How to Use the IBGE Pesquisas — Brasil Cidades MCP in LlamaIndex

Q: How does the IBGE Pesquisas — Brasil Cidades tool integration prevent hallucinations in LlamaIndex?

It feeds raw data from getresultados directly into the context window of your LlamaIndex agent. This forces the model to synthesize answers using actual Brazilian municipal records instead of training data.

Q: Can I index the output of IBGE Pesquisas — Brasil Cidades directly into a vector store using LlamaIndex?

Yes, you can convert the JSON output of getindicadores into LlamaIndex Document objects. This lets you run semantic searches over structured Brazilian city metrics alongside your text files.

Q: How do I filter which IBGE Pesquisas — Brasil Cidades tools my LlamaIndex agent can access?

Use the allowedtools filter when initializing your McpToolSpec. You can restrict the agent to only use getrankingindicador if you want to limit its actions to regional benchmarking.

Index raw Brazilian municipal data directly into your LlamaIndex vector stores for grounded, hallucination-free RAG.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect IBGE Pesquisas — Brasil Cidades MCP to LlamaIndex

Create your Vinkius account to connect IBGE Pesquisas — Brasil Cidades 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 Pesquisas — Brasil Cidades with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn live IBGE data into searchable LlamaIndex nodes

The `get_resultados` tool retrieves specific municipal research data and immediately feeds it into your LlamaIndex document pipeline. Instead of relying on static PDFs, your RAG system indexes live statistical tables directly from Brazilian cities. This live indexing prevents your agent from hallucinating local economic figures. The retrieved metrics become part of your vector store, allowing semantic search queries to return exact, verified numbers.

Ground your agent queries in real Brazilian rankings

The `get_ranking_indicador` tool provides structured municipal rankings that LlamaIndex uses to ground its synthesis steps. Your agent queries the tool, gets the sorted list of cities, and references those exact positions in its final response. By using the McpToolSpec, these ranking arrays are treated as structured data sources. This ensures your synthesis engine doesn't invent municipal hierarchies or scramble regional data during retrieval.

Build an active MCP Server knowledge base of municipal surveys

The `list_pesquisas` tool pulls the complete catalog of active Brazilian research programs directly into your LlamaIndex query engine. Your system indexes this metadata so users can ask natural language questions about which surveys are available. The engine maps these user queries to the correct survey IDs automatically. From there, it triggers `get_indicadores` to fetch the actual metrics, creating a fully automated data-discovery loop.

Setup guide

Set up IBGE Pesquisas — Brasil Cidades 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 Pesquisas — Brasil Cidades 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 Pesquisas — Brasil Cidades tools.",
)
response = await agent.run("List recent IBGE Pesquisas — Brasil Cidades 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 Pesquisas — Brasil Cidades 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 Pesquisas — Brasil Cidades MCP in LlamaIndex

It feeds raw data from `get_resultados` directly into the context window of your LlamaIndex agent. This forces the model to synthesize answers using actual Brazilian municipal records instead of training data.

Yes, you can convert the JSON output of `get_indicadores` into LlamaIndex Document objects. This lets you run semantic searches over structured Brazilian city metrics alongside your text files.

Use the allowed_tools filter when initializing your McpToolSpec. You can restrict the agent to only use `get_ranking_indicador` if you want to limit its actions to regional benchmarking.

Yes, you can use the asynchronous tool list method to fetch municipal data without blocking your main application loop. This keeps your RAG pipeline fast even when querying multiple Brazilian cities.

This server only touches public, non-identifiable Brazilian municipal statistics and survey metadata. All requests are routed through a zero-trust sandbox that keeps your query parameters and API keys isolated from other users.

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