How to Use the MarketMan MCP in OpenAI Agents SDK

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

Install the package using pip install openai-agents first. Then, initialize the server using MCPServerStreamableHttp with the Vinkius URL and pass it to your Agent constructor.

Q: Can OpenAI Agents SDK automatically check stock levels in MarketMan?

Yes. The agent uses listinventory over the MCP connection to pull current stock counts. It can run this check on a schedule or trigger it when a specific menu item runs low.

Q: How do I optimize tool discovery latency with this setup?

Enable cacheToolsList=True in your Python code. This caches the schema of tools like listcategories so your agents do not waste execution time querying the server on every run.

Give your OpenAI Agents SDK production system direct, safe access to live MarketMan inventory and food waste records.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MarketMan MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe menu cost auditing with OpenAI Agents SDK

Let your deployment run automated menu cost audits without worrying about bad actions. By using this MCP Server, your agents auto-discover tools like `list_recipes` and `list_inventory` directly from your MarketMan database. The built-in guardrails in your SDK validate every step before execution to prevent erratic purchasing decisions. You can set up specialized agents for menu engineering and let them hand off tasks to one another. One agent pulls the recipe lists while another cross-checks unit prices, keeping your operational data clean and your calculations accurate.

Real-time waste tracking with built-in guardrails

Stop letting money rot in the trash can. This integration lets your OpenAI Agents SDK monitor kitchen waste by executing `get_waste_events` directly from your live operations. You get instant visibility into what is being thrown out and why, without manual spreadsheet logging. Because you are running a production agent system, safety constraints are critical. The SDK ensures that agents only read waste data and cannot accidentally trigger unauthorized actions, giving you clean telemetry on food loss.

Automate procurement with strict agent tracing

Hand over vendor order tracking to your agents. They can use `list_purchase_orders` and `list_vendors` to check what was ordered versus what actually arrived at the loading dock. Every single tool call is traced in your OpenAI dashboard so you can audit the decisions. To keep performance snappy during heavy procurement cycles, use this MCP setup with `cacheToolsList=True` in your configuration. This prevents unnecessary network roundtrips when your agent checks vendor contracts or looks up active item prices.

Setup guide

Set up MarketMan 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 MarketMan tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package using `pip install openai-agents` first. Then, initialize the server using `MCPServerStreamableHttp` with the Vinkius URL and pass it to your Agent constructor.

Yes. The agent uses `list_inventory` over the MCP connection to pull current stock counts. It can run this check on a schedule or trigger it when a specific menu item runs low.

You define specialized agents—one for inventory and one for purchasing. The SDK allows the inventory agent to gather data using `get_count_sheets` and hand the context over to the purchasing agent to draft orders.

Enable `cacheToolsList=True` in your Python code. This caches the schema of tools like `list_categories` so your agents do not waste execution time querying the server on every run.

All API calls to fetch purchase orders or restaurant details go through Vinkius's secure sandbox. No raw credentials or supplier contract terms are stored on external servers, keeping your cost data isolated.

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