How to Use the VTEX Catalog MCP in OpenAI Agents SDK

Q: Can I search products using the OpenAI Agents SDK and VTEX Catalog?

Yep. You use the searchproducts tool. Your agent can take natural language input (like 'Coca Cola') and map it to a product query against your VTEX Catalog.

Q: How do I update stock levels using the OpenAI Agents SDK for VTEX Catalog?

Use the managestock tool. You just need to provide the target SKU and the new quantity. The OpenAI Agents SDK handles sending that update directly to your catalog.

Connect VTEX Catalog to your OpenAI Agents SDK. Get product data, manage inventory, all from a production agent system.

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 OpenAI Agents SDK

Create your Vinkius account to connect VTEX Catalog to OpenAI Agents 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 VTEX Catalog with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Product and Inventory Management

You can use the `save_product` tool to create or update items directly in VTEX Catalog. Need to change stock? Just call `manage_stock` with a SKU, and your agent updates the available quantity instantly. It's built for deployment, not testing. When you pass this MCP Server to the OpenAI Agents SDK, those actions run through guardrails first—you never risk bad data hitting your live catalog.

Deep Product Discovery

Don't just search by keywords. The `search_products` tool lets you query VTEX Catalog using text, a brand ID (`b/1234`), or a category ID (`c/5678`). Get the full picture with `get_product`, which provides every detail about an item. The OpenAI Agents SDK auto-discovers these tools. This means your agent can figure out what data it needs, whether it's finding a brand with `get_brand` or just checking inventory levels.

Structured Data Retrieval

Need specific details? You can pull an entire SKU record using `get_sku`. Or maybe you only need the category structure, in which case `get_category` works. These tools give your agent granular control over VTEX Catalog data. The performance boost from setting `cacheToolsList=True` means that when your OpenAI Agents SDK runs multiple lookups—say, checking 20 different products—it's fast. It won't drag.

Setup guide

Set up VTEX Catalog MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all VTEX Catalog tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives VTEX Catalog tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate VTEX Catalog tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="VTEX Catalog Agent",
            instructions="You have access to VTEX Catalog tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

The MCP Server exposes all VTEX Catalog tools to your agent, letting it act on them. You pass the server streamable instance when initializing the OpenAI Agents SDK, and boom—it's ready to go.

The action runs through built-in guardrails first. This validates the product data against safety constraints before it ever hits your VTEX Catalog, so you avoid bad updates.

Yep. You use the `search_products` tool. Your agent can take natural language input (like 'Coca Cola') and map it to a product query against your VTEX Catalog.

This server manages core e-commerce data, including Brand IDs (`b/1234`), Category IDs (`c/5678`), SKU details, and product content.

Use the `manage_stock` tool. You just need to provide the target SKU and the new quantity. The OpenAI Agents SDK handles sending that update directly to your catalog.

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