PrestaShop MCP (Legacy WebService)

PrestaShop MCP (Legacy WebService)

Enables AI assistants to read and manage PrestaShop catalogs via the legacy WebService API, covering products, categories, stock, and more across PrestaShop 1.6-9. Provides 45 tools for CRUD operations and read-only generic access.

Category
Visit Server

README

PrestaShop MCP (Legacy WebService)

An MCP server that lets an AI assistant (Claude, Cursor, …) read and manage a PrestaShop catalog through the legacy WebService API (XML) — the API that older and current shops alike still expose. Works on PrestaShop 1.6, 1.7, 8, and 9.

45 tools: categories, features, attributes, products, combinations, stock, warehouses, plus read-only access to any resource the API key allows (customers, orders, cart rules, …).

Why this one — and when to use the official MCP instead

PrestaShop ships an official MCP built on the PS 9 Admin API (OAuth2). That's the right choice for a modern PS 9 shop you fully control. This server is for the cases it doesn't cover:

This server (legacy WebService) Official MCP (Admin API)
Transport Legacy WebService API (XML) PS 9 Admin API (API Platform / OAuth2)
PrestaShop versions 1.6 → 9 PS 9+ only
Auth WebService API key (per-resource permissions) OAuth2 client
Warehouse stock (/stocks) ✅ incl. PShowAdvancedStockWarehouses varies
Setup one API key + a .env OAuth2 app registration

Use the official MCP if you're on PS 9 and want the supported, forward-looking path. Use this if you're on PS 1.6/1.7/8, or you already have a WebService key, or you need the legacy /stocks warehouse flow.

Install

Requires Python 3.10+.

git clone https://github.com/Breczek/prestashop-mcp-legacy
cd prestashop-mcp-legacy
pip install -r requirements.txt
cp .env.example .env      # then fill in PS_SHOP_URL and PS_API_KEY

The server reads .env from the current working directory, so each shop/project keeps its own credentials.

Claude Code — run it from the project directory that holds the .env, and register the server (e.g. in ~/.claude/settings.json or via claude mcp add):

{
  "mcpServers": {
    "prestashop": { "command": "python3", "args": ["/abs/path/prestashop-mcp-legacy/server.py"] }
  }
}

Claude Desktop / Cursor — same config, but set the working directory to the folder containing .env (these clients launch the server themselves):

{
  "mcpServers": {
    "prestashop": {
      "command": "python3",
      "args": ["/abs/path/prestashop-mcp-legacy/server.py"],
      "cwd": "/abs/path/to/your/shop-project"
    }
  }
}

Security & permissions — read before connecting a live shop

This server can write to your shop — create, update, and delete categories, prices, stock, and combinations — and the AI assistant decides when to call those tools. Treat it accordingly:

  • Use a least-privilege API key. Grant only the resources you actually need. The key's permissions are the real security boundary — the generic ps_query tool can read any resource the key allows.
  • Prefer a staging shop for anything experimental. Deletes are permanent.
  • Generic access is read-only. ps_query / ps_get_record are strictly GET; there is no generic write tool. Writes go only through the specific, named tools.
  • Sensitive fields are redacted before they ever reach the model: passwd, secure_key, reset_password_token, api_key, checksum.
  • Your API key is never logged. The optional local log records only action / resource / id / HTTP status.
  • Requests use a 30s timeout and verify TLS by default.

Tools (45)

  • Catalog: categories, features + values, attribute groups + values, products (list/find/get/activate/price), combinations (list/get/find/update/ assign image).
  • Stock: stock_available get/update; warehouse /stocks list/create/update.
  • Reference: warehouses, manufacturers, languages.
  • Generic (read-only): ps_api_resources, ps_schema, ps_query, ps_get_record, ps_search, ps_resource_guide, ps_product_images, plus convenience readers for customers, orders, and cart rules.

Run ps_verify first to confirm the connection and see which resources your key exposes.

Requirements

  • Python 3.10+, mcp[cli], requests (see requirements.txt).
  • A PrestaShop shop with the WebService enabled and an API key.
  • Warehouse /stocks tools assume the PShowAdvancedStockWarehouses setup.

Contributing

PrestaShop's WebService varies across versions and plugins — corrections and additions welcome. Open an issue or PR with your PS version.

License

MIT.

Author

Marcin Bręczewski (@Breczek) — PrestaShop development and AI tooling.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured