How do I get an Access Token for Mercado Livre?

Go to the [**Mercado Livre Developers**](https://developers.mercadolivre.com.br) portal, create an App, and use the OAuth2 flow to generate your Access Token. It usually starts with `APP_USR-...`.

Can I create listings with images?

Yes, the create_item tool accepts a JSON body where you can include picture IDs. Ensure images are already uploaded to Mercado Livre's servers via their Picture API first.

How do I update stock for multiple items?

You can use the update_stock action for each item individually. For bulk updates, we recommend using the stock update endpoint directly or creating a loop in your workflow.

What listing types does Mercado Livre support?

Mercado Livre supports several listing types: 'gold_special' (premium with fulfillment), 'gold_pro' (classic), and 'gold' (basic). Each type offers different levels of visibility, fees, and buyer reach.

Mercado Livre Catalog MCP Server for LangChain 9 tools — connect in under 2 minutes

Name: Mercado Livre Catalog
Availability: InStock
Author: Vinkius

python.langchain.com/docs/integrations/tools/mcp

Built by Vinkius GDPR 9 Tools Framework

LangChain is the leading Python framework for composable LLM applications. Connect Mercado Livre Catalog through Vinkius and LangChain agents can call every tool natively. combine them with retrievers, memory, and output parsers for sophisticated AI pipelines.

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 langchain_mcp_adapters.client import MultiServerMCPClient
from langchain_openai import ChatOpenAI
from langgraph.prebuilt import create_react_agent

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MultiServerMCPClient({
        "mercado-livre-catalog": {
            "transport": "streamable_http",
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
        }
    }) as client:
        tools = client.get_tools()
        agent = create_react_agent(
            ChatOpenAI(model="gpt-4o"),
            tools,
        )
        response = await agent.ainvoke({
            "messages": [{
                "role": "user",
                "content": "Using Mercado Livre Catalog, show me what tools are available.",
            }]
        })
        print(response["messages"][-1].content)

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 Mercado Livre Catalog MCP Server

Connect Mercado Livre Catalog to any AI agent and streamline your e-commerce operations — manage listings, adjust stock levels, update prices, and discover categories through natural conversation.

LangChain's ecosystem of 500+ components combines seamlessly with Mercado Livre Catalog through native MCP adapters. Connect 9 tools via Vinkius and use ReAct agents, Plan-and-Execute strategies, or custom agent architectures. with LangSmith tracing giving full visibility into every tool call, latency, and token cost.

What you can do

Create Listings — Publish new products with full details and attributes
Stock Management — Update inventory levels instantly across all listings
Price Updates — Change prices dynamically to stay competitive
Search & Discovery — Find your active listings and browse categories
Attribute Management — Get mandatory attributes for specific categories (e.g., voltage, size)
Deactivation — Close listings that are no longer available

The Mercado Livre Catalog MCP Server exposes 9 tools through the Vinkius. Connect it to LangChain 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 Mercado Livre Catalog to LangChain via MCP

Follow these steps to integrate the Mercado Livre Catalog MCP Server with LangChain.

Install dependencies

Run pip install langchain langchain-mcp-adapters langgraph langchain-openai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save the code and run python agent.py

Explore tools

The agent discovers 9 tools from Mercado Livre Catalog via MCP

Why Use LangChain with the Mercado Livre Catalog MCP Server

LangChain provides unique advantages when paired with Mercado Livre Catalog through the Model Context Protocol.

The largest ecosystem of integrations, chains, and agents. combine Mercado Livre Catalog MCP tools with 500+ LangChain components

Agent architecture supports ReAct, Plan-and-Execute, and custom strategies with full MCP tool access at every step

LangSmith tracing gives you complete visibility into tool calls, latencies, and token usage for production debugging

Memory and conversation persistence let agents maintain context across Mercado Livre Catalog queries for multi-turn workflows

Mercado Livre Catalog + LangChain Use Cases

Practical scenarios where LangChain combined with the Mercado Livre Catalog MCP Server delivers measurable value.

RAG with live data: combine Mercado Livre Catalog tool results with vector store retrievals for answers grounded in both real-time and historical data

Autonomous research agents: LangChain agents query Mercado Livre Catalog, synthesize findings, and generate comprehensive research reports

Multi-tool orchestration: chain Mercado Livre Catalog tools with web scrapers, databases, and calculators in a single agent run

Production monitoring: use LangSmith to trace every Mercado Livre Catalog tool call, measure latency, and optimize your agent's performance

Mercado Livre Catalog MCP Tools for LangChain (9)

These 9 tools become available when you connect Mercado Livre Catalog to LangChain via MCP:

create_item

Create a new listing

delete_item

Deactivate a listing (close it)

get_categories

List top-level categories of Mercado Livre Brasil

get_domain_attributes

Get required attributes for a category/domain

get_item

Get details of a specific listing

search_items

Note: Full search parameters are available via query string in documentation. Search for listings belonging to the authenticated user

update_item

Update a listing (title, description, attributes)

update_price

Update the price of an item

update_stock

Update available quantity for an item

Example Prompts for Mercado Livre Catalog in LangChain

Ready-to-use prompts you can give your LangChain agent to start working with Mercado Livre Catalog immediately.

"Update the price of item MLB123456 to R$99.90."

"Create a new listing for a 'Wireless Mouse' in category 'Accessories'."

"What are the mandatory attributes for the Cellphones category?"

Troubleshooting Mercado Livre Catalog MCP Server with LangChain

Common issues when connecting Mercado Livre Catalog to LangChain through the Vinkius, and how to resolve them.

MultiServerMCPClient not found

Install: pip install langchain-mcp-adapters

Mercado Livre Catalog + LangChain FAQ

Common questions about integrating Mercado Livre Catalog MCP Server with LangChain.

How does LangChain connect to MCP servers?

Use langchain-mcp-adapters to create an MCP client. LangChain discovers all tools and wraps them as native LangChain tools compatible with any agent type.

Which LangChain agent types work with MCP?

All agent types including ReAct, OpenAI Functions, and custom agents work with MCP tools. The tools appear as standard LangChain tools after the adapter wraps them.