics needing clean socio-economic datasets.
You use this to query specific tables, like fetching all salary ranges by state to build a comparative report.
You run checks on public company records or historical datasets to verify claims for an article without leaving your writing environment.
You pull socio-economic time series data, using pagination support to gather full longitudinal studies for a paper.
What Changes When You Connect
Saves hours of manual work by eliminating the need to download and reconcile disparate CSV files from various government portals.
Use list_datasets first. You can immediately see if a dataset you need—like 'covid19' or 'salarios-magistrados'—is available before writing a single query.
The get_table_metadata tool lets you check the schema instantly. This means you know exactly what column name to filter on, avoiding guesswork when querying data.
query_table_data handles complex filtering (by state, city, date) using simple JSON input, making your requests precise and repeatable.
Pagination support ensures that even massive datasets are manageable; you can walk through millions of records without hitting a limit.
See it in action
Comparing regional health trends
A public health analyst needs to compare COVID-19 data between Rio de Janeiro and São Paulo. They ask the agent, which uses query_table_data, filtering by both states' codes and specifying date ranges. The result is a clean, comparative dataset ready for charting.
Verifying corporate history
A journalist investigating market shifts needs to know if a company filed specific documents in the last five years. They first use list_datasets to find the correct record type and then query it using query_table_data filtered by date range.
Academic research on demographics
A researcher is compiling a paper on salary disparities across Brazilian states. They use list_datasets to find the relevant payroll data, then run multiple calls with query_table_data, iterating through different states and using pagination to cover all available records.
Quick fact-checking for a report
A business developer needs the confirmed case count in Curitiba on a specific date. They simply ask their agent, which uses query_table_data with precise filters, and get the exact number without needing to navigate complex web forms.
The honest tradeoffs
Treating it like general search
Asking the agent, 'Tell me everything about Brazilian politics.' The system can't answer because it needs structured data.
Instead, use list_datasets to narrow your scope. If you need political spending records, first find the correct dataset, then use that tool for focused questions.
Forgetting the schema
Running a query and getting an empty result because you used 'State' instead of the required field name 'state'.
Always run get_table_metadata first. Check the exact column names—it’s crucial for successful data retrieval.
Ignoring large volume limits
Trying to pull every single record from a massive table in one go and timing out.
Use pagination support. Ask your agent to process records in batches or use filters (like state codes) to limit the dataset size before running query_table_data.
When It Fits, When It Doesn't
Use this MCP if your data needs are structured, factual, and tied to specific Brazilian public domains like health reports, company filings, or historical statistics. The process must involve: 1) Discovery (list_datasets), 2) Schema validation (get_table_metadata), and 3) Filtered retrieval (query_table_data). Don't use this if you need unstructured data—if your goal is analyzing an uploaded PDF or summarizing a legal document, that requires a different kind of tool. Also, remember it queries structured tables; it doesn't browse the live web for news articles.
Questions you might have
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.
How do I use `list_datasets` if I forget my Brasil.io API Token? +
You must provide your valid API token during initial setup. Without it, the agent can't authenticate or access any public datasets for listing or querying.
What is the best workflow when I want to analyze complex socio-economic data using this MCP? +
Start by running list_datasets to identify the right domain. Next, use get_table_metadata on that dataset to confirm all available columns before you attempt any queries.
What should I do if my JSON filter for `query_table_data` returns an error? +
The error usually means your filter syntax or data type is wrong. Run get_table_metadata first to check the exact column names and required formats.
Does `query_table_data` handle high volumes of records efficiently? +
Yes, it includes pagination support built in. This lets you pull massive datasets in controlled chunks, keeping your queries stable and efficient.
How do I verify if a specific dataset, like company records, is available? +
First, run list_datasets to see all hosted domains. If the topic appears, use get_table_metadata on that dataset's table name for specifics.
We've already built the connector for Brasil.io. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 3 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.