How to Use the Mercado Pago MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK agent handle recurring payments with Mercado Pago?

Yes, by using createpreference to build custom checkout preferences for your buyers. The agent generates the checkout URL, allowing customers to complete recurring setups securely on the hosted checkout page.

Q: Does this integration support CPF and CNPJ validation?

Yes, the agent calls getidentificationtypes to retrieve the active list of valid document types. It then checks the user's input against these types before running createcustomer.

Run production-grade billing agents that collect Pix payments and manage customers using the OpenAI Agents SDK MCP Server.

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 OpenAI Agents SDK

Create your Vinkius account to connect Mercado Pago to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Issue Pix QR Codes with OpenAI Agents SDK

The `create_pix_payment` tool lets your agent generate instant Pix QR codes and copy-paste payloads directly inside your Python execution loop. By combining this with the OpenAI Agents SDK guardrails, the agent validates the transaction amount before hitting the live API. You define the validation parameters in your agent schema, preventing unauthorized or out-of-bounds payment creation. Once verified, the agent executes the request and returns the payment payload containing the raw QR string for immediate customer presentation.

Register Customers and Cards Safely

The `create_customer` tool registers new buyers in Brazil, while the `create_card` tool securely links pre-tokenized cards to their profiles. The OpenAI Agents SDK manages these multi-step operations by passing state between a dedicated onboarding agent and a billing agent. This handoff ensures that sensitive customer details never leak into unrelated agent contexts. Your agent calls `get_identification_types` to verify document formats like CPF or CNPJ before committing any customer records to the platform.

Reconcile Payments and Issue Refunds

The `search_payments` tool queries your transaction history using filters, allowing your agent to identify unapplied balances or pending clearances via the MCP standard. If a customer disputes a charge, the agent uses `refund_payment` to return the funds partially or fully based on the transaction ID. The OpenAI dashboard tracks every tool call, giving you a clear audit trail of which agent initiated the refund and why. Your agent checks the status of individual transactions with `get_payment` to ensure reconciliation matches your internal database records.

Setup guide

Set up Mercado Pago MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Mercado Pago tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Mercado Pago tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Mercado Pago tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Mercado Pago Agent",
            instructions="You have access to Mercado Pago tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install openai-agents via pip and initialize the MCP server using MCPServerStreamableHttp with your Vinkius endpoint. Pass this server instance in the mcp_servers list when instantiating your agent to auto-discover all 12 payment tools.

Yes, by using create_preference to build custom checkout preferences for your buyers. The agent generates the checkout URL, allowing customers to complete recurring setups securely on the hosted checkout page.

You configure agent guardrails to check transaction history first using search_payments before executing a new charge. The SDK guarantees that the agent validates state prior to calling the payment creation endpoint.

Yes, the agent calls get_identification_types to retrieve the active list of valid document types. It then checks the user's input against these types before running create_customer.

Only raw API payloads like customer IDs, card tokens, and Pix strings go through the secure MCP V8 sandbox. Vinkius operates ephemerally, meaning transaction details and payment credentials are never stored on the hosting platform.

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