mcp-google-drive

mcp-google-drive

MCP server for Google Drive integration with file management, search, sharing, and full CRUD operations.

Category
访问服务器

README

MCP Google Drive

Advanced MCP server for Google Drive integration with full CRUD operations, file management, and sharing capabilities.

✨ Features

  • File Management: Create, read, update, delete files and folders
  • Search & Discovery: Advanced search with multiple criteria
  • Sharing & Permissions: Manage file sharing and access control
  • Content Operations: Upload, download, and modify file content
  • Drive Operations: List drives, manage shared drives
  • Type Safety: Full TypeScript support with Zod validation
  • Error Handling: Comprehensive error handling and logging

🚀 Quick Setup

Prerequisites

  • Node.js 18+
  • Google Service Account with Drive API enabled
  • Service Account JSON key file

Installation

npm install mcp-google-drive

Environment Setup

Set your Google Service Account credentials:

export GOOGLE_SERVICE_ACCOUNT_KEY='{"type":"service_account",...}'

🔧 Cursor MCP Integration

Automatic Integration

The MCP server is designed to work seamlessly with Cursor. Add this configuration to your ~/.cursor/mcp.json:

{
  "mcpServers": {
    "mcp-google-drive": {
      "command": "npx",
      "args": ["mcp-google-drive@1.3.2"],
      "env": {
        "GOOGLE_SERVICE_ACCOUNT_KEY": "your-service-account-json",
        "MCP_MODE": "stdio",
        "LOG_LEVEL": "info",
        "DISABLE_CONSOLE_OUTPUT": "false"
      },
      "cwd": "/path/to/your/project"
    }
  }
}

Troubleshooting Cursor Integration

If MCP tools are not working in Cursor:

  1. Restart Cursor after updating mcp.json
  2. Check MCP Status: Command Palette → "MCP: Show Servers"
  3. Verify Connection: Command Palette → "MCP: Test Connection"
  4. Check Logs: Look for MCP server startup messages

Manual Server Start

If automatic integration fails, you can start the server manually:

# In your project directory
npm run start

# Or globally
npx mcp-google-drive

🛠️ Available Tools

File Operations

  • search_files - Search files with advanced criteria
  • get_file - Get file metadata and content
  • create_file - Create new files and folders
  • update_file - Update file content and metadata
  • delete_file - Delete files and folders
  • copy_file - Copy files to new locations
  • move_file - Move files between folders

Drive Management

  • get_drive_info - Get drive information
  • list_shared_drives - List available shared drives

Sharing & Permissions

  • get_file_permissions - Get file sharing settings
  • share_file - Share files with users
  • get_file_revisions - Get file version history

📚 Documentation

🧪 Development

Build

npm run build

Development Mode

npm run dev

Linting

npm run lint
npm run lint:fix

📄 License

MIT License - see LICENSE for details.

🤝 Contributing

Contributions welcome! Please read our contributing guidelines and submit pull requests.

📞 Support

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