How to Use the Shoplazza / 店匠 MCP in OpenAI Agents SDK

Q: How do I use Shoplazza / 店匠 with OpenAI Agents SDK?

You set up the server using MCPServerStreamableHttp and pass it into your Agent constructor. Because of the built-in guardrails, the agent validates every action before running it, which is a huge plus for production systems.

Q: What kind of data can Shoplazza / 店匠 provide to OpenAI Agents SDK?

It provides everything from customer records (getcustomer) to real-time inventory counts (getinventorylevels). Since you're building a deployed product, the agent gets clean, reliable access points.

Q: If I need order data for Shoplazza / 店匠, which tools should I use with OpenAI Agents SDK?

Start by listing all orders using listorders. If you only care about one specific transaction, then call getorder and pass the relevant ID. It's a straightforward two-step process.

Q: When checking product details for Shoplazza / 店匠, what does the OpenAI Agents SDK handle?

It handles calling getproduct, which gives you all the necessary specs on an item. It's designed to take that raw data and make it usable within your agent's workflow.

Q: Does Shoplazza / 店匠 touch sensitive customer data when using OpenAI Agents SDK?

Yes, the server touches customer names and email addresses via getcustomer and listcustomers. Make sure your agents only access this data with explicit permissions.

Build production e-commerce agents for Shoplazza / 店匠 using your OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Shoplazza / 店匠 MCP to OpenAI Agents SDK

Create your Vinkius account to connect Shoplazza / 店匠 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 Shoplazza / 店匠 with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Manage product listings

Need to check what's on the shelves? You can pull specific item data with `get_product`, or list entire sets of items using `list_products`. This means you don't have to manually search for every single SKU when building out your agent logic. Want a broader view of your catalog? Call `list_collections` to get the names and groupings, then use `list_webhooks` if you need to know what external systems are attached to Shoplazza / 店匠.

Track customer activity

If your agent needs to follow up with a client, it can pull details using `get_customer`. You also get full visibility into who shopped recently by calling `list_customers`—so you know exactly who's in the system. For order history checks, use `list_orders` or drill down on a single transaction with `get_order`. This pair of tools lets your agent build a complete timeline for any specific buyer.

Check shop health and stock

Knowing the current status is key. Use `get_shop_info` to grab core details about the store itself, or check out what's on hand with `get_inventory_levels`. This tells your agent if a product can actually be sold right now. These tools let you build checks for both physical stock and system setup. You just pass the required IDs, and the agent gives you actionable data to proceed.

Setup guide

Set up Shoplazza / 店匠 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 Shoplazza / 店匠 tools at runtime.
3

Create your Agent

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

Run the agent

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

You set up the server using `MCPServerStreamableHttp` and pass it into your Agent constructor. Because of the built-in guardrails, the agent validates every action before running it, which is a huge plus for production systems.

It provides everything from customer records (`get_customer`) to real-time inventory counts (`get_inventory_levels`). Since you're building a deployed product, the agent gets clean, reliable access points.

Start by listing all orders using `list_orders`. If you only care about one specific transaction, then call `get_order` and pass the relevant ID. It's a straightforward two-step process.

It handles calling `get_product`, which gives you all the necessary specs on an item. It's designed to take that raw data and make it usable within your agent's workflow.

Yes, the server touches **customer names and email addresses** via `get_customer` and `list_customers`. Make sure your agents only access this data with explicit permissions.

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