How to Use the Medusa (Headless E-commerce Engine) MCP in OpenAI Agents SDK

Q: How do I configure the Medusa (Headless E-commerce Engine) MCP Server with OpenAI Agents SDK?

Use MCPServerStreamableHttp to connect the endpoint. Pass this server in the mcpservers list of your Agent constructor and set cacheToolsList=True to optimize tool discovery.

Q: Can OpenAI Agents SDK handle multi-region pricing using this integration?

Yes. The agent calls listregions to identify tax rates and active payment providers, then pulls details with getstoreconfig to match the customer's local currency.

Q: Does the Medusa (Headless E-commerce Engine) MCP Server support customer CRM lookups with OpenAI Agents SDK?

Absolutely. Your agent uses listcustomers and getcustomer to retrieve profiles, which allows it to resolve support issues with accurate customer history.

Drive your Medusa storefront using OpenAI Agents SDK and our managed MCP Server to run safe, multi-agent operations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Medusa (Headless E-commerce Engine) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Medusa (Headless E-commerce Engine) 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 Medusa (Headless E-commerce Engine) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe payment capturing via OpenAI Agents SDK

The `capture_payment` tool lets your agent process order payments directly inside your Python backend. Because OpenAI Agents SDK enforces runtime guardrails, your MCP tool calls won't execute payment captures without meeting safety parameters. You track every single transaction state directly inside the OpenAI developer dashboard. This prevents runaway loops and ensures your store's financial data remains consistent with your Medusa ledger.

Multi-agent product and collection cataloging

The `list_products` and `list_collections` tools expose your inventory metadata to specialized agents. One agent can read raw product variants via `get_product`, while another handles currency localization using `list_regions`. Handoffs occur automatically behind the scenes. This architecture keeps your catalog management isolated from customer support flows, ensuring high-throughput operations.

Order auditing with built-in tracing

The `get_order` tool pulls complete line items, shipping details, and fulfillment states into your agent's context. When a customer asks about a delivery, your agent queries `list_orders` to find the exact ID. Every step of this order lookup is recorded in your telemetry. If an agent misinterprets a billing address, you can trace the exact prompt and response payload inside your log suite.

Setup guide

Set up Medusa (Headless E-commerce Engine) 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 Medusa (Headless E-commerce Engine) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Medusa (Headless E-commerce Engine) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Medusa (Headless E-commerce Engine) 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="Medusa (Headless E-commerce Engine) Agent",
            instructions="You have access to Medusa (Headless E-commerce Engine) 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 MedusaJS. 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 Medusa (Headless E-commerce Engine) 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 Medusa (Headless E-commerce Engine) MCP in OpenAI Agents SDK

Use `MCPServerStreamableHttp` to connect the endpoint. Pass this server in the `mcp_servers` list of your Agent constructor and set `cacheToolsList=True` to optimize tool discovery.

Yes. The agent calls `list_regions` to identify tax rates and active payment providers, then pulls details with `get_store_config` to match the customer's local currency.

Absolutely. Your agent uses `list_customers` and `get_customer` to retrieve profiles, which allows it to resolve support issues with accurate customer history.

Define strict guardrail functions inside your OpenAI Agents SDK configuration. These guardrails intercept the tool call, validating the order state before the payment is captured.

Customer profiles and order details are processed entirely within ephemeral V8 sandboxes. No customer emails, phone numbers, or addresses retrieved by `get_customer` are ever stored on Vinkius servers.

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