Vendure MCP Server

Vendure MCP Server

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.

Category
访问服务器

Tools

vendure_add

Add features to your Vendure project. IMPORTANT USAGE PATTERNS: - For API Extension: Requires apiExtension="plugin-name", plus queryName OR mutationName, plus selectedService - For Entity: Requires entity="EntityName" and selectedPlugin="plugin-name" - For Service: Requires service="ServiceName" and selectedPlugin="plugin-name" - For Job Queue: Requires jobQueue="plugin-name", name="queue-name", and selectedService="service-name" EXAMPLES: - Add API extension: {apiExtension: "my-plugin", queryName: "customProducts", selectedService: "ProductService"} - Add entity: {entity: "CustomProduct", selectedPlugin: "my-plugin"} - Add service: {service: "CustomService", selectedPlugin: "my-plugin"} - Create new plugin: {plugin: "MyNewPlugin"} Use list_plugins tool first to see available plugin names.

vendure_migrate

Generate, run or revert a database migration

list_commands

List all available Vendure CLI commands accessible via MCP

vendure_add_help

Get detailed guidance on how to use the vendure_add tool with correct parameter combinations

list_plugins

List all plugins in the Vendure project by analyzing the project structure

analyze_project_structure

Analyze the overall structure of a Vendure project including entities, services, and configuration

check_vendure_installation

Check if Vendure CLI is properly installed and what version is available in the project

README

Vendure MCP Server

A standalone Model Context Protocol (MCP) server for Vendure CLI orchestration. This independent package allows external clients to interact with Vendure CLI commands in a programmatic way, enabling automation and integration with various MCP clients like Cursor.

Features

  • CLI Integration: Direct access to Vendure CLI add and migrate commands.
  • Project Analysis: Analyze project structure, list plugins, entities, and services.
  • Environment Check: Verify Vendure installation and dependencies.
  • Dual Transport: Support for both STDIO and HTTP transport protocols.
  • Real-time: Works with any Vendure project without modification.

Installation

From npm (Recommended)

Install globally for easy access

npm install -g @vendure/mcp-server

Or install locally in your project

npm install @vendure/mcp-server

From Source

git clone https://github.com/vendure-ecommerce/mcp.git
cd vendure-mcp
npm install
npm run build

Usage and Configuration

This guide provides instructions for both end-users (using the published npm package) and developers (working from the source code).

For End-Users (Published Package)

If you have installed the server from npm, you can use npx to run it without requiring a global installation.

MCP Client Configuration

Add the following to your MCP client's configuration file:

If you have installed the package globally (npm install -g @vendure/mcp-server), you can add it directly in your mcp.json:

{
  "mcpServers": {
    "vendure": {
      "command": "npx",
      "args": ["@vendure/mcp-server"]
    }
  }
}

This command will automatically download and run the latest version of the server.

Starting the HTTP Server

If you have installed the package locally, you would have to run it on a server:

vendure-mcp --transport http --port 8000

Your mcp.json should then look like this:

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

For Developers (Local Source)

When developing the server, you should run it directly from the source code to ensure you are using your latest changes.

MCP Client Configuration (Development)

To connect your MCP client to the local development server, configure it to use the npm run dev script. This provides live reloading for a smoother development experience.

{
  "mcpServers": {
    "vendure-dev": {
      "command": "npm",
      "args": ["run", "dev"],
      "cwd": "/path/to/your/vendure-mcp/project"
    }
  }
}

Note: Ensure the cwd (current working directory) points to the root of this project.

Starting the Dev Server Manually

You can also run the development server directly from your terminal:

# Start STDIO dev server with live-reloading
npm run dev

# Start HTTP dev server with live-reloading
npm run dev:http

Available Tools

1. vendure_add

2. vendure_migrate

3. list_plugins

4. analyze_project_structure

5. check_vendure_installation

Dynamic CLI Integration

The server dynamically generates MCP tools from 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, specifically the cli tools will always be correct.

Development

Building from Source

git clone https://github.com/vendure-ecommerce/mcp.git
cd vendure-mcp
npm install
npm run build

Development Mode

STDIO mode

npm run dev

HTTP mode

npm run dev:http

License

This project is licensed under the MIT License - see the LICENSE.md file for details.

Error Handling

Comprehensive error handling includes:

  • Project path validation
  • Vendure CLI availability checks
  • Parameter validation with detailed messages
  • CLI execution error forwarding
  • File system operation safety

Security

  • Path validation: Prevents directory traversal attacks
  • Input sanitization: All parameters validated against schemas
  • Isolated execution: Commands run in specified project directories only
  • No elevated privileges: Runs with standard user permissions

Contributing

Follow our contributing guide in our main repository.

Links

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选