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 **OMS** read/write permissions. No code, no SDK — just connect and go.

Can my agent register an invoice and tracking number at the same time?

Yes! The 'register_invoice' tool accepts the invoice number and an optional tracking number in one call. Once submitted, the order automatically moves to 'Invoiced' status — eliminating the manual step of navigating to the VTEX Admin, opening the order detail, and filling each field separately.

How does the agent handle order cancellations with refunds?

Just tell your agent to cancel the order. It uses the 'cancel_order' tool with an optional reason (so your team has an audit trail). VTEX then handles the refund automatically based on the payment method. No tab-switching, no admin navigation — your support team resolves it in one conversation.

Can I monitor fulfillment status across hundreds of orders?

Absolutely. The 'search_orders' tool supports status filters and pagination, so your agent can scan the entire order queue — for example, listing all orders stuck in 'ready-for-handling' to identify fulfillment delays. Perfect for operations teams managing high-volume VTEX stores with multiple sellers.

VTEX Orders MCP Server for OpenAI Agents SDK 6 tools — connect in under 2 minutes

Name: VTEX Orders
Availability: InStock
Author: Vinkius

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

Built by Vinkius GDPR 6 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect VTEX Orders 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 Orders Assistant",
            instructions=(
                "You help users interact with VTEX Orders. "
                "You have access to 6 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from VTEX Orders"
        )
        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 Orders MCP Server

Connect your VTEX Order Management System (OMS) to any AI agent and take full control of your store's order lifecycle through natural conversation.

The OpenAI Agents SDK auto-discovers all 6 tools from VTEX Orders through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries VTEX Orders, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

Order Lookup — Retrieve the full details of any order by ID, including items, client profile, payment method, logistics, and current status.
Order Search — Search and filter orders by status (e.g., 'ready-for-handling', 'invoiced', 'canceled') with built-in pagination for large result sets.
Status Updates — Advance orders through the fulfillment pipeline by updating their status (e.g., move from 'ready-for-handling' to 'handling').
Shipment Tracking — Retrieve tracking information for shipped packages, including carrier, tracking number, and tracking URL.
Invoice Registration — Attach tax invoices (NF-e) and tracking numbers to orders, automatically moving them to 'Invoiced' status.
Order Cancellation — Cancel orders with an optional reason, triggering automatic refund processing.

The VTEX Orders MCP Server exposes 6 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 Orders to OpenAI Agents SDK via MCP

Follow these steps to integrate the VTEX Orders 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 6 tools from VTEX Orders

Why Use OpenAI Agents SDK with the VTEX Orders MCP Server

OpenAI Agents SDK provides unique advantages when paired with VTEX Orders 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 Orders + OpenAI Agents SDK Use Cases

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

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

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

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

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

VTEX Orders MCP Tools for OpenAI Agents SDK (6)

These 6 tools become available when you connect VTEX Orders to OpenAI Agents SDK via MCP:

cancel_order

Cancel an order

get_order

Get full details of a specific order

get_tracking_info

Get tracking info for an order package

register_invoice

search_orders

g., "ready-for-handling"). Search for orders by status or pagination

update_order_status

Update the status of an order

Example Prompts for VTEX Orders in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with VTEX Orders immediately.

"Show me the details of order v-1234567890"

"List all orders with status 'ready-for-handling'"

"Cancel order v-444 — customer requested wrong size"

Troubleshooting VTEX Orders MCP Server with OpenAI Agents SDK

Common issues when connecting VTEX Orders 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 Orders + OpenAI Agents SDK FAQ

Common questions about integrating VTEX Orders 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.