How to Use the Mercado Livre Interactions MCP in Mastra AI

Q: Can I require human approval before Mastra AI calls the answerquestion tool?

Yes. You can set requireToolApproval to true on your agent. This pauses the workflow when answerquestion is triggered, letting you review the draft before it goes to Mercado Livre.

Q: How do I register the Mercado Livre Interactions MCP Server tools with a Mastra AI agent?

Initialize the client and call mcpClient.listTools(). You then spread those tools directly into your Mastra agent's tool array so it can access getquestions or getreputation.

Q: Does this server support multi-step conditional workflows?

Yes. You can design workflows that check getmetrics first, analyze the data, and then conditionally fetch message logs if performance dips below your targets.

Q: Where does my buyer message data go during a Mastra AI workflow?

All buyer questions and order messages fetched via getmessages remain strictly within your execution environment. Vinkius executes this MCP Server in an isolated V8 sandbox, ensuring your customers' private purchase history never leaks.

Build automated, resilient workflows for Mercado Livre Interactions using Mastra AI agents with built-in retries.

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 Interactions MCP to Mastra AI

Create your Vinkius account to connect Mercado Livre Interactions to Mastra AI 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 Interactions with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate buyer replies using Mastra AI agents

`get_questions` fetches all unanswered buyer inquiries from your Mercado Livre listings. Your Mastra AI agent processes this list, evaluates the buyer's intent, and prepares a response draft. If the draft meets your quality threshold, the agent uses `answer_question` to post the reply. The workflow engine automatically retries the API call if it hits rate limits, preventing missed customer inquiries.

Track store standing with this Mastra MCP Server

`get_reputation` retrieves your current seller tier and warning flags. This MCP Server feeds that data directly into a Mastra AI monitoring agent to watch for status changes. If your tier drops, the agent triggers a workflow to fetch detailed performance data via `get_metrics`. This allows your system to alert your team on Slack before the algorithm suppresses your listings.

Resolve order issues with conditional Mastra workflows

`get_messages` pulls the complete conversation history for any problematic sale. Your Mastra AI agent analyzes this text to determine if a buyer is complaining about shipping delays. The workflow then branches based on the sentiment analysis. If a dispute is detected, the agent escalates the ticket to a human manager, ensuring you never get penalized for unaddressed buyer anger.

Setup guide

Set up Mercado Livre Interactions MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Mercado Livre Interactions tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "mercado-livre-interactions-mcp-client",
  servers: {
    "mercado-livre-interactions-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Mercado Livre Interactions Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Mercado Livre Interactions tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Mercado Livre Interactions transactions"
);
console.log(result.text);

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 Interactions 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 Interactions MCP in Mastra AI

Mastra AI features a built-in workflow engine with exponential backoff. If the `answer_question` tool hits a rate limit, the system pauses and retries the call automatically without failing the execution.

Yes. You can set `requireToolApproval` to true on your agent. This pauses the workflow when `answer_question` is triggered, letting you review the draft before it goes to Mercado Livre.

Initialize the client and call `mcpClient.listTools()`. You then spread those tools directly into your Mastra agent's tool array so it can access `get_questions` or `get_reputation`.

Yes. You can design workflows that check `get_metrics` first, analyze the data, and then conditionally fetch message logs if performance dips below your targets.

All buyer questions and order messages fetched via `get_messages` remain strictly within your execution environment. Vinkius executes this MCP Server in an isolated V8 sandbox, ensuring your customers' private purchase history never leaks.

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