How to Use the Mercado Pago MCP in LangChain

Q: How do I install the Mercado Pago MCP Server for LangChain?

Run pip install langchain-mcp-adapters langgraph to set up the environment. Next, initialize the MultiServerMCPClient with the Vinkius endpoint to expose the 12 payment tools to your agent.

Q: Can my LangChain agent handle Pix refunds through Mercado Pago?

Yes, your agent can call refundpayment when a refund request is triggered. If the agent omits the amount argument, the tool executes a full refund automatically.

Q: How does LangChain track Mercado Pago tool execution?

You use LangSmith to monitor every API call made by createpayment or createpreference. This gives you full visibility into latency and token usage for each transaction.

Q: Can I use multiple payment methods in a single LangChain run?

Yes, your agent uses listpaymentmethods to check active options in Brazil before choosing between createpayment or createpixpayment. The agent decides the best path based on user input.

Run Mercado Pago transactions and manage customer records directly within your LangChain reasoning chains.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mercado Pago MCP to LangChain

Create your Vinkius account to connect Mercado Pago 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 Mercado Pago with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Pix payments in LangChain chains

The `create_pix_payment` tool generates instant QR codes and copy-paste keys for Brazilian customers directly inside your LangChain run loop. Your agent grabs the payment payload and passes it to the next step in your chain without manual data mapping. This setup lets you build multi-step payment flows where LangSmith tracks every tool input and output. You see exactly when the QR code was generated and how your agent handled the response on this MCP Server.

Reconcile transactions via ReAct loops

The `search_payments` tool queries your transaction history using filters to find specific records. Your LangChain agent analyzes these results to match paid invoices with internal database records. If a customer disputes a charge, the agent uses `get_payment` to check the status and triggers `refund_payment` for the exact amount. This entire chain runs autonomously while keeping a clear execution trace.

Manage customer profiles across servers

The `create_customer` tool registers new buyers in your Mercado Pago account during checkout. Your agent coordinates this tool with `create_card` to save payment instruments for future transactions. This MCP Server coordinates with other APIs in your MultiServerMCPClient setup. You can pull a user profile from a database and instantly register them in Brazil's largest payment network.

Setup guide

Set up Mercado Pago 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 Mercado Pago 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({
    "mercado-pago-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 Mercado Pago 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 Mercado Pago. 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 Mercado Pago 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 Mercado Pago MCP in LangChain

Run `pip install langchain-mcp-adapters langgraph` to set up the environment. Next, initialize the MultiServerMCPClient with the Vinkius endpoint to expose the 12 payment tools to your agent.

Yes, your agent can call `refund_payment` when a refund request is triggered. If the agent omits the amount argument, the tool executes a full refund automatically.

You use LangSmith to monitor every API call made by `create_payment` or `create_preference`. This gives you full visibility into latency and token usage for each transaction.

Yes, your agent uses `list_payment_methods` to check active options in Brazil before choosing between `create_payment` or `create_pix_payment`. The agent decides the best path based on user input.

All credit card tokens and customer records are processed inside a secure V8 sandbox. The server never stores your API keys or raw transaction data, keeping your financial operations isolated.

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