How to Use the MarketMan MCP in AutoGen

Q: How do I load MarketMan tools into AutoGen?

Use mcpservertools with your endpoint URL. Pass the resulting tool list to your AssistantAgent constructor. The adapter handles the schema conversion.

Q: Can AutoGen agents debate MarketMan inventory counts?

Yes. One agent pulls getcountsheets while another pulls getrestaurantinfo. They cross-reference location data and argue over discrepancies before presenting a final audit.

Q: Can the agents update my recipe costs automatically?

The tools are read-only. Your agents analyze listcategories and recipe data to recommend menu price changes, but they cannot overwrite your live specs.

Let AutoGen agents debate and optimize your MarketMan food costs.

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 AutoGen

Create your Vinkius account to connect MarketMan to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

AutoGen multi-agent cost analysis

One agent checks the numbers. Another agent challenges them. You set up a procurement agent that reads `list_purchase_orders` and a finance agent that checks `list_inventory`. They argue over the variance. The procurement agent says you bought enough chicken. The finance agent points out the stock is gone. They negotiate a conclusion and hand you a verified report.

Audit waste against recipe specs

You need to know why yields are down. Your culinary agent pulls the exact plate builds using `list_recipes`. Your operations agent pulls the trash logs using `get_waste_events`. They compare the theoretical yield against the actual garbage. If prep staff are trimming too much fat off the steaks, the agents flag the discrepancy. You get a targeted training plan for the morning shift.

Manage vendor relations via MCP Server

Vendor pricing creeps up on you. You connect this MCP Server and let your agents fetch the current supplier list using `list_vendors`. They cross-check those vendors against recent invoices. A compliance agent verifies the pricing matches your contracted rates. If a supplier sneaks a price hike into a recent delivery, the agents catch it. You hold the vendor accountable.

Setup guide

Set up MarketMan MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes MarketMan tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="MarketMan_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent MarketMan data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="MarketMan_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent MarketMan data")
    print(result.messages[-1].content)

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 AutoGen

Use mcp_server_tools with your endpoint URL. Pass the resulting tool list to your AssistantAgent constructor. The adapter handles the schema conversion.

Yes. One agent pulls `get_count_sheets` while another pulls `get_restaurant_info`. They cross-reference location data and argue over discrepancies before presenting a final audit.

No. The McpToolAdapter translates the raw JSON into something the agents understand. They read the data and start deliberating immediately.

The tools are read-only. Your agents analyze `list_categories` and recipe data to recommend menu price changes, but they cannot overwrite your live specs.

Your raw inventory counts are never stored. The server runs in an ephemeral V8 sandbox that dies after the request. The data flows securely to your agents and nowhere else.

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