How to Use the Wherefour MCP in OpenAI Agents SDK

Q: What kind of data does Wherefour handle with OpenAI Agents SDK?

It manages core business data, including customer records (listcustomers), inventory details (searchinventory), and financial documents like invoices. Your agent can access structured lists across the board.

Q: Can I check stock using Wherefour with OpenAI Agents SDK?

Absolutely. You call listinventoryitems or use getinventoryitem if you know the specific SKU. This allows your agent to provide real-time stock data directly into a conversation or report.

Q: Does Wherefour support production usage with OpenAI Agents SDK?

Yes, it's built for deployment. You use the MCPServerStreamableHttp context manager and set cacheToolsList=True. This setup is designed to handle high-volume, reliable agent execution.

Process complex inventory and order logic with your AI client using OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Wherefour MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Check current stock levels instantly

The `list_inventory_items` tool lets you see everything sitting in stock. You get a full list of all items, making it easy to know what's available before promising anything. Need to narrow the focus? Use `search_inventory` to filter down the results by name or part number. This saves time and keeps your agent from getting bogged down in irrelevant data.

Manage customer sales records

Want to know what a client owes you? Call `list_invoices` with their ID, and the system pulls up all outstanding bills. You can then cross-reference this by checking historical orders using `get_order`. Don't forget about who they are in the first place. The `list_customers` tool gives you a complete roster of every account, helping your agent keep track of relationships and payments.

Track materials from purchase to sale

The system tracks everything using purchasing data. Running `list_purchases` shows exactly what raw materials came in the door and when they arrived. It’s a good way to audit supplier records against your internal needs. Pairing this with `get_inventory_item` lets you see how much of those purchased goods actually made it into usable stock, giving you true end-to-end visibility.

Setup guide

Set up Wherefour 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 Wherefour tools at runtime.
3

Create your Agent

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

Run the agent

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

You pass the MCP Server object directly to the Agent constructor. Since it's an auto-discovered toolset, your agent automatically knows how to call functions like `list_orders` without you having to write wrapper code for every single function.

It manages core business data, including customer records (`list_customers`), inventory details (`search_inventory`), and financial documents like invoices. Your agent can access structured lists across the board.

Absolutely. You call `list_inventory_items` or use `get_inventory_item` if you know the specific SKU. This allows your agent to provide real-time stock data directly into a conversation or report.

Yes, it's built for deployment. You use the `MCPServerStreamableHttp` context manager and set `cacheToolsList=True`. This setup is designed to handle high-volume, reliable agent execution.

The server touches customer payment and order history data. All communication flows through the Vinkius platform using a zero-trust model, requiring an endpoint token for every interaction.

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