How to Use the Zakeke MCP in AutoGen

Q: Is it possible to validate product lists with Zakeke and AutoGen?

Absolutely. You can set up a 'Validator Agent' that uses listproducts as its source of truth. Other agents then challenge any proposed configuration against this list, ensuring all components are valid.

Q: What data does the Zakeke MCP Server touch regarding cart information?

The server touches 3D configuration data via getcartinfo. Agents can use this output to debate if the current cart state is optimal or needs adjustments based on external business rules.

Run multi-agent debates on complex Zakeke e-commerce decisions with AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Zakeke MCP to AutoGen

Create your Vinkius account to connect Zakeke 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 Zakeke with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Simulating order fulfillment checks

The `get_order_details` tool provides the baseline data. You can set up agents—say, a 'Fulfillment Agent' and an 'Inventory Agent'—to debate if an order is ready to ship. The raw output of this MCP Server call becomes the core evidence for their discussion. This simulates real-world decision making where multiple perspectives must agree on one conclusion. It moves beyond simple execution into genuine deliberation.

Validating custom product configurations

Use `get_cart_info` to gather the current 3D setup. You then pass this data to a 'Compliance Agent' and a 'Technical Agent.' They debate whether the configuration meets all necessary technical specs, using the structured output as their basis for disagreement or consensus. This is where AutoGen shines. The system doesn't just run tools; it forces competing AI perspectives to argue until they converge on a final decision.

Comparing multiple design lists

Want to know if a customer's custom design works with existing products? You can have agents debate using `list_designs` and `list_products`. One agent might argue that the design is too complex, while another uses the master product list to find alternatives. This consensus-driven approach allows you to build systems where the answer requires multiple points of view—something simple function calling never achieves.

Setup guide

Set up Zakeke 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 Zakeke 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="Zakeke_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Zakeke 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="Zakeke_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Zakeke 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 Zakeke. 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 Zakeke 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 Zakeke MCP in AutoGen

You give the initial facts, like an Order ID, to the Assistant Agent. The agents then debate the status of that order by calling `get_order_details`. They argue over shipping details or payment validation until they reach a final consensus.

Yes, it's built for this. You can set up agents to debate the viability of a design using `get_design_details` and comparing that output against what is available via `list_compositions`. The discussion leads to an actionable assessment.

The server handles print-ready outputs. You can task agents with checking if a design has corresponding print files by calling `get_design_print_files`. The debate centers on whether the provided ZIP content is sufficient for production.

Absolutely. You can set up a 'Validator Agent' that uses `list_products` as its source of truth. Other agents then challenge any proposed configuration against this list, ensuring all components are valid.

The server touches 3D configuration data via `get_cart_info`. Agents can use this output to debate if the current cart state is optimal or needs adjustments based on external business rules.

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