How to Use the ItemPath MCP in OpenAI Agents SDK

Q: How do I configure the ItemPath MCP Server inside the OpenAI Agents SDK?

Install the package using pip install openai-agents and initialize the server with MCPServerStreamableHttp(params=MCPServerStreamableHttpParams(url="your-vinkius-endpoint")). Pass the server instance into your Agent constructor using the mcpservers parameter. The SDK automatically discovers all 10 tools, including listmaterials and listorders.

Q: How do I optimize the performance of ItemPath lookups in my python script?

Set cacheToolsList=True when initializing your connection to prevent the SDK from fetching the tool definitions on every single message turn. This reduces latency significantly when your agent frequently calls listlocations to map warehouse storage layouts.

Run production-ready inventory agents with the OpenAI Agents SDK using direct, guardrailed access to ItemPath warehouse data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ItemPath MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guardrailed ItemPath inventory queries with OpenAI Agents SDK

`list_materials` serves as the foundation for your agent to inspect inventory items before executing any warehouse logic. Your Python agent automatically registers this tool alongside `get_material` to fetch SKU details and quantity-on-hand without manual schema mapping. The OpenAI SDK validates these tool calls against built-in guardrails before execution. You track every single transaction and material inspection directly inside your OpenAI developer dashboard using this MCP Server connection.

Trace order fulfillment cycles through agent handoffs

`list_orders` lets your specialized fulfillment agent track warehouse throughput and current order statuses in real time. One agent monitors the queue, then hands off the task to a shipping agent once the order status changes. The second agent invokes `get_order` to pull target locations and picker details. This multi-agent coordination happens within a single session, keeping your warehouse pipeline organized and fully traceable.

Audit stock transactions with cached tool discovery

`list_transactions` exposes raw inventory changes, timestamps, and user IDs to your auditing agent for instant verification. Setting `cacheToolsList=True` in the MCP Server configuration speeds up tool discovery, making these frequent lookup calls fast. Your agent cross-references these transactions with `list_users` to attribute stock movements to specific warehouse floor operators. This setup runs inside an asynchronous context manager, ensuring connection pools close cleanly after each audit.

Setup guide

Set up ItemPath 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 ItemPath tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package using `pip install openai-agents` and initialize the server with `MCPServerStreamableHttp(params=MCPServerStreamableHttpParams(url="your-vinkius-endpoint"))`. Pass the server instance into your Agent constructor using the `mcp_servers` parameter. The SDK automatically discovers all 10 tools, including `list_materials` and `list_orders`.

The OpenAI SDK registers all discovered tools by default, but you can restrict access by setting up separate agent instances with specific system instructions. Assign `get_order` and `list_orders` only to your fulfillment agent, while leaving `list_transactions` for your auditing agent. This prevents agents from invoking tools outside their designated operational scope.

The SDK relies on JSON-RPC schemas exposed by the server to generate tool definitions for the model. When your agent calls `get_material`, the SDK validates the arguments against the expected SKU format before sending the request. This runtime validation stops malformed API calls from hitting your warehouse database.

Set `cacheToolsList=True` when initializing your connection to prevent the SDK from fetching the tool definitions on every single message turn. This reduces latency significantly when your agent frequently calls `list_locations` to map warehouse storage layouts.

No, because Vinkius runs the server in an isolated, zero-trust sandbox that only passes tool execution results back to your local SDK client. Your warehouse data, including material quantities from `get_material` and order details, is processed in memory and never stored by the proxy.

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