Bring Brazil Data
to Pydantic AI
Learn how to connect Brasil.io to Pydantic AI and start using 3 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the Brasil.io MCP Server?
Connect to Brasil.io, the leading platform for accessible Brazilian public data, and empower your AI agent to analyze real-world datasets through natural conversation.
What you can do
- Dataset Discovery — List all available public datasets hosted on the platform, from health data to judicial salaries.
- Metadata Inspection — Fetch detailed schemas and metadata for specific tables to understand available columns and data types.
- Advanced Querying — Retrieve actual data records with powerful filtering capabilities (by state, city, date, etc.) using simple JSON filters.
- Pagination Support — Navigate through large datasets efficiently using built-in pagination controls.
How it works
- Subscribe to this server
- Enter your Brasil.io API Token
- Start querying Brazilian public intelligence from Claude, Cursor, or any MCP client
No more manual CSV downloads or wrestling with government transparency portals. Your AI acts as a data scientist specialized in Brazilian public records.
Who is this for?
- Data Analysts & Journalists — quickly extract facts and figures for reports without writing complex scrapers.
- Researchers — access historical and current socio-economic data for academic or market studies.
- Developers — integrate real Brazilian administrative data into your workflows or applications via your IDE.
Built-in capabilities (3)
Get metadata for a specific table in a dataset
io platform. Supports pagination. List available datasets on Brasil.io
You can pass arbitrary filters as a JSON string to filter by column names (e.g., {"state": "PR"}). Query data records from a specific table
Why Pydantic AI?
Pydantic AI validates every Brasil.io tool response against typed schemas, catching data inconsistencies at build time. Connect 3 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Brasil.io integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Brasil.io connection logic from agent behavior for testable, maintainable code
Brasil.io in Pydantic AI
Brasil.io and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Brasil.io to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Brasil.io in Pydantic AI
The Brasil.io MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 3 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Brasil.io for Pydantic AI
Every tool call from Pydantic AI to the Brasil.io MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
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 does Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your Brasil.io MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai
Explore More MCP Servers
View all →
Shutterstock
9 toolsEquip your AI agent to radically sift through Shutterstock's immense media vault. Search high-quality images, videos, audio, and audit editorial licenses directly from your prompt.
DNSimple
77 toolsManage domains, DNSSEC, and email forwarding via DNSimple — list accounts, control domains, and manage DS records directly from your AI agent.
Mastodon
35 toolsAutomate social interactions on the Fediverse — post statuses, manage follows, and track trending content directly from your AI agent.
Basin
12 toolsForm backend and lead capture automation — manage form submissions, filter spam, and trigger webhooks via AI.