How do I get a Mercado Pago Access Token?

Go to your Mercado Pago account, navigate to **Developers > Your Integrations > Production Credentials** (or Sandbox), and copy your **Access Token**. It starts with 'APP_USR-' for production.

Can I generate Pix payments?

Yes! Use the `create_pix_payment` action. It generates a Pix transaction and returns QR Code data that can be displayed for the payer to scan and pay instantly.

Yes! Use the `refund_payment` action with a payment_id. If you omit the amount, it performs a full refund. If you provide an amount, it performs a partial refund.

Mercado Pago MCP Server for Pydantic AI 12 tools — connect in under 2 minutes

Name: Mercado Pago
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 12 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Mercado Pago through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Mercado Pago "
            "(12 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Mercado Pago?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Mercado Pago MCP Server

Connect Mercado Pago to any AI agent and unlock Brazil's leading payment gateway — create Pix payments, manage credit card transactions, issue refunds, and handle customer data through natural conversation.

Pydantic AI validates every Mercado Pago tool response against typed schemas, catching data inconsistencies at build time. Connect 12 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Pix Payments — Generate instant Pix QR Codes for frictionless payments
Credit Card Processing — Charge cards (Visa, Mastercard, Elo) securely
Checkout Preferences — Generate payment links for web checkout
Customer Management — Register customers and save cards for one-click payments
Refunds — Issue partial or full refunds instantly
Payment Search — Find and reconcile payments by email, status, or ID
Payment Methods — List all supported methods in Brazil

The Mercado Pago MCP Server exposes 12 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Mercado Pago to Pydantic AI via MCP

Follow these steps to integrate the Mercado Pago MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 12 tools from Mercado Pago with type-safe schemas

Why Use Pydantic AI with the Mercado Pago MCP Server

Pydantic AI provides unique advantages when paired with Mercado Pago through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Mercado Pago integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Mercado Pago connection logic from agent behavior for testable, maintainable code

Mercado Pago + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Mercado Pago MCP Server delivers measurable value.

Type-safe data pipelines: query Mercado Pago with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Mercado Pago tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Mercado Pago and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Mercado Pago responses and write comprehensive agent tests

Mercado Pago MCP Tools for Pydantic AI (12)

These 12 tools become available when you connect Mercado Pago to Pydantic AI via MCP:

create_card

Save a card for a customer

create_customer

create_payment

Requires a valid card token (generated via SDK frontend). Payment methods: visa, master, amex, etc. Create a new payment using card or other methods

create_pix_payment

Returns QR Code data for the user to scan and pay instantly. Create a Pix payment with QR Code

create_preference

Create a checkout preference for redirection

get_customer

Get customer details

get_identification_types

Get valid identification types (CPF, CNPJ, etc)

get_payment

Get details of a specific payment by ID

get_preference

Get details of a checkout preference

list_payment_methods

List all available payment methods for Brazil

refund_payment

If amount is omitted, performs a full refund. Refund a payment partially or fully

search_payments

Useful for reconciliation and reporting. Search for payments with filters

Example Prompts for Mercado Pago in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Mercado Pago immediately.

"Create a Pix payment for R$150 for a customer."

"Refund payment 12345678 fully."

"Show me all approved payments for user@email.com."

Troubleshooting Mercado Pago MCP Server with Pydantic AI

Common issues when connecting Mercado Pago to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Mercado Pago + Pydantic AI FAQ

Common questions about integrating Mercado Pago MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Mercado Pago MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.