How to Use the Brasil.io MCP in LangChain

Q: Can LangChain execute multi-step analysis on Brasil.io tables?

Yes. The agent can first call listdatasets to find the correct data source, then use gettablemetadata to read the columns, and finally execute querytabledata to get the records.

Feed structured Brazilian public data directly into your LangChain reasoning loops.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Brasil.io MCP to LangChain

Create your Vinkius account to connect Brasil.io 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 Brasil.io with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map Brasil.io datasets in your LangChain loops

The `list_datasets` tool exposes every public dataset available on the Brasil.io platform straight to your active LangChain agent. This means your agent doesn't guess what datasets exist; it programmatically pulls the live inventory to decide where to route its next query. By using this MCP Server, your chains can dynamically branch based on what public data is actually available. If a user asks for COVID-19 stats, LangChain checks the live list before writing a single database query.

Inspect schemas dynamically inside chains

The `get_table_metadata` tool gives your LangChain agent the exact column structure and data types of any specific table. Your agent uses this metadata to build precise query filters without manual schema mapping. This setup prevents schema mismatch errors when running multi-step LangChain pipelines. Because the agent inspects the layout first, it avoids sending broken filters down the chain.

Pull live Brazilian public data into LangChain

The `query_table_data` tool retrieves actual records like company registrations or healthcare stats directly into your LangChain context. Your agent can filter these records on the fly using raw JSON parameters. You can trace these data pulls in LangSmith to monitor latency and raw token payloads. This MCP Server integration ensures your agent relies on verified government data rather than outdated training sets.

Setup guide

Set up Brasil.io 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 Brasil.io 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({
    "brasilio-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 Brasil.io 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 Brasil.io. 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 Brasil.io 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 Brasil.io MCP in LangChain

Install langchain-mcp-adapters and langgraph via pip, then initialize the MultiServerMCPClient pointing to your Vinkius endpoint. You then call client.get_tools() to pass them directly to your agent constructor.

Yes. The agent can first call list_datasets to find the correct data source, then use get_table_metadata to read the columns, and finally execute query_table_data to get the records.

You can manage rate limits by using LangChain's native token and run tracing in LangSmith. Since the server runs in a V8 sandbox on Vinkius, connection handling is managed, but you should structure your agent's loops to avoid redundant queries.

Yes. LangChain allows you to load tools from multiple MCP endpoints simultaneously, letting your agent cross-reference Brazilian public records with external vector databases.

Your queries for Brazilian company records and COVID-19 stats run through an isolated V8 sandbox on Vinkius. No raw data is cached or stored on our servers, ensuring your public data lookups remain completely private.

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