How to Use the PrestaShop MCP in LangChain

Q: How do I pass PrestaShop tool schemas into a LangChain agent?

Install the langchain-mcp-adapters package and initialize the MCP client with your Vinkius endpoint. You then call client.gettools() to get the schemas for listproducts and other endpoints, passing them directly to your agent constructor.

Run multi-step chains with LangChain to inspect orders and pull stock counts from your PrestaShop store.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect PrestaShop MCP to LangChain

Create your Vinkius account to connect PrestaShop to LangChain — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup PrestaShop with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Chain PrestaShop lookups inside your LangChain pipelines

The `list_products` tool lets your agent pull items from the store catalog to feed directly into the next step of your chain. You can pass that output into `get_product` inside a LangChain runnable to fetch pricing and categories without writing custom wrappers. It makes catalog exploration fast. This MCP Server works with LangChain's tracing tools so you can watch data move from node to node. If a customer asks for an item, your agent checks the catalog, pulls the product ID, and passes it to the next tool in line. You get clean execution logs for every catalog query.

Map fulfillment runs with LangChain agents

The `list_orders` tool retrieves active sales and passes the raw totals and statuses directly to your LangChain agent. Your agent can immediately parse that list and call `get_order` to map line items and payment states. It simplifies order tracking. Connecting this MCP Server to your runnables lets you trace exactly how many tokens your agent uses when it pulls customer records. You get full visibility into the exact payloads moving through your LangChain chains. No guesswork.

Track inventory levels across active chains

The `list_stock` tool pulls exact physical units from your warehouse database to verify actual availability. When LangChain triggers this tool, it passes the stock trace items directly to your agent to evaluate standard rules versus custom overrides. It keeps your stock data accurate. You can use `get_stock` in a LangGraph state machine to automatically pause processing if inventory drops below a specific threshold. This keeps your automated fulfillment loops accurate without manual inventory checks. It just works.

Setup guide

Set up PrestaShop 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 PrestaShop 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({
    "prestashop-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 PrestaShop 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 PrestaShop. 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 PrestaShop 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 PrestaShop MCP in LangChain

Install the `langchain-mcp-adapters` package and initialize the MCP client with your Vinkius endpoint. You then call `client.get_tools()` to get the schemas for `list_products` and other endpoints, passing them directly to your agent constructor.

Yes, because this server integrates with LangSmith. Every time your agent runs `get_order` or `list_stock`, you can view the exact latency, token usage, and payload data in your LangSmith dashboard.

Your LangChain chains should include retry logic or token bucket rate limiters. If `list_customers` or `list_addresses` returns a rate limit error, the framework can catch the exception and pause before retrying.

Yes, you can combine this MCP Server's tools with database or vector store tools in the same LangChain agent. The agent will decide whether to pull data via `get_product` or search an external database based on the user's prompt.

Vinkius runs this integration inside a zero-trust, ephemeral V8 Isolate sandbox. Your PrestaShop customer records, shipping addresses, and order details are never stored on Vinkius servers, and all API traffic is encrypted in transit.

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