How to Use the Nubank MX MCP in CrewAI

Q: How do I add the Nubank MX MCP Server to a CrewAI agent?

Install the package via pip install crewai "crewaitools". You can pass the Vinkius HTTP URL directly into your agent definition using the mcps list argument, exposing the financial tools to your crew.

Q: How do I restrict which Nubank MX MCP tools my CrewAI agents can use?

You can import MCPServerHTTP from crewai.mcp and use the toolfilter parameter. This lets you restrict access, allowing agents to use read-only tools like listtransactions while hiding transactional tools like createtransfer.

Deploy autonomous multi-agent teams to manage your Nubank MX banking operations using CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nubank MX MCP to CrewAI

Create your Vinkius account to connect Nubank MX 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 Nubank MX with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a financial analysis crew with CrewAI

CrewAI lets you deploy a team of specialized agents to manage your finances through this MCP Server. You can assign one agent to pull transaction histories using `list_transactions` and another to analyze spending trends via `get_spending_analytics`. These agents share memory and collaborate. The analyst agent compares your current statement from `get_credit_card_statement` with historic data to draft a detailed budget report, all without human intervention.

Autonomous billing and payment coordination

You can set up an autonomous operations crew to monitor your bills. One agent uses `list_bills` to track pending payments, while a separate coordinator agent determines if a payment is safe to execute based on `get_account_balance`. By defining a hierarchical execution path, the coordinator agent can delegate the actual execution of `pay_bill` to a transactional agent. This multi-agent structure ensures multiple layers of logical checks before any money leaves your account.

Specialized rewards monitoring MCP Server integration

Tracking points can be tedious. You can build a dedicated agent focused entirely on maximizing your benefits by calling `list_rewards` and comparing available perks against your recent credit card transactions from `list_credit_card_transactions`. This agent operates alongside your main financial crew, feeding its findings into the shared memory. It ensures your CrewAI team always has up-to-date context on your Nubank MX rewards profile.

Setup guide

Set up Nubank MX 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 Nubank MX tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Nubank MX 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="Nubank MX Analyst",
        goal="Access and analyze Nubank MX data via MCP.",
        backstory="Expert analyst with direct Nubank MX access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Nubank MX 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 Nubank Mexico. 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 Nubank MX 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 Nubank MX MCP in CrewAI

Install the package via `pip install crewai "crewai[tools]"`. You can pass the Vinkius HTTP URL directly into your agent definition using the `mcps` list argument, exposing the financial tools to your crew.

Yes. Because CrewAI utilizes shared memory, one agent can fetch data using `get_account_balance` while another agent processes that balance to make investment decisions.

You can import `MCPServerHTTP` from `crewai.mcp` and use the `tool_filter` parameter. This lets you restrict access, allowing agents to use read-only tools like `list_transactions` while hiding transactional tools like `create_transfer`.

Yes. The setup supports standard stdio, SSE, and Streamable HTTP transports, making it highly flexible for local python scripts or containerized crew deployments.

Your raw transaction histories, credit card details, and rewards data are handled in Vinkius's secure, ephemeral V8 isolates. The MCP setup ensures no banking credentials or sensitive statements are stored within the CrewAI framework or shared with external LLM providers directly.

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