How do I get my VTEX API credentials?

Log in to your VTEX Admin, go to **Account Settings → Application Keys**, and create a new App Key. You'll receive an App Key and App Token pair. You also need your Account Name (the subdomain you use to access the VTEX Admin, e.g., 'mystore'). Ensure the key has **Catalog** and **Logistics** read/write permissions. No code, no SDK — just connect and go.

Can my agent update stock levels without opening the VTEX Admin?

Yes! Use the 'manage_stock' tool with a SKU ID and the new quantity. Your agent updates the inventory balance in real-time through the VTEX Logistics API — perfect for warehouse teams receiving shipments who need to update stock counts without navigating to the Inventory module.

How does product search work with categories and brands?

The 'search_products' tool supports three search modes: full-text (e.g., 'Nike Running Shoes'), by brand ID (e.g., 'b/1234'), or by category ID (e.g., 'c/5678'). This means your agent can quickly audit all products under a specific brand or explore an entire product category — no manual catalog browsing required.

Can I create new products and manage my entire catalog via AI?

Absolutely. The 'save_product' tool lets your agent create or update products by sending a structured JSON body. Combined with 'get_category' and 'get_brand' for classification, your agent can handle the full product lifecycle — from initial creation to SKU-level stock adjustments — ideal for merchandising teams managing large VTEX catalogs with thousands of products.

VTEX Catalog MCP Server for LangChain 7 tools — connect in under 2 minutes

Name: VTEX Catalog
Availability: InStock
Author: Vinkius

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

Built by Vinkius GDPR 7 Tools Framework

LangChain is the leading Python framework for composable LLM applications. Connect VTEX 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({
        "vtex-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 VTEX 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 VTEX Catalog MCP Server

Connect your VTEX Catalog API to any AI agent and manage your entire product catalog through natural conversation.

LangChain's ecosystem of 500+ components combines seamlessly with VTEX Catalog through native MCP adapters. Connect 7 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

Product Search — Run full-text searches across your product catalog by name, brand ID, or category ID. Returns complete product listings with pricing, availability, and images.
Product Details — Retrieve the full specification sheet of any product by ID, including all associated SKUs, categories, dimensions, and metadata.
Product Management — Create or update products directly from your agent. Send structured product data and have it reflected in your VTEX catalog immediately.
SKU Inspection — Look up specific SKUs with detailed attributes like price, weight, dimensions, EAN, and stock status.
Stock Management — Update the available quantity of any SKU across your logistics warehouses. Adjust inventory in real-time without opening the VTEX Admin.
Category & Brand Lookup — Explore your category tree and brand directory to understand how your catalog is organized and ensure correct product classification.

The VTEX Catalog MCP Server exposes 7 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 VTEX Catalog to LangChain via MCP

Follow these steps to integrate the VTEX 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 7 tools from VTEX Catalog via MCP

Why Use LangChain with the VTEX Catalog MCP Server

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

The largest ecosystem of integrations, chains, and agents. combine VTEX 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 VTEX Catalog queries for multi-turn workflows

VTEX Catalog + LangChain Use Cases

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

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

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

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

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

VTEX Catalog MCP Tools for LangChain (7)

These 7 tools become available when you connect VTEX Catalog to LangChain via MCP:

get_brand

Get details of a brand

get_category

Get details of a category

get_product

Get full details of a specific product

get_sku

Get details of a specific SKU

manage_stock

Update the available quantity of a SKU

save_product

Create or update a product

search_products

Examples: "Coca Cola", "b/1234" (brand ID), "c/5678" (category ID). Search for products by text, brand, or category

Example Prompts for VTEX Catalog in LangChain

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

"Search for 'Nike Air Max' in my VTEX catalog"

"Update the stock of SKU 12345 to 150 units"

"Show me the details of category 5678"

Troubleshooting VTEX Catalog MCP Server with LangChain

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

MultiServerMCPClient not found

Install: pip install langchain-mcp-adapters

VTEX Catalog + LangChain FAQ

Common questions about integrating VTEX 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.