How to Use the Zakeke MCP in CrewAI

Q: How does Zakeke help with initial product listing using CrewAI?

You assign a specialized agent to run listproducts. This agent then hands the resulting list of available items to other agents for further analysis, making the process totally autonomous.

Q: Can CrewAI use Zakeke to list all customer designs?

Yes. You give an agent the task of calling listdesigns. This operation populates the shared memory, allowing subsequent agents to build their findings upon that initial data set.

Q: What data types does the Zakeke MCP Server touch regarding privacy?

This server touches designdetails, which contain highly specific metrics about customized builds. Because the CrewAI runs autonomously, it's critical to monitor who has access to this detailed product configuration information.

Run autonomous e-commerce analysis using CrewAI with Zakeke's MCP Server.

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 CrewAI

Create your Vinkius account to connect Zakeke to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Research all available customization options

Need to scope out the project? Have one agent run `list_products` and another run `list_compositions`. This gives your crew a complete view of what's possible. The autonomous nature of CrewAI allows specialized agents—say, a 'Research Agent'—to gather this information without constant human prompting.

Analyze specific customer orders or designs

The crew can focus on deep dives. An 'Analysis Agent' uses `get_order_details` to pull full order records, while another agent pulls granular data using `get_design_details`. This specialization is key. The shared memory feature lets the agents pass these detailed findings—the results of the MCP Server calls—to the next agent in the sequence.

Generate final print files autonomously

When all analysis is done, the 'Action Agent' executes `get_design_print_files`. It takes the finalized design ID and retrieves the necessary ZIP file outputs. This completes the loop. The CrewAI framework manages this entire sequence: Research -> Analyze -> Act—all without needing manual intervention.

Setup guide

Set up Zakeke MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Zakeke tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Zakeke Analyst",
    goal="Access and analyze Zakeke data via MCP.",
    backstory="Expert analyst with direct Zakeke access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Zakeke transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Zakeke Analyst",
        goal="Access and analyze Zakeke data via MCP.",
        backstory="Expert analyst with direct Zakeke access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Zakeke transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You assign a specialized agent to run `list_products`. This agent then hands the resulting list of available items to other agents for further analysis, making the process totally autonomous.

A 'Moderator Agent' can take a batch of IDs and sequentially call `get_order_details` for each one. The crew handles the iteration, reporting out a consolidated status report.

Yes. You give an agent the task of calling `list_designs`. This operation populates the shared memory, allowing subsequent agents to build their findings upon that initial data set.

This server touches `design_details`, which contain highly specific metrics about customized builds. Because the CrewAI runs autonomously, it's critical to monitor who has access to this detailed product configuration information.

You configure a specialized agent whose sole job is to call `list_products`. This ensures the most accurate and up-to-date catalog data feeds into your autonomous pipeline.

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