How to Use the commercetools MCP in OpenAI Agents SDK

Plug the commercetools MCP Server into your OpenAI Agents SDK to manage product catalogs and order flows directly from your Python code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect commercetools MCP to OpenAI Agents SDK

Create your Vinkius account to connect commercetools 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 commercetools with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Direct order and product inspection

Call `get_order` or `get_product` to pull live data into your agent execution trace. You get raw JSON responses from the platform without writing custom API wrappers. Your agent logic stays clean because the tools handle the authentication handshake. Focus on your business rules while the agent handles the heavy lifting.

Search through your commercetools inventory

Use `search_product_by_key` to locate specific items for customer inquiries. It saves you from manual lookups in the dashboard. This MCP Server provides the search functions your agents need to resolve tickets faster. It keeps your data flow strictly within the OpenAI environment.

List carts and customers in Python

Run `list_active_carts` or `list_customers` to feed data into your agent's decision engine. These tools map directly to your backend state. Building out complex workflows becomes trivial when your agent can query the database directly. It removes the need for brittle middleware.

Setup guide

Set up commercetools 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 commercetools tools at runtime.
3

Create your Agent

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

Run the agent

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

You initialize the MCPServerStreamableHttp class using the Vinkius endpoint URL. Pass the instance into your Agent constructor's mcp_servers list to enable tool discovery.

Yes, you use the built-in guardrails in the SDK to validate tool outputs before execution. This prevents the agent from sending bad data to your store.

Set cacheToolsList=True in your configuration to speed up tool discovery. It reduces latency when your agent re-initializes during high-frequency tasks.

All interactions flow through the standard OpenAI dashboard. You can inspect the input and output logs for every tool call executed by your agent.

Your customer records never leave the secure Vinkius sandbox during the request cycle. We handle authentication via a single endpoint token, ensuring your credentials aren't leaked.

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