How to Use the Banco do Brasil MCP in LangChain

Q: Can I monitor Banco do Brasil transaction history using LangChain chains?

Yes, you can chain getpixhistory with other LangChain tools to analyze your financial flows. Every API call is fully visible in LangSmith so you can track latencies and inputs.

Q: How do I pull banking statements?

Use getstatement with start and end dates formatted as YYYY-MM-DD. The returned transaction list can be piped into your analytical chains or formatted into CSVs.

Run multi-step banking workflows with LangChain and your Banco do Brasil accounts.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Banco do Brasil MCP to LangChain

Create your Vinkius account to connect Banco do Brasil 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 Banco do Brasil with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run direct Pix payments through LangChain

`create_pix` lets your LangChain agent execute instant Pix transfers using a specific key over this MCP connection. The agent verifies the recipient details first, then runs the payment without manual intervention. If the transfer fails, the agent reads `get_pix_history` to inspect past transactions and debug the state. It handles the retry logic programmatically, chaining the output of one step directly into the next.

Monitor balances using this Banco do Brasil MCP Server

`get_balance` retrieves your current checking account balance and credit limits directly into your LangChain run. Your agent feeds this number into decision nodes before authorizing any outgoing payments. To keep a clean ledger, `get_statement` pulls transactions for specific date ranges. LangSmith traces these tool calls, giving you full visibility into exactly when and why your agent checked your banking data.

Pay utility bills and boletos automatically

`pay_barcode` and `pay_utility_bill` enable your agent to settle outstanding Brazilian slips. The agent parses the invoice barcode from an email or document, then executes the payment directly. You can combine this with `get_scheduled_payments` to check for duplicate scheduled transactions before paying. This prevents double-paying bills and keeps your cash flow predictable.

Setup guide

Set up Banco do Brasil 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 Banco do Brasil 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({
    "banco-do-brasil-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 Banco do Brasil 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 Banco do Brasil. 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 Banco do Brasil 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 Banco do Brasil MCP in LangChain

Vinkius manages the authentication handshake securely behind a single endpoint. You just pass this URL to the LangChain MultiServerMCPClient and your agent gets immediate access to the banking tools.

Yes, you can chain get_pix_history with other LangChain tools to analyze your financial flows. Every API call is fully visible in LangSmith so you can track latencies and inputs.

You control the agent's boundaries by defining strict prompt templates and validation steps in your graph. The agent only triggers create_pix or pay_barcode when your specific chain conditions are met.

Use get_statement with start and end dates formatted as YYYY-MM-DD. The returned transaction list can be piped into your analytical chains or formatted into CSVs.

All communication runs through a zero-trust V8 sandbox environment on Vinkius. Your financial statements, balances, and Pix history are processed ephemerally and never stored on our servers.

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