4,500+ servers built on MCP Fusion
Vinkius
IBGE Economia — CNAE Activities logo
Vinkius
Pydantic AI logo

How to Use the IBGE Economia — CNAE Activities MCP in Pydantic AI

Ensure type-safe Brazilian economic classification in Pydantic AI using runtime-validated CNAE tools via this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

IBGE Economia — CNAE Activities MCP on Cursor AI Code Editor MCP Client IBGE Economia — CNAE Activities MCP on Claude Desktop App MCP Integration IBGE Economia — CNAE Activities MCP on OpenAI Agents SDK MCP Compatible IBGE Economia — CNAE Activities MCP on Visual Studio Code MCP Extension Client IBGE Economia — CNAE Activities MCP on GitHub Copilot AI Agent MCP Integration IBGE Economia — CNAE Activities MCP on Google Gemini AI MCP Integration IBGE Economia — CNAE Activities MCP on Lovable AI Development MCP Client IBGE Economia — CNAE Activities MCP on Mistral AI Agents MCP Compatible IBGE Economia — CNAE Activities MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
Pydantic AI

Connect IBGE Economia — CNAE Activities MCP to Pydantic AI

Create your Vinkius account to connect IBGE Economia — CNAE Activities 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

Type-safe tax mapping with Pydantic AI

Validating payloads from `get_subclasse_cnae` and `list_secoes_cnae` at runtime protects your automated tax systems from silent classification failures. By using this MCP Server with Pydantic AI, every payload returned from the tools is validated against strict schemas at runtime. If the external taxonomy API returns anomalous data, the system raises a validation error immediately. This strictness ensures your database is never corrupted with malformed economic codes. Your agent can query the taxonomy knowing that the returned structure matches your internal type hints exactly.

Model-agnostic taxonomy navigation

Executing `list_divisoes_cnae` across different LLMs keeps your taxonomy navigation consistent and model-agnostic. Whether you use OpenAI, Anthropic, or local models, Pydantic AI keeps your tool execution consistent. Your agent can use this tool to explore the 87 divisions of the Brazilian economy, regardless of the underlying LLM's raw capabilities. The framework translates the server's schemas into structured tools that any compatible model can invoke. This allows you to swap models as pricing or performance requirements change, without rewriting your classification logic.

Validate complex corporate structures

Running `list_subclasses_por_classe` and `list_classes_cnae` ensures your agent never misses a valid economic code during complex corporate registrations. Mapping multi-activity corporations requires precise data. Your agent can call these tools to fetch all subclasses under a specific parent class, ensuring no valid economic code is missed. By using these targeted lookups, your agent can narrow down the search space step-by-step. The framework's dependency injection system ensures that your database connections and API tokens are managed safely throughout the entire taxonomy lookup.

Setup guide

Set up IBGE Economia — CNAE Activities MCP in Pydantic AI

Prerequisites

  • Python 3.10+ installed
  • pydantic-ai-slim[fastmcp] package
  • Active Vinkius subscription with a valid endpoint token
  1. 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. 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. 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": {
        "ibge-economia-cnae-activities-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent IBGE Economia — CNAE Activities transactions")
print(result.output)

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

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 IBGE Economia — CNAE Activities MCP in Pydantic AI

First, run pip install "pydantic-ai-slim[mcp]" to get the required dependencies. Then, instantiate MCPToolset with your server's HTTP endpoint and pass it to your Agent's toolsets list.
Yes, the framework supports both Streamable HTTP and SSE transports for connecting to external servers. This allows you to maintain persistent, lightweight connections to the taxonomy tools in production.
The framework will raise a validation error at runtime, preventing the agent from passing corrupt data to your backend. This guarantees that only perfectly structured CNAE codes are written to your database.
No, MCPServerHTTP is deprecated in favor of the unified MCPToolset class. You should use the unified toolset class to handle all external server connections.
The server runs inside an ephemeral, zero-trust V8 isolate sandbox that processes your Brazilian economic taxonomy codes entirely in memory. No queries or corporate tax IDs are persisted on the host, maintaining strict data isolation for your automated compliance pipelines.

Start using the IBGE Economia — CNAE Activities MCP today

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

Built & Managed by Vinkius 30s setup 5 tools

We've already built the connector for IBGE Economia — CNAE Activities. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 5 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

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.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.