How to Use the IBGE Serviços de Dados MCP in LlamaIndex

Q: Can I use IBGE Serviços de Dados to filter search queries in LlamaIndex?

Yes, you can use the official classifications from getcnaeclasse as metadata filters. Your query engine matches these codes against your indexed documents. This ensures your search results align with official Brazilian economic categories.

Q: Does this server support asynchronous tool calls in LlamaIndex?

Yes, you can use totoollistasync to load the tools for async execution. This prevents your indexing pipelines from blocking while waiting for large aggregate tables to download.

Index official IBGE demographic data and economic classifications directly into your LlamaIndex vector stores.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect IBGE Serviços de Dados MCP to LlamaIndex

Create your Vinkius account to connect IBGE Serviços de Dados 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 Serviços de Dados with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live census tables for semantic search

`get_agregados` pulls structural statistical tables directly from the Brazilian government to feed your index. The tool outputs clean data blocks that LlamaIndex turns into document nodes, making raw demographic tables searchable via natural language queries. This eliminates outdated static files. Your agent queries the live API, indexes the fresh numbers, and updates your local vector database so your RAG pipeline always references current census metrics.

Build structured RAG with LlamaIndex MCP Server tools

`get_cnae_classe` provides official Brazilian economic classifications to ground your search queries in real business taxonomies. Your agent matches user queries against these classes, preventing the LLM from inventing fake industry codes during retrieval. You combine these live classifications with internal documents. The result is a unified query engine that knows both your private data and official Brazilian market standards.

Ground demographic analysis in historical metadata

`get_metadados` retrieves the structural details of IBGE's research cycles to verify the context of your data index. Your agent uses this tool to check when a survey was conducted, preventing outdated statistics from skewing your market models. This metadata acts as a verification layer. LlamaIndex reads the survey parameters directly, ensuring your synthesized answers explicitly state the data's collection year.

Setup guide

Set up IBGE Serviços de Dados 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 Serviços de Dados 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 Serviços de Dados tools.",
)
response = await agent.run("List recent IBGE Serviços de Dados 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 Serviços de Dados 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 Serviços de Dados MCP in LlamaIndex

You load the tools using the McpToolSpec and pass the output of `get_agregados` directly to your indexer. The framework parses the JSON response into document nodes. From there, you can vector-index the data for semantic search.

Yes, you can use the official classifications from `get_cnae_classe` as metadata filters. Your query engine matches these codes against your indexed documents. This ensures your search results align with official Brazilian economic categories.

The FunctionAgent evaluates the user's query and selects tools like `get_noticias` or `get_nome_geografico` based on their schemas. The MCP adapter handles the underlying communication automatically.

Yes, you can use `to_tool_list_async` to load the tools for async execution. This prevents your indexing pipelines from blocking while waiting for large aggregate tables to download.

Vinkius executes the MCP server in an ephemeral sandbox, meaning no Brazilian demographic, geographic, or economic data is cached or stored. The connection uses one-way SSL to pull directly from IBGE. Your proprietary query vectors remain strictly inside your local LlamaIndex instance.

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