Skip to main content
Glama

Vendure MCP Server

Official

Vendure MCP Server

A standalone Model Context Protocol (MCP) server for Vendure CLI orchestration. This package runs on a per-project basis, allowing external clients like Cursor to interact with your local Vendure project's CLI commands in a programmatic and context-aware way.

Features

  • Deep Project Integration: Operates directly within your Vendure project, providing context-aware tooling.
  • CLI Integration: Direct access to Vendure CLI add and migrate commands.
  • Project Analysis: Analyze project structure, list plugins, entities, and services.
  • Dual Transport Support: Connect via standard I/O (STDIO) for local clients like Cursor or via HTTP for networked clients.
  • Environment Check: Verify Vendure installation and dependencies within the project.
  • Real-time: Works with any local Vendure project without modification.

Installation and Setup Workflow

The server is designed to be installed and run directly from your Vendure project. This ensures it always has access to the correct dependencies and project context.

Step 1: Install in Your Vendure Project

Navigate to your Vendure project's root directory and install the server as a development dependency:

In your Vendure project's root directory

npm install @vendure/mcp-server --save-dev

Step 2: Configure Your MCP Client (e.g., Cursor)

Create or update the mcp.json file used by your MCP client. This file is typically located at .cursor/mcp.json inside your project's root folder.

Below are configurations for both STDIO and HTTP connections.

This is the simplest and most direct way to connect.

{ "mcpServers": { "vendure": { "command": "npx", "args": [ "--package", "@vendure/mcp-server", "vendure-mcp", "--projectPath", "/path/to/your/vendure-project" ] } } }

Note: You must replace /path/to/your/vendure-project with the absolute path to your Vendure project's root directory.

Option 2: HTTP Connection

If your client does not support STDIO or you need to connect over a network, you can run the server in HTTP mode.

First, start the server from your terminal in your Vendure project's root directory:

npx vendure-mcp --transport http --projectPath .

This will start the server on the default port (8000), you can explicitly define the port by using the --port <0000> flag.

Then, configure your mcp.json to connect to the running server's URL:

{ "mcpServers": { "vendure": { "command": "http://localhost:8000/mcp" } } }

Dynamic CLI Integration

The server dynamically generates MCP tools from your project's installed Vendure CLI command definitions. This ensures:

  • Single Source of Truth: CLI changes automatically reflect in MCP tools.
  • Type Safety: Full TypeScript integration with proper parameter validation.
  • Future-proof: New CLI commands and options become available automatically.
  • No Hallucinations: The code generated by the tools will always be correct, as it's based on the actual CLI definitions in your project.

Development

If you are contributing to the vendure-mcp-server itself, you'll want to run it from the source code.

Build from Source

git clone https://github.com/vendure-ecommerce/mcp.git cd vendure-mcp-server # Or the correct directory name npm install npm run build

Development Mode

To connect an MCP client to your local development server, use the npm run dev script and point it to a test Vendure project. You can run it in either STDIO or HTTP mode.

  • STDIO Mode: npm run dev -- --projectPath /path/to/your/test-vendure-project
  • HTTP Mode: npm run dev:http -- --projectPath /path/to/your/test-vendure-project

Configure your mcp.json as described in the setup section to connect to your development server. The -- is required to pass arguments to the npm script correctly.

Install Server
A
security – no known vulnerabilities
F
license - not found
A
quality - confirmed to work

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

A standalone server that enables programmatic interaction with Vendure CLI commands, allowing external MCP clients to automate and integrate with Vendure e-commerce projects through command execution and project analysis.

  1. Features
    1. Installation and Setup Workflow
      1. Step 1: Install in Your Vendure Project
      2. Step 2: Configure Your MCP Client (e.g., Cursor)
    2. Dynamic CLI Integration
      1. Development
        1. Build from Source
        2. Development Mode
      2. Links

        Related MCP Servers

        • A
          security
          F
          license
          A
          quality
          A TypeScript-based MCP server designed for experimentation and integration with Calude Desktop and Cursor IDE, offering a modular playground for extending server capabilities.
          Last updated -
          2
          705
          4
          JavaScript
        • -
          security
          F
          license
          -
          quality
          This is an MCP server that facilitates building tools for interacting with various APIs and workflows, supporting Python-based development with potential for customizable prompts and user configurations.
          Last updated -
          Python
        • -
          security
          A
          license
          -
          quality
          An MCP server that enables dynamic tool registration and execution based on API definitions, providing seamless integration with services like Claude.ai and Cursor.ai.
          Last updated -
          7
          Python
          MIT License
          • Apple
        • -
          security
          F
          license
          -
          quality
          An MCP Server that provides access to the Jumpseller e-commerce platform API, allowing users to interact with Jumpseller's functionality through natural language commands.
          Last updated -
          Python
          • Linux
          • Apple

        View all related MCP servers

        MCP directory API

        We provide all the information about MCP servers via our MCP API.

        curl -X GET 'https://glama.ai/api/mcp/v1/servers/vendure-ecommerce/mcp'

        If you have feedback or need assistance with the MCP directory API, please join our Discord server