How to Use the Sellfy MCP in OpenAI Agents SDK

Q: How do I connect the Sellfy MCP Server to my OpenAI Agents SDK project?

You'll instantiate the MCPServerStreamableHttp class with your Vinkius URL. Then, just pass that server object into the mcpservers list when you create your agent. The tools are discovered automatically.

Q: Can my agent add products to my Sellfy store without me logging in?

Yes, that's what the createproduct tool is for. Your agent can call it with a product title and price to create a new listing in your store.

Q: Is it safe to let an OpenAI agent manage my Sellfy orders?

It is. The tools for orders, listorders and getorderdetails, are read-only. Your agent can't change or delete existing orders, so it's perfect for safe reporting and data synchronization tasks.

Q: What's the best way to get all my Sellfy product data with the OpenAI Agents SDK?

Use the listproducts tool to get the full catalog. For detailed information, you can then have your agent loop through the results and call getproductdetails for each item. Set cacheToolsList=True in your setup for better performance on repeated calls.

Build production-ready Sellfy agents with the OpenAI Agents SDK, complete with built-in safety checks and full tracing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sellfy MCP to OpenAI Agents SDK

Create your Vinkius account to connect Sellfy to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Sellfy with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Create Sellfy Products from Anywhere

This MCP server gives your agent a `create_product` tool. You can now build workflows that add new products to your store programmatically, triggered by anything from a webhook to a new file in a folder. Here's the thing: the OpenAI Agents SDK lets you define guardrails. This means you can enforce rules—like price limits or required fields—before your agent ever calls the tool. It prevents bad data from ever hitting your live store.

Sync Store Data with OpenAI Guardrails

Pulling business data is the main job here. Your agent can use `list_orders` to get recent sales or `list_customers` to see your customer base. Then it can dig into specifics with `get_order_details` or `get_customer_details`. You can build specialized agents and hand off tasks between them. For example, an 'accounting agent' could have permission for order tools, while a 'marketing agent' gets customer tools. The OpenAI dashboard gives you a full trace of which agent did what.

Monitor Your Sellfy Store in Real-Time

Build an agent that keeps an eye on your store's health. It can use `get_store_information` for high-level status and `list_store_coupons` to check on active discounts. You can have it periodically run `list_products` to check for inventory changes. Every action your agent takes is logged and traceable in the OpenAI platform. This gives you a complete audit trail, so you always know what your automated systems are doing on your behalf. It's the right way to manage a production MCP integration.

Setup guide

Set up Sellfy 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 Sellfy tools at runtime.
3

Create your Agent

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

Run the agent

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

You'll instantiate the `MCPServerStreamableHttp` class with your Vinkius URL. Then, just pass that server object into the `mcp_servers` list when you create your agent. The tools are discovered automatically.

Yes, that's what the `create_product` tool is for. Your agent can call it with a product title and price to create a new listing in your store.

It is. The tools for orders, `list_orders` and `get_order_details`, are read-only. Your agent can't change or delete existing orders, so it's perfect for safe reporting and data synchronization tasks.

Use the `list_products` tool to get the full catalog. For detailed information, you can then have your agent loop through the results and call `get_product_details` for each item. Set `cacheToolsList=True` in your setup for better performance on repeated calls.

The server provides access to customer names, email addresses, and order history through the `list_customers` and `get_customer_details` tools. Vinkius runs each MCP server in an ephemeral, zero-trust sandbox. Your data is only streamed to the agent for the duration of the request and is not stored.

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