How to Use the Zakeke MCP in LangChain

Q: How do I search past Zakeke orders using LangChain?

Your agent can use listorders to get a history list. You then feed specific order IDs into the chain, allowing you to call getorderdetails. The output is fully observable in your LangSmith trace.

Q: Can I compare designs and products with Zakeke using LangChain?

Absolutely. You can first use listdesigns to get a list of customer creations. Then, pass specific design IDs into the chain alongside calling listproducts. This lets you build comparison logic that checks available items against saved user work.

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

The server touches print-ready output files. You use the getdesignprintfiles tool to retrieve a ZIP file containing these outputs for a specific design ID.

Q: Is it possible to manage cart data with Zakeke and LangChain?

Yes, you can. Start by calling getcartinfo to get the current 3D configuration data. You then pass this raw output into subsequent steps of your chain for further processing or validation.

Q: What if I need a list of available products with Zakeke and LangChain?

Just use listproducts. This function returns all product SKUs available for customization. You can then pass this master list to other tools in your chain, like getdesigndetails, to narrow down options.

Build complex e-commerce workflows and decision chains with LangChain.

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 LangChain

Create your Vinkius account to connect Zakeke to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-step design retrieval

Need to know what a customer configured? The `get_design_details` tool pulls specific configuration data. You can chain this output directly into another step, maybe comparing it against the results of calling `list_compositions` for context. This lets your ReAct agent build complex reasoning paths. It doesn't just call one function; it decides which functions to run and in what order based on the intermediate data it collects.

Order history processing

Your chain can check customer orders using `list_orders`. The output—the list of custom product purchases—can then feed into a second tool. For example, you might pass an order ID to `get_order_details` to validate the items. This structure is perfect for billing or support agents. You're building multi-step logic where one API call confirms data needed by the next part of your workflow.

Product and cart validation

A key use case involves verifying a customer's current selection. The `get_cart_info` tool reads the 3D configuration details, providing raw data you can pass along. You might immediately follow this with calling `get_composition_details` to get specific technical specs. This sequential process is how your agent validates inputs before proceeding. It uses the structured output of one MCP Server call as input for the next.

Setup guide

Set up Zakeke MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Zakeke tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "zakeke-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Zakeke transactions"
    })
    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 LangChain

Your agent can use `list_orders` to get a history list. You then feed specific order IDs into the chain, allowing you to call `get_order_details`. The output is fully observable in your LangSmith trace.

Absolutely. You can first use `list_designs` to get a list of customer creations. Then, pass specific design IDs into the chain alongside calling `list_products`. This lets you build comparison logic that checks available items against saved user work.

The server touches print-ready output files. You use the `get_design_print_files` tool to retrieve a ZIP file containing these outputs for a specific design ID.

Yes, you can. Start by calling `get_cart_info` to get the current 3D configuration data. You then pass this raw output into subsequent steps of your chain for further processing or validation.

Just use `list_products`. This function returns all product SKUs available for customization. You can then pass this master list to other tools in your chain, like `get_design_details`, to narrow down options.

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