How to Use the Commerce Layer MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK manage active Commerce Layer promotions?

The agent queries listpromotions to fetch active discount campaigns. It then applies the correct code to the customer's cart during the checkout flow.

Build production-grade e-commerce checkout agents with strict guardrails using the OpenAI Agents SDK and this Commerce Layer MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Commerce Layer MCP to OpenAI Agents SDK

Create your Vinkius account to connect Commerce Layer 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 Commerce Layer with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Look up SKUs and prices with OpenAI Agents SDK

Your agent calls `list_skus` and `list_prices` to pull current pricing and stock data straight from Commerce Layer. This gives your agent real-time catalog data during a customer chat, preventing it from quoting outdated prices or selling items that aren't in stock. By caching these tool lists in your Python code, you keep latency low. The agent handles the pricing logic, while the OpenAI dashboard lets you track every single API call to verify accuracy.

Draft orders directly inside agent workflows

The `create_order` tool lets your agent configure draft orders when a customer decides to buy. From there, the agent uses `get_order` and `list_orders` to check on payment or shipping status without human intervention. Guardrails in this SDK validate these actions before they execute. You don't have to worry about an agent creating rogue orders or leaking customer details during an MCP session.

Manage shipments and discounts via MCP Server

The server exposes `list_shipments` and `list_promotions` to help your agent resolve delivery questions and apply active discounts. When a customer asks where their package is, the agent queries the shipping data directly. This setup keeps your support team out of the weeds. You get clean execution logs in your dashboard, showing exactly which promotional codes the agent applied to each draft order.

Setup guide

Set up Commerce Layer 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 Commerce Layer tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Commerce Layer 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="Commerce Layer Agent",
            instructions="You have access to Commerce Layer 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 Commerce Layer. 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 Commerce Layer 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 Commerce Layer MCP in OpenAI Agents SDK

Install the SDK and pass the Vinkius HTTP endpoint to your agent constructor. Use the `MCPServerStreamableHttp` class to register the MCP server, and the agent will automatically discover all twelve tools.

Yes, the SDK's built-in guardrails validate tool inputs before running `create_order`. This prevents the agent from passing bad pricing or invalid customer addresses to Commerce Layer.

The agent queries `list_promotions` to fetch active discount campaigns. It then applies the correct code to the customer's cart during the checkout flow.

You can handle this by defining separate agent instances and passing only the necessary tools to each. For example, a support agent might only need `list_shipments`, while a sales agent gets `create_order`.

All traffic passes through Vinkius's zero-trust sandboxed environment, meaning your customer addresses, order histories, and payment methods are never stored. The connection uses ephemeral tokens, keeping your Commerce Layer API keys completely isolated from the LLM.

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