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

Q: How does the IBGE Pesquisas — Brasil Cidades server pass survey IDs to my LangChain agents?

Your LangChain agent calls listpesquisas to grab the active survey index. It then feeds that specific ID directly into getindicadores in a single execution chain.

Q: How do I handle complex municipal queries with LangChain?

Use LangGraph to build a stateful loop. Your agent calls getrankingindicador to find outliers, then loops through getresultados to pull deep-dive metrics for those specific Brazilian cities.

Chain Brazilian municipal data into your LangChain workflows using this MCP Server to build automated policy pipelines.

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 LangChain

Create your Vinkius account to connect IBGE Pesquisas — Brasil Cidades to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multi-step data chains with LangChain

The `list_pesquisas` tool connects your LangChain agent directly to the official IBGE research directory. Your agent queries this directory first to find the exact survey ID, removing the need for you to hardcode API endpoints or look up IDs manually. Once the agent finds the right survey, it passes that ID directly to the next link in the chain. This setup lets your pipeline dynamically adapt based on whether you are analyzing agricultural output or local demographic shifts.

Rank and filter regional metrics dynamically

The `get_ranking_indicador` tool pulls sorted municipal metrics directly into your LangChain runnable chains. You configure the agent to fetch these rankings, evaluate which cities fall below a specific threshold, and immediately trigger follow-up actions. This direct integration means your agent doesn't just read data; it acts on it. The output of your ranking query feeds directly into your next prompt or external database write without manual intervention.

Analyze local indicators via LangSmith tracing

The `get_indicadores` tool pulls raw municipal data points directly into your observable LangChain execution paths. Every single data point fetched from the Brazilian census or health databases is logged, traced, and measured for latency within your LangSmith dashboard. You see exactly which municipal IDs were requested and how the agent parsed the payload. This visibility ensures you can debug complex multi-city comparisons without guessing what the model sent to the IBGE server.

Setup guide

Set up IBGE Pesquisas — Brasil Cidades MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes IBGE Pesquisas — Brasil Cidades tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "ibge-pesquisas-brasil-cidades-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent IBGE Pesquisas — Brasil Cidades transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Your LangChain agent calls `list_pesquisas` to grab the active survey index. It then feeds that specific ID directly into `get_indicadores` in a single execution chain.

Yes, every tool call is traced automatically if you use LangSmith. You will see the exact payload from `get_resultados` and how long the IBGE server took to respond.

Yes, you can combine this server with other tools using the MultiServerMCPClient. Your LangChain agent can query Brazilian city data and immediately cross-reference it with other services in your stack.

Use LangGraph to build a stateful loop. Your agent calls `get_ranking_indicador` to find outliers, then loops through `get_resultados` to pull deep-dive metrics for those specific Brazilian cities.

The server only handles public Brazilian statistical data, meaning no personal citizen records are ever processed. Vinkius runs the connection inside a secure, ephemeral V8 isolate that destroys itself after your LangChain session ends.

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