- DISCOVERY
- STRUCTURE
- PREP
- HUMAN
Short answer
How can I check Brasil.io table structures with AI?
Your AI uses the Brasil.io MCP to pull a list of available datasets and then fetches the specific metadata for any table you choose. This gives you a clear view of columns and data types before you start writing queries. You'll get a full breakdown of the workflow below.
The outcomes
What you get from schema inspection
The AI turns raw dataset lists into actionable structural maps.
DISCOVERY
Dataset inventory
The AI identifies which datasets are available in the Brasil.io repository. You get a clean list of available tables to work with.
STRUCTURE
Column and type maps
Your agent pulls the exact schema for a specific table. It identifies every column name and its corresponding data type.
PREP
Analysis readiness
With the schema in context, your AI can write accurate code or queries. You won't hit errors caused by typos in column names.
HUMAN
Manual verification
You decide which datasets are relevant to your research. The AI provides the technical map, but you make the final call on data selection.
The workflow
What your AI does when the request arrives.
The AI moves from broad discovery to specific technical details.
Find datasets
The AI scans the Brasil.io catalog to find the specific datasets you are looking for.
list_datasetsPull table details
Once a dataset is identified, the AI grabs the technical schema for the target table.
get_table_metadataMap data types
The AI parses the metadata to understand how to treat each column during analysis.
get_table_metadataConfirm structure
The agent presents a summary of the table layout so you can verify it's correct.
get_table_metadata
Try it
Copy these to start.
Use these prompts to begin your inspection.
Starting points
These are starting points. Swap out the dataset names for the specific ones you need to inspect.
Brasil.io Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_swehodurJBOgqLG2QWdYnp1gP3aOvkPJZvrwX5yQ/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Brasil.io capabilities are ready to use.
{
"mcpServers": {
"brasilio-mcp": {
"url": "https://edge.vinkius.com/vk_preview_swehodurJBOgqLG2QWdYnp1gP3aOvkPJZvrwX5yQ/mcp"
}
}
}List all available datasets in Brasil.io.
Get the metadata for the 'transparencia_gastos' table in Brasil.io.
What are the columns and data types in the Brasil.io 'municipios' dataset?
Show me the schema for the most recent dataset in Brasil.io.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Brasil.io once, then ask.
Connect the MCP to your preferred client in one click. Your credentials stay encrypted, and you can start asking questions immediately.
Connect Brasil.io to your AIFAQ
How this task behaves.
- 01
Can the AI download the actual data rows?
No. This specific task is for inspecting schemas and metadata, not for bulk downloading dataset contents.
- 02
Can the AI change or delete data in Brasil.io?
No. The tools only allow for reading metadata and listing datasets. The AI has no write access to the Brasil.io platform.
- 03
Does the AI know which columns are empty?
The AI can see the schema, but it doesn't perform a full scan of every row to check for null values unless you ask it to analyze a specific sample.
- 04
Can I use this with Claude?
Yes, as long as you are using an MCP-compatible client like Claude Desktop.
- 05
Do I need to provide my own API keys?
No. Vinkius manages the connection so you don't have to handle individual API credentials for the MCP.
More questions about Brasil.io? See everything the Brasil.io Connector can do
Connect Brasil.io to Claude, Cursor, ChatGPT & more
