MCP Harbor

MCP Harbor

MCP Harbor is a Node.js application that provides a Model Context Protocol (MCP) server for interacting with Harbor container registry.

Category
访问服务器

README

MCP Harbor

License: MIT TypeScript Node.js codecov

MCP Harbor is a Node.js application that provides a Model Context Protocol (MCP) server for interacting with Harbor container registry.

Table of Contents

Features

  • MCP Server: Exposes tools for interacting with Harbor through the Model Context Protocol
  • Harbor Operations: Supports operations for projects, repositories, tags, and Helm charts
  • TypeScript: Written in TypeScript for better type safety and developer experience
  • Automated Tests: Comprehensive test suite for reliable functionality

Prerequisites

Before installing MCP Harbor, ensure you have:

  • Node.js 18.x or higher
  • npm 8.x or higher
  • Access to a Harbor registry instance
  • Git (for cloning the repository)

Installation

  1. Clone the repository:

    git clone https://github.com/nomagicln/mcp-harbor.git
    
  2. Navigate to the project directory:

    cd mcp-harbor
    
  3. Install dependencies:

    npm install
    
  4. Build the project:

    npm run build
    

Usage

Command Line Arguments

The application accepts the following command line arguments:

Options:
  --url       Harbor API URL                              [string] [required]
  --username  Harbor username (or robot account name)     [string] [required]
  --password  Harbor password (mutually exclusive with --token)       [string]
  --token     Harbor token for robot/service accounts                [string]
  --insecure  Disable TLS/SSL certificate validation [boolean] [default: false]
  --debug     Enable debug mode                   [boolean] [default: false]
  --help      Show help                                             [boolean]

Note: You must provide either --password or --token, but not both.

Environment Variables

Instead of command line arguments, you can also use environment variables. Create a .env file in the root directory:

# Harbor API Configuration
HARBOR_URL=https://harbor.example.com
HARBOR_USERNAME=admin

# Authentication: use either PASSWORD or TOKEN (mutually exclusive)
# Option 1: Password-based authentication
HARBOR_PASSWORD=Harbor12345

# Option 2: Token-based authentication (for robot/service accounts)
# HARBOR_USERNAME=robot$myrobot
# HARBOR_TOKEN=your-robot-token-here

# Debug Mode (true/false)
DEBUG=false

# Disable TLS/SSL certificate validation (true/false)
# HARBOR_INSECURE=false

Token Authentication (Robot/Service Accounts)

Harbor supports robot accounts for automated access. To use token-based authentication:

  1. Create a robot account in your Harbor instance (Administration > Robot Accounts)
  2. Use the robot account name as --username (e.g., robot$myrobot)
  3. Use the generated token as --token
mcp-harbor --url https://harbor.example.com --username "robot\$myrobot" --token "your-robot-token"

MCP Client Configuration

Claude Desktop

Add the following to your Claude Desktop configuration file (claude_desktop_config.json):

Using password authentication:

{
  "mcpServers": {
    "harbor": {
      "command": "npx",
      "args": [
        "mcp-harbor",
        "--url", "https://harbor.example.com",
        "--username", "admin",
        "--password", "your-password"
      ]
    }
  }
}

Using token authentication (robot/service account):

{
  "mcpServers": {
    "harbor": {
      "command": "npx",
      "args": [
        "mcp-harbor",
        "--url", "https://harbor.example.com",
        "--username", "robot$myrobot",
        "--token", "your-robot-token"
      ]
    }
  }
}

With self-signed certificates:

{
  "mcpServers": {
    "harbor": {
      "command": "npx",
      "args": [
        "mcp-harbor",
        "--url", "https://harbor.example.com",
        "--username", "admin",
        "--password", "your-password",
        "--insecure"
      ]
    }
  }
}

Cursor / Windsurf

Add the following to your MCP configuration file (.cursor/mcp.json or .windsurf/mcp.json):

{
  "mcpServers": {
    "harbor": {
      "command": "npx",
      "args": [
        "mcp-harbor",
        "--url", "https://harbor.example.com",
        "--username", "admin",
        "--password", "your-password"
      ]
    }
  }
}

Using environment variables

You can also reference environment variables to avoid hardcoding credentials:

{
  "mcpServers": {
    "harbor": {
      "command": "npx",
      "args": ["mcp-harbor"],
      "env": {
        "HARBOR_URL": "https://harbor.example.com",
        "HARBOR_USERNAME": "admin",
        "HARBOR_PASSWORD": "your-password"
      }
    }
  }
}

SSE Transport (remote/shared server)

If you prefer running the MCP server as a standalone process with SSE transport:

npx mcp-harbor --url https://harbor.example.com --username admin --password your-password --sse --port 3000

Then configure your MCP client to connect via SSE at http://localhost:3000/sse.

MCP Tools

The MCP server exposes the following tools:

Tool Name Description Parameters
list_projects List all projects in Harbor None
get_project Get project details by ID projectId: string
create_project Create a new project project_name: string, metadata?: object
delete_project Delete a project projectId: string
list_repositories List repositories in a project projectId: string
delete_repository Delete a repository projectId: string, repositoryName: string
list_tags List tags in a repository projectId: string, repositoryName: string
delete_tag Delete a tag projectId: string, repositoryName: string, tag: string
list_charts List Helm charts projectId: string
list_chart_versions List chart versions projectId: string, chartName: string
delete_chart Delete chart version projectId: string, chartName: string, version: string

Development

Running in Development Mode

npm run dev

Running Tests

# Run all tests
npm test

# Run tests with coverage
npm run test:coverage

Project Structure

mcp-harbor
├── src
│   ├── app.ts                 # Main application entry point (MCP server)
│   ├── definitions
│   │   └── tool.definitions.ts # Tool definitions for MCP
│   ├── services
│   │   └── harbor.service.ts  # Harbor service implementation
│   └── types
│       └── index.ts           # TypeScript type definitions
├── test
│   └── harbor.test.ts         # Tests for Harbor service
├── .env.example              # Example environment variables
├── .gitignore               # Git ignore file
├── .eslintrc.json           # ESLint configuration
├── package.json            # Project dependencies
├── jest.config.js           # Jest configuration
├── tsconfig.test.json      # TypeScript configuration for tests
├── tsconfig.json          # TypeScript configuration
├── LICENSE                # Project license
└── README.md             # Project documentation

Troubleshooting

Common Issues

  1. Connection Failed

    Error: Unable to connect to Harbor instance
    
    • Verify HARBOR_URL is correct and accessible
    • Check network connectivity
    • Ensure Harbor instance is running
  2. Authentication Failed

    Error: Invalid credentials
    
    • Verify HARBOR_USERNAME and HARBOR_PASSWORD are correct
    • Check if user has required permissions
  3. Build Errors

    Error: TypeScript compilation failed
    
    • Run npm install to ensure all dependencies are installed
    • Check TypeScript version compatibility
    • Clear the dist directory and rebuild

Debug Mode

Enable debug mode by using the --debug flag or setting:

DEBUG=true

Support

For additional help:

  1. Review the application logs

License

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

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