How to Use the Mercado Pago MCP in AutoGen

Q: How do I configure the Mercado Pago MCP Server in AutoGen?

Install the extension with pip install -U "autogen-extmcp" and use the mcpservertools helper. Pass the tools list directly to your AssistantAgent constructor to enable payment capabilities.

Q: Can AutoGen agents coordinate to create Pix payments in Mercado Pago?

Yes, one agent can gather customer details to call createcustomer while another triggers createpixpayment. They share the QR code payload to present to the user.

Q: How do AutoGen agents resolve transaction discrepancies in Mercado Pago?

Your agents use searchpayments to pull transaction records and debate discrepancies. They compare the API data against your internal database to find mismatches automatically.

Run multi-agent debates in AutoGen to validate and process Mercado Pago payments safely.

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 AutoGen

Create your Vinkius account to connect Mercado Pago to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate payment safety in AutoGen

The `create_payment` tool processes credit card transactions through this MCP Server after your AutoGen agents reach a consensus. A security agent can analyze customer metadata while a billing agent prepares the card token, ensuring no transaction is sent without multi-agent approval. This cooperative validation prevents fraudulent transactions. The agents discuss the risk profile before executing the tool, reducing chargebacks.

Automate complex refund negotiations

The `refund_payment` tool reverses transactions during dispute resolution conversations. Your AutoGen customer service agent proposes a refund, which a supervisor agent must review and approve before the tool is triggered. This multi-agent flow ensures that refunds are only processed under correct company policies. The agents verify the payment status using `get_payment` before executing the refund.

Coordinate checkout setup via MCP Server

The `create_preference` tool generates checkout URLs for your e-commerce store. In your AutoGen setup, a marketing agent defines the item details, while a finance agent validates tax configurations before the preference is generated. This collaborative approach ensures checkouts are built correctly. The agents coordinate the entire setup process, checking active options via `list_payment_methods` before finalizing the checkout link.

Setup guide

Set up Mercado Pago MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Mercado Pago tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Mercado Pago_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Mercado Pago data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Mercado Pago_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Mercado Pago data")
    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 AutoGen

Install the extension with `pip install -U "autogen-ext[mcp]"` and use the mcp_server_tools helper. Pass the tools list directly to your AssistantAgent constructor to enable payment capabilities.

Yes, one agent can gather customer details to call `create_customer` while another triggers `create_pix_payment`. They share the QR code payload to present to the user.

Your agents use `search_payments` to pull transaction records and debate discrepancies. They compare the API data against your internal database to find mismatches automatically.

Yes, the McpToolAdapter handles communication over stdio or Streamable HTTP. This allows your agents to invoke payment tools with minimal latency.

The MCP Server uses ephemeral V8 sandboxes to isolate transaction data. No QR code payloads or customer details are stored on the Vinkius platform, ensuring your financial data remains secure.

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