How to Use the Banco do Brasil MCP in CrewAI

Q: How can I make one CrewAI agent find Banco do Brasil bills and another one pay them?

Assign the getcreditcardinvoices tool to your first agent. Then, have it pass the payment details to a second agent that has access to the paybarcode tool. This role-based separation is a core strength of CrewAI.

Q: Can a CrewAI team monitor my Banco do Brasil account for specific Pix transactions?

Yes. Have an agent run the getpixhistory tool periodically. It can be tasked with looking for transactions that match certain criteria, like an amount over a threshold, and then trigger another agent to take action.

Q: Can my agents check the account balance before making a payment?

Definitely. Before your 'Payer' agent calls paybarcode, have a 'Validator' agent call getbalance. The crew can then proceed only if the balance is sufficient, preventing overdrafts.

Deploy a crew of autonomous agents to manage your Banco do Brasil account with CrewAI.

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 CrewAI

Create your Vinkius account to connect Banco do Brasil to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble a Financial Analyst Crew

Assign roles to your CrewAI agents. One agent, the 'Accountant,' can use `get_statement` and `get_pix_history` to pull raw data. A second 'Analyst' agent can then process that data to identify spending patterns or large transactions. A third 'Notifier' agent could take the Analyst's findings and send a summary report. Because CrewAI agents share memory, the Accountant's raw data is immediately available to the Analyst. This is how you build an autonomous financial monitoring system.

Build an Automated Payment Team

Create a crew to handle all your payables. A 'Scanner' agent can use `get_credit_card_invoices` and `get_scheduled_payments` to find upcoming bills. It then passes the details to a 'Payer' agent. The Payer agent uses `pay_barcode` or `pay_utility_bill` to execute the payments. You could even add a 'Treasurer' agent that first checks the account balance with `get_balance` and gives the go-ahead, creating a complete, automated workflow for your CrewAI.

An MCP Server for Autonomous Crews

Give your CrewAI agents the tools they need to interact with the real world. This MCP Server makes your Banco do Brasil account accessible through a simple set of tools, perfect for specialized agent roles. You can assign specific tools to specific agents. For example, only give the 'Payer' agent access to `create_pix`, while the 'Analyst' can only use read-only tools like `get_statement`. This is easy to configure using the `tool_filter` option when you set up your agents.

Setup guide

Set up Banco do Brasil MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Banco do Brasil tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Banco do Brasil Analyst",
    goal="Access and analyze Banco do Brasil data via MCP.",
    backstory="Expert analyst with direct Banco do Brasil access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Banco do Brasil transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Banco do Brasil Analyst",
        goal="Access and analyze Banco do Brasil data via MCP.",
        backstory="Expert analyst with direct Banco do Brasil access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Banco do Brasil transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Assign the `get_credit_card_invoices` tool to your first agent. Then, have it pass the payment details to a second agent that has access to the `pay_barcode` tool. This role-based separation is a core strength of CrewAI.

Yes. Have an agent run the `get_pix_history` tool periodically. It can be tasked with looking for transactions that match certain criteria, like an amount over a threshold, and then trigger another agent to take action.

The simplest way is to pass the Vinkius server URL directly into the `mcps` list when defining your Agent. For more control, use the `MCPServerHTTP` class from `crewai.mcp` to filter which tools each agent can access.

Definitely. Before your 'Payer' agent calls `pay_barcode`, have a 'Validator' agent call `get_balance`. The crew can then proceed only if the balance is sufficient, preventing overdrafts.

Each tool call your CrewAI agent makes is an independent, encrypted HTTPS request to the Vinkius MCP Server. The server operates on a zero-trust model, processing your statement or balance data within an ephemeral sandbox that is immediately destroyed. We don't log or store the contents of your financial data.

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