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 OpenAI Agents SDK 7 tools — connect in under 2 minutes

Name: VTEX Catalog
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 7 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect VTEX Catalog through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

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 agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="VTEX Catalog Assistant",
            instructions=(
                "You help users interact with VTEX Catalog. "
                "You have access to 7 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from VTEX Catalog"
        )
        print(result.final_output)

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.

The OpenAI Agents SDK auto-discovers all 7 tools from VTEX Catalog through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries VTEX Catalog, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

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 OpenAI Agents SDK 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 OpenAI Agents SDK via MCP

Follow these steps to integrate the VTEX Catalog MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 7 tools from VTEX Catalog

Why Use OpenAI Agents SDK with the VTEX Catalog MCP Server

OpenAI Agents SDK provides unique advantages when paired with VTEX Catalog through the Model Context Protocol.

Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

VTEX Catalog + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the VTEX Catalog MCP Server delivers measurable value.

Automated workflows: build agents that query VTEX Catalog, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries VTEX Catalog, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through VTEX Catalog tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query VTEX Catalog to resolve tickets, look up records, and update statuses without human intervention

VTEX Catalog MCP Tools for OpenAI Agents SDK (7)

These 7 tools become available when you connect VTEX Catalog to OpenAI Agents SDK 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 OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK 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 OpenAI Agents SDK

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

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

VTEX Catalog + OpenAI Agents SDK FAQ

Common questions about integrating VTEX Catalog MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.