How to Use the VTEX Catalog MCP in LangChain

Q: Can I manage product creation using VTEX Catalog and LangChain?

Yes. You can use the saveproduct tool to create new records or update existing ones in the catalog, all orchestrated through a multi-step chain. It's designed for complex, sequential data operations.

Run multi-step VTEX operations with LangChain's ReAct agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect VTEX Catalog MCP to LangChain

Create your Vinkius account to connect VTEX Catalog to LangChain 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 VTEX Catalog with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build complex product pipelines with LangChain

You build chains where the output of one tool feeds directly into the next. For example, an agent can use `search_products` to find a brand ID, then feed that ID into `get_brand`, and finally pass both pieces of data to create a new product using `save_product`. This ability means your agent doesn't just call tools; it reasons about the required sequence. LangChain handles this entire workflow, giving you full visibility via tracing.

Update inventory and catalog data with MCP Server

The system lets your AI client interact with critical backend functions like updating stock levels. You can trigger `manage_stock` to adjust a SKU's quantity, or use `save_product` to create entirely new items in the VTEX Catalog. This level of control means you don't need separate API calls for every task; it all happens within one logical chain managed by LangChain.

Discover product details using LangChain

Need to know about a specific item? You can call `get_product` for full details, or use `get_sku` if you only have the stock keeping unit. The agent handles which tool is best suited based on your initial query. Furthermore, `search_products` lets you narrow down results by text, brand ID (`b/`), or category ID (`c/`) in a single, efficient step.

Setup guide

Set up VTEX Catalog MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes VTEX Catalog tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

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

async with MultiServerMCPClient({
    "vtex-catalog-mcp": {
        "transport": "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,
    )
    result = await agent.ainvoke({
        "messages": "List recent VTEX Catalog transactions"
    })
    print(result["messages"][-1].content)

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 VTEX. 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 VTEX Catalog 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 VTEX Catalog MCP in LangChain

LangChain lets your agent orchestrate multiple API calls. You can combine `search_products` results—for instance, finding a category ID first—and then use that ID to retrieve detailed information about the entire group using `get_category`.

The server accesses live, structured data from your VTEX backend. This includes everything from brand metadata via `get_brand` to current inventory counts managed by `manage_stock`. The results are always fresh.

Yes. You can use the `save_product` tool to create new records or update existing ones in the catalog, all orchestrated through a multi-step chain. It's designed for complex, sequential data operations.

Yes. The LangChain adapter supports aggregation across multiple MCP Servers. This means you can combine VTEX Catalog tools with other external APIs in one single agent chain.

The server handles product metadata, including brand IDs and category relationships. It also manages critical inventory data points associated with every SKU you interact with.

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