How to Use the Nubank MX MCP in LangChain

Q: How do I connect Nubank MX to LangChain?

Install langchain-mcp-adapters and use MultiServerMCPClient pointing to the Vinkius endpoint. You call client.gettools() and pass them directly to your agent constructor.

Q: Can a LangChain agent send a SPEI transfer via Nubank MX?

Yes. Your agent calls the createtransfer tool with the destination CLABE, amount, and recipient name. It only runs during Mexican banking hours as enforced by the bank.

Q: How does LangChain handle errors when calling Nubank MX tools?

LangChain raises standard tool execution exceptions if paybill or getaccountinfo fails. You can catch these errors in your chain or let your agent retry the call with corrected arguments.

Get your LangChain agents checking balances, paying bills, and sending SPEI transfers directly through Nubank MX.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Step Banking Chains with LangChain

This MCP Server exposes `create_transfer` and `pay_bill` directly to your LangChain runnables. Your agent executes complex financial workflows by chaining these tools, turning raw output from one step into input for the next without manual glue code. You track every step with LangSmith tracing to monitor latency and token costs. If a chain needs to check `get_account_balance` before triggering `pay_bill`, LangChain handles the state transitions and tool-calling loop automatically.

Real-Time Transaction Analysis and Audits

The `list_transactions` tool pulls your latest bank statements directly into your agent's context window. Your agent parses this raw transaction log to identify patterns or flag unexpected charges. You can feed this data straight into `get_spending_analytics` to compare monthly trends. It keeps your financial logs accurate without you having to log into the Nubank mobile app.

Credit and Reward Management

The `get_credit_card_statement` tool fetches your current open statement details directly within your LangChain pipeline. Your agent reads the balance, checks due dates, and cross-references your available credit. Running `list_rewards` lets you track your points alongside your spending. This lets your agent calculate your cash-back value or point balance in the same execution run.

Setup guide

Set up Nubank MX 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 Nubank MX 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({
    "nubank-mx-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 Nubank MX 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 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 LangChain

Install `langchain-mcp-adapters` and use `MultiServerMCPClient` pointing to the Vinkius endpoint. You call `client.get_tools()` and pass them directly to your agent constructor.

Yes. Your agent calls the `create_transfer` tool with the destination CLABE, amount, and recipient name. It only runs during Mexican banking hours as enforced by the bank.

LangChain raises standard tool execution exceptions if `pay_bill` or `get_account_info` fails. You can catch these errors in your chain or let your agent retry the call with corrected arguments.

The MCP Server is stateless by default. For persistent context across multiple financial queries, use `client.session()` in your LangChain setup to maintain the connection.

All API tokens and credentials stay inside the secure Vinkius MCP Server sandbox. Your raw account balances, SPEI transfer details, and credit card histories are never stored or used for model training.

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