How to Use the Medusa (Headless E-commerce Engine) MCP in LangChain

Q: How do I chain Medusa (Headless E-commerce Engine) product lookups inside a LangChain agent?

Use MultiServerMCPClient to load the tools from this Medusa (Headless E-commerce Engine) MCP Server into your agent's runtime. The agent calls listproducts first, filters the results, and then passes the specific ID to getproduct in a single execution loop.

Q: What is the fastest way to register this MCP Server with my LangChain setup?

Install the adapter using pip install langchain-mcp-adapters langgraph. Then, point the client to the Vinkius endpoint URL and pass the output of client.gettools() directly to your agent constructor.

Run multi-step commerce workflows by chaining Medusa (Headless E-commerce Engine) tools directly inside your LangChain agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Medusa (Headless E-commerce Engine) MCP to LangChain

Create your Vinkius account to connect Medusa (Headless E-commerce Engine) 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 Medusa (Headless E-commerce Engine) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain store queries with LangChain

The `list_products` tool retrieves your catalog data directly into your active LangChain run. By reading this output, your agent filters items before calling `get_product` to fetch pricing and variant details. You do not need to hardcode the sequence of these calls. LangChain parses the inventory data and decides which product IDs to inspect next without human intervention.

Trace order captures with LangSmith

The `capture_payment` tool processes transactions while LangSmith traces the exact inputs and latency of the call. This gives you a clear log of every financial action triggered by your agent. If a payment fails, the trace shows whether the error came from the `get_order` payload or the gateway. You see the exact state of line items and shipping addresses before the failure occurred.

Build ReAct agents using this MCP Server

This MCP Server exposes tools like `list_orders` and `get_customer` to let your ReAct agent investigate support tickets. Instead of manual lookups, the agent checks order history and customer profiles in a single loop to resolve issues. By loading these tools into a MultiServerMCPClient, you combine customer CRM data with external shipping APIs. Your agent routes the gathered information to draft personalized email responses.

Setup guide

Set up Medusa (Headless E-commerce Engine) 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 Medusa (Headless E-commerce Engine) 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({
    "medusa-headless-e-commerce-engine-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 Medusa (Headless E-commerce Engine) 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 MedusaJS. 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 Medusa (Headless E-commerce Engine) 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 Medusa (Headless E-commerce Engine) MCP in LangChain

Use `MultiServerMCPClient` to load the tools from this Medusa (Headless E-commerce Engine) MCP Server into your agent's runtime. The agent calls `list_products` first, filters the results, and then passes the specific ID to `get_product` in a single execution loop.

Yes. LangSmith automatically traces the inputs and outputs of the `capture_payment` tool. You get a visual timeline of the execution, making it easy to debug failed transactions or slow response times.

LangChain agents are stateless by default, but you can maintain customer context by using `client.session()`. This keeps the retrieved data from `get_customer` active across multiple turns of the conversation.

Install the adapter using `pip install langchain-mcp-adapters langgraph`. Then, point the client to the Vinkius endpoint URL and pass the output of `client.get_tools()` directly to your agent constructor.

Vinkius runs the server in an isolated V8 sandbox, preventing any third-party access to customer profiles or payment status. No commerce data is stored on Vinkius servers; it merely acts as a secure, ephemeral pass-through to your store.

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