How to Use the Mercado Livre Orders MCP in OpenAI Agents SDK

Q: How do I setup the Mercado Livre Orders MCP Server with the OpenAI Agents SDK?

Install the package, then initialize the server with MCPServerStreamableHttp using your Vinkius endpoint. Pass the server instance inside the mcpservers list when creating your agent. The tools will auto-discover instantly.

Q: Can my agent handle shipping updates automatically?

Yes, the agent can coordinate updates using getshippinginfo and settracking. You write the logic to check your warehouse database, and the agent updates Mercado Livre directly.

Run production-grade agents that handle Mercado Livre orders with OpenAI Agents SDK safety guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mercado Livre Orders MCP to OpenAI Agents SDK

Create your Vinkius account to connect Mercado Livre Orders 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 Livre Orders with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe order cancellations via OpenAI Agents SDK

Your automated support agents can safely stop problematic sales before they ship. By combining `get_feedback` and `get_shipping_info`, the agent evaluates buyer sentiment and transit lag. It only calls `cancel_order` when specific safety guardrails are met, preventing accidental hits to your seller reputation. This MCP Server handles the actual API calls while the OpenAI Agents SDK manages the logic. You get full execution tracing directly on your OpenAI dashboard. If an agent tries to cancel an active shipment, your custom guardrail catches it before the API gets hit.

Smart shipping updates and tracking

Keeping buyers updated on Mercado Livre requires constant tracking adjustments. The agent uses `get_shipments` to pull active orders and matches them against your carrier updates. Once it verifies the carrier data, it triggers `set_tracking` to update the marketplace. Running this workflow through the MCP setup means you can hand off the tracking task to a specialized logistics agent. The core agent handles general customer inquiries, then transfers the session to a shipping agent when tracking numbers need to be updated.

Automated feedback analysis for support teams

Customer disputes can tank your seller rating on Mercado Livre. Use `get_feedback` to monitor buyer reviews and flag negative comments immediately. Your agent scans recent transactions using `search_orders` to isolate problematic accounts. Because the SDK supports async context managers, you can run these background checks across thousands of sales. The agent flags low-rating buyers, retrieves their details using `get_order`, and queues them for your support team.

Setup guide

Set up Mercado Livre Orders 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 Livre Orders tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Mercado Livre Orders 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 Livre Orders 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 Livre Orders Agent",
            instructions="You have access to Mercado Livre Orders 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 Livre. 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 Livre Orders 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 Livre Orders MCP in OpenAI Agents SDK

The MCP framework catches API errors during runtime and routes them back to the agent. If `get_order` fails due to a rate limit, the agent reads the error payload and schedules a retry. You can monitor these failures directly in your OpenAI dashboard.

Yes, you control tool access during agent initialization. If you want a support agent to only view sales, pass only `get_order` and `search_orders` to the constructor. This prevents the agent from triggering `cancel_order` without authorization.

Install the package, then initialize the server with `MCPServerStreamableHttp` using your Vinkius endpoint. Pass the server instance inside the `mcp_servers` list when creating your agent. The tools will auto-discover instantly.

Yes, the agent can coordinate updates using `get_shipping_info` and `set_tracking`. You write the logic to check your warehouse database, and the agent updates Mercado Livre directly.

Your sales and tracking details stay within the secure Vinkius sandbox and your OpenAI execution environment. Vinkius runs the MCP Server in an isolated runtime, so your order details are never stored or exposed to third parties.

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