How to Use the BrasilAPI MCP in Pydantic AI

Get type-safe BrasilAPI data in Pydantic AI with runtime validation for every institutional lookup.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BrasilAPI MCP to Pydantic AI

Create your Vinkius account to connect BrasilAPI to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup BrasilAPI with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe corporate and location lookups

Invoke `get_cnpj_details` or `get_cep_details` and let Pydantic AI validate the shape of the response. If the API structure shifts, your agent catches it immediately. This keeps your agent logic free from silent data corruption. You get structured, verified objects every time.

Financial and automotive data modeling

Use `get_fipe_vehicle_price` to populate your typed data models. It ensures your valuation logic always receives the expected numeric types. Call `list_brazilian_banks` to map institutional names into your strongly typed enums. Your agent works with data that matches your internal schema.

Operational logic with an MCP Server

Integrate `list_brazilian_states` to restrict your agent's geographic scope using typed results. It prevents logic errors based on invalid region codes. This MCP Server acts as a reliable source of truth. Your agent consumes the output as a validated Python object.

Setup guide

Set up BrasilAPI MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "brasilapi-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to BrasilAPI tools.",
)

result = await agent.run("List recent BrasilAPI transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by BrasilAPI. 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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect BrasilAPI now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about BrasilAPI MCP in Pydantic AI

The framework automatically checks the API output against your Pydantic models. It throws an error if the data doesn't match, preventing bad state.

Yes, the server runs externally and connects via HTTP or SSE. This keeps your agent project lightweight and decoupled.

It is. Because Pydantic AI enforces schemas at runtime, your agent remains stable even if external data sources return unexpected fields.

This server touches public institutional records like state UFs and bank codes. We handle this data through secure, transient memory buffers.

All six tools are fully supported. You map them into your agent toolset and enjoy full type safety for every response.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript

Mastra AI sdk-typescript

Start using the BrasilAPI MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Get started