How do I get my Secret Key?

Log in to the Pagar.me dashboard, navigate to **Settings > API Keys** and copy your **Secret Key** (starts with `sk_...`). No complex OAuth apps, no webhooks — just connect and start processing payments.

Does it support Pix and Boleto?

Yes! Generate instant Pix QR Codes or Boletos right in the chat. Your agent handles the entire checkout flow — creating the order, retrieving the payment code, and allowing the customer to pay without ever leaving the conversation.

Can I manage subscriptions?

Yes. Just tell your AI agent to subscribe a new customer. It will register the customer, attach them to your predefined SaaS recurring plan, and confirm the active billing status — all in a single prompt without touching a dashboard.

Can I manage complete customer profiles and track their transaction histories?

Absolutely. View detailed customer records, pull entire order histories, and verify payment statuses instantly — perfect for SaaS founders, customer support teams, and digital agencies handling multiple accounts.

Pagar.me MCP Server for Pydantic AI 11 tools — connect in under 2 minutes

Name: Pagar.me
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 11 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Pagar.me through 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 Pagar.me "
            "(11 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Pagar.me?"
    )
    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 Pagar.me MCP Server

Connect Pagar.me to any AI agent and unlock a powerful Brazilian payment infrastructure — create orders with Pix, Boleto, or Credit Card, manage recurring subscriptions, and track transactions through natural conversation.

Pydantic AI validates every Pagar.me tool response against typed schemas, catching data inconsistencies at build time. Connect 11 tools through 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

Order Creation — Create orders for single items with multiple payment methods
Pix Payments — Generate instant Pix QR Codes for immediate payment
Boleto Generation — Create Boleto Bancário with custom due dates
Subscriptions — Set up recurring billing for services
Customer Management — Register customers and view their history
Transaction Tracking — List orders and check their status

The Pagar.me MCP Server exposes 11 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 Pagar.me to Pydantic AI via MCP

Follow these steps to integrate the Pagar.me 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 11 tools from Pagar.me with type-safe schemas

Why Use Pydantic AI with the Pagar.me MCP Server

Pydantic AI provides unique advantages when paired with Pagar.me 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 Pagar.me integration code

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

Dependency injection system cleanly separates your Pagar.me connection logic from agent behavior for testable, maintainable code

Pagar.me + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Pagar.me MCP Server delivers measurable value.

Type-safe data pipelines: query Pagar.me with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Pagar.me tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Pagar.me and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Pagar.me responses and write comprehensive agent tests

Pagar.me MCP Tools for Pydantic AI (11)

These 11 tools become available when you connect Pagar.me to Pydantic AI via MCP:

cancel_order

Cancel an order

capture_order

Capture an authorized order

create_boleto_order

Create an order paid via Boleto

create_customer

Document can be CPF or CNPJ. Register a new customer

create_order

Items and Customer are required. You can add custom payments array or use the Pix/Boleto helpers. Create a new order with credit card or custom payments

create_pix_order

Expires in 1 hour. Create an order paid via Pix

create_subscription

Create a recurring subscription for a customer

get_customer

Get customer details

get_order

Get details of a specific order

get_subscription

Get subscription details

list_orders

List recent orders

Example Prompts for Pagar.me in Pydantic AI

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

"Create a Pix order for R$50.00 for customer João Silva."

"Show me the last 5 orders."

"Create a monthly subscription of R$99.90 for customer 123 on plan 456."

Troubleshooting Pagar.me MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Pagar.me + Pydantic AI FAQ

Common questions about integrating Pagar.me 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 Pagar.me MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.