How to Use the Mercado Libre MCP in Vercel AI SDK

Q: Can I use Vercel AI SDK to predict product categories on Mercado Libre?

Yes. Your app feeds a listing title to predictcategory via the SDK tool-calling mechanism. The predicted category ID streams back to your frontend, allowing you to auto-populate listing forms instantly.

Q: What happens when a customer files a dispute?

Your agent calls getclaim to pull the dispute reasons and current status. You can then stream these specific resolution options directly to your support dashboard.

Q: Is customer address data safe when using this MCP Server?

Absolutely. When your agent calls getuseraddresses to verify delivery locations, the raw address data passes through Vinkius's ephemeral V8 sandboxes. Your Mercado Libre credentials and customer location details are never stored or logged on our servers.

Build live-streaming dashboards that feed real-time Mercado Libre logistics and buyer data straight to your Vercel AI SDK frontend.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mercado Libre MCP to Vercel AI SDK

Create your Vinkius account to connect Mercado Libre to Vercel AI 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 Libre with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Live Mercado Libre Order Data

`get_order` is the tool your Vercel AI SDK client calls to pull raw transaction details directly into your user's viewport without a loading spinner. The customer or support agent sees the order status, pricing, and buyer ID populate the React component instantly as the stream resolves. Instead of waiting for a full API roundtrip, `search_orders` works alongside the streaming interface to filter through thousands of past transactions on the fly. You build interfaces where search results paint the screen row-by-row, keeping the user experience fast and responsive even during peak holiday sales.

Track Shipments Instantly via this MCP Server

`get_shipment` gives your application immediate access to tracking codes, carrier updates, and current transit milestones. Your Next.js frontend renders these logistics updates in real-time as the Vercel AI SDK feeds the raw payload straight to your custom progress-bar components. To prevent shipping delays before they happen, `get_shipment_sla` pulls the exact delivery window commitments directly from the platform. Your support team views these strict deadlines side-by-side with live transit data, making it easy to spot delayed packages before buyers start filing complaints.

Answer Buyer Questions on the Fly

`search_questions` lets your support agent scan incoming pre-sale inquiries on your frontend without refreshing the page. The Vercel AI SDK handles the streaming text generation, allowing your team to watch draft responses write themselves in real-time inside the text editor. Once the draft looks solid, `answer_question` posts the response directly back to the marketplace listing. This setup cuts down response times to seconds, which helps boost your listing visibility in search results.

Setup guide

Set up Mercado Libre MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Mercado Libre tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Mercado Libre transactions",
});

console.log(text);
await mcpClient.close();

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 Libre. 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 Libre 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 Libre MCP in Vercel AI SDK

Use streamText along with the MCP client tools. The SDK handles the HTTP connection to Vinkius, allowing `get_order` data to stream directly into your React hooks.

Yes. Your app feeds a listing title to `predict_category` via the SDK tool-calling mechanism. The predicted category ID streams back to your frontend, allowing you to auto-populate listing forms instantly.

Vinkius manages the underlying API connections and token buckets. When your Edge Functions call `get_shipment` or `get_sale_price`, the server handles the queueing so your frontend stays fast.

Your agent calls `get_claim` to pull the dispute reasons and current status. You can then stream these specific resolution options directly to your support dashboard.

Absolutely. When your agent calls `get_user_addresses` to verify delivery locations, the raw address data passes through Vinkius's ephemeral V8 sandboxes. Your Mercado Libre credentials and customer location details are never stored or logged on our servers.

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