How to Use the BrasilAPI MCP in LangChain

Q: Can I monitor the latency of BrasilAPI calls inside LangChain?

Yes, every call to tools like getcnpjdetails is automatically tracked if you have LangSmith enabled. You will see exact execution times and payload sizes for every Brazilian corporate registry lookup.

Run multi-step LangChain runs that query CNPJs, verify CEP addresses, and pull live Brazilian bank data in a single chain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BrasilAPI MCP to LangChain

Create your Vinkius account to connect BrasilAPI 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 BrasilAPI with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain CNPJ audits directly into LangChain agent runs

Let your LangChain agent pull official corporate records using `get_cnpj_details` and feed that raw text straight into your downstream processing chains. You don't have to manually parse Brazilian tax registration data because the agent handles the schema mapping on the fly. LangSmith tracks every step of these MCP Server calls, showing you the exact token usage and latency when fetching business structures. If a CNPJ query fails or returns unexpected data, your chain can catch the exception and try an alternative path without dropping the execution.

Resolve Brazilian addresses with CEP routing

Feed postal codes into `get_cep_details` to automatically resolve street names, neighborhoods, and states inside your conversational chains using this MCP Server. This tool lets your agent correct typos in user-submitted addresses before writing them to your database. Because LangChain handles state through graph structures, you can pass the resolved city data into `list_brazilian_states` to cross-reference regional tax rules. Your agent makes these decisions sequentially, using the output of the address lookup to decide which state policy to pull next.

Track vehicle values through FIPE lookup sequences

Build financial workflows that fetch current car valuations with `get_fipe_vehicle_price` and pipe those numbers into your custom calculation nodes. Your agent reads the vehicle's market value, compares it against historic trends, and formats the output for client reports. Combining this tool with `list_brazilian_banks` lets your chain build a complete auto-financing recommendation based on active institutions. The agent handles the multi-step logic, querying the vehicle price first, then searching for compatible lenders in the same run.

Setup guide

Set up BrasilAPI 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 BrasilAPI 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({
    "brasilapi-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 BrasilAPI 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 BrasilAPI. 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 BrasilAPI 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 BrasilAPI MCP in LangChain

Install the adapter package and use the multi-server client to point to the Vinkius endpoint. Call the tool getter method and pass that list directly to your agent constructor to start querying Brazilian data.

Yes, every call to tools like `get_cnpj_details` is automatically tracked if you have LangSmith enabled. You will see exact execution times and payload sizes for every Brazilian corporate registry lookup.

Your agent can use standard ReAct logic to catch the error and retry or ask the user for clarification. If `get_cep_details` returns a 404 for a bad postal code, the chain won't crash; it just handles the failure gracefully.

You can load this MCP Server alongside database tools or search tools in the same LangChain agent. The agent decides when to pull bank registries or vehicle prices and when to write those details to your internal storage.

Your queries for specific postal codes and corporate tax IDs run in an isolated Vinkius sandbox that doesn't persist your payload history. No raw Brazilian business records or address lookups are stored on the host after the tool execution completes.

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