How to Use the IBGE Economia — CNAE Activities MCP in LlamaIndex

Q: How does LlamaIndex prevent hallucinations when querying IBGE Economia — CNAE Activities?

The agent relies on getsubclassecnae to fetch cold, hard facts from the official Brazilian database instead of guessing. This direct lookup ensures every tax classification your LlamaIndex system outputs is legally accurate.

Q: Can I filter which IBGE Economia — CNAE Activities tools LlamaIndex can access?

Yes, you use the allowedtools parameter when initializing the MCP tool spec in LlamaIndex. This lets you restrict your agent to specific operations, like only allowing listsecoescnae while blocking deeper write-level tools.

Index Brazil's entire CNAE taxonomy into your LlamaIndex vector store to build tax-grounded RAG applications.

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 LlamaIndex

Create your Vinkius account to connect IBGE Economia — CNAE Activities to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build tax-grounded RAG indexes with LlamaIndex

The `list_secoes_cnae` tool retrieves the highest level of Brazil's economic structure so your LlamaIndex pipeline can index official tax categories. Your agent queries these sections to build a map of Brazilian industries, ensuring your RAG application grounds its answers in real regulatory data. By storing these outputs in a local vector store, you avoid hallucinations when users ask about tax liabilities. This local index matches user queries with the correct federal economic classifications.

Map nested economic divisions for semantic search

This MCP Server exposes `list_divisoes_cnae` to let your LlamaIndex agent fetch and index the 87 divisions of Brazilian business activities. Your pipeline parses these divisions to create structured metadata tags for your corporate documents, making compliance audits searchable by industry. When a user searches for specific compliance rules, the agent calls `list_classes_cnae` to narrow down the search space. Filtering by these exact classes keeps your search results highly relevant because they are tied directly to official IBGE classification codes.

Query granular subclasses via MCP Server tools

The `get_subclasse_cnae` tool pulls the exact 7-digit code details to resolve complex business classification queries in your LlamaIndex application. Your query engine triggers this tool dynamically when a user asks for specific tax exemptions linked to a particular business code. By integrating `list_subclasses_por_classe`, your agent walks down the taxonomic tree from broad classes to specific subclasses. This programmatic navigation guarantees that your RAG system never guesses a tax code, retrieving only verified IBGE data.

Setup guide

Set up IBGE Economia — CNAE Activities MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all IBGE Economia — CNAE Activities MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to IBGE Economia — CNAE Activities tools.",
)
response = await agent.run("List recent IBGE Economia — CNAE Activities data")

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 LlamaIndex

Yes, you use the McpToolSpec to load the IBGE Economia — CNAE Activities MCP Server into your LlamaIndex pipeline. The agent queries tools like `list_subclasses_por_classe` and writes the returned taxonomy data directly into your vector index for semantic search.

The agent relies on `get_subclasse_cnae` to fetch cold, hard facts from the official Brazilian database instead of guessing. This direct lookup ensures every tax classification your LlamaIndex system outputs is legally accurate.

Yes, you use the allowed_tools parameter when initializing the MCP tool spec in LlamaIndex. This lets you restrict your agent to specific operations, like only allowing `list_secoes_cnae` while blocking deeper write-level tools.

The MCP Server acts as a translator between your LlamaIndex agent and the IBGE API. Your agent uses the tools to navigate the five levels of the CNAE hierarchy, resolving complex business classifications step by step.

The server only handles public IBGE taxonomy metadata and CNAE classification codes, meaning no sensitive corporate financial records are transmitted. All traffic is isolated within your secure Vinkius runtime environment.

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