How to Use the IBGE Economia — CNAE Activities MCP in Google ADK

Q: Can I restrict which tools from the IBGE Economia — CNAE Activities MCP server are exposed to google-adk?

Yes, you can use the optional toolnames filter when initializing your McpToolset. This allows you to restrict the agent to only use specific tools like getsubclassecnae while hiding the broader listing tools.

Run enterprise classification agents on Google ADK using real-time IBGE CNAE taxonomy tools via this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect IBGE Economia — CNAE Activities MCP to Google ADK

Create your Vinkius account to connect IBGE Economia — CNAE Activities to Google ADK 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 IBGE Economia — CNAE Activities with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect BigQuery data to Google ADK tools

Querying `list_secoes_cnae` and `list_divisoes_cnae` from your Google ADK pipelines lets Gemini-powered agents map raw BigQuery merchant data to official sectors. Enterprise data engines running on Google Cloud often store raw, unclassified merchant descriptions in BigQuery. By integrating this MCP Server, your agents can read these descriptions and assign correct codes instantly. This setup lets you run massive classification pipelines directly from your data warehouse. The agent queries `list_classes_cnae` to find the correct division, then updates your tables with validated codes.

Long-context reasoning over 1,332 activity codes

Calling `list_divisoes_cnae` and `list_subclasses_por_classe` lets your agent analyze deep hierarchical structures within a single long-context window. Gemini models can handle massive context windows, making them perfect for analyzing complex corporate structures. Your agent can pull a complete list of divisions and analyze it alongside a company's financial statements to determine its primary tax classification. Instead of making dozens of small API calls, the agent can look at the entire subclass structure at once. It compares the official descriptions against the company's actual operations to find the perfect compliance match.

Deep subclass lookups with Gemini agents

Invoking `get_subclasse_cnae` retrieves the precise fiscal metadata needed to verify if an ambiguous business qualifies for municipal tax incentives. When your pipeline encounters an ambiguous business model, your Google ADK agent can use this tool to retrieve the exact fiscal definition. Because the framework supports both Stdio and HTTP transports, you can host this server on Cloud Run or run it locally during development. This flexibility ensures your enterprise pipelines remain stable regardless of your deployment architecture.

Setup guide

Set up IBGE Economia — CNAE Activities MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with IBGE Economia — CNAE Activities tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="IBGE Economia — CNAE Activities_agent",
    model="gemini-2.0-flash",
    instruction="You have access to IBGE Economia — CNAE Activities tools via MCP.",
    tools=mcp_tools,
)

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 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.

Connect IBGE Economia — CNAE Activities 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 IBGE Economia — CNAE Activities MCP in Google ADK

You run pip install google-adk and initialize the toolset using McpToolset with your server's HTTP parameters. Once initialized, pass the toolset directly to your LlmAgent instance in the tools list.

Yes, you can use the optional tool_names filter when initializing your McpToolset. This allows you to restrict the agent to only use specific tools like `get_subclasse_cnae` while hiding the broader listing tools.

Yes, the framework natively supports both transport protocols. You can choose the transport method that best fits your enterprise architecture, whether you are running local CLI tests or deploying production cloud functions.

Gemini's large context window allows it to process the hierarchical outputs of tools like `list_secoes_cnae` and `list_subclasses_por_classe` simultaneously. The model can trace a business activity from the top-level section down to the specific subclass in a single reasoning step.

Yes, because all communication with the IBGE taxonomy endpoints is handled through a secure, isolated V8 sandbox on Vinkius. No business data or raw CNAE tax classification data is stored or logged, ensuring your enterprise remains fully compliant with LGPD regulations.

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