google-drive-mcp-server
Enables AI assistants to interact with Google Drive, including reading, searching, listing folders, and uploading files.
README
Google Drive MCP Server
A Model Context Protocol (MCP) server for Google Drive integration. This server allows AI assistants to interact directly with your Google Drive, providing tools to read, search, list folders, and upload files.
Built with TypeScript and utilizing the official Google APIs Node.js Client.
Available Modules & Tools
Files & Folders
Manage and search your Google Drive contents.
list_recent_files: Lists recent files from Google Drive, ordered by recency, modification date, or name.search_files: Searches for files and folders in Google Drive by name or content. Accepts plain text or Drive query syntax.list_folder: Lists the contents (files and subfolders) of a specific Google Drive folder by its ID. Works with both My Drive and Shared Drives.read_file_content: Reads the text content of a Google Drive file (Docs, Sheets, PDFs, plain text).get_file_metadata: Returns metadata of a Drive file: name, MIME type, size, owners, modification date, parent folders, and view link.upload_file: Uploads a file to Google Drive. Pass text content directly or base64-encoded content for binary files.upload_file_from_path: Uploads a file from a local path on the server to Google Drive. Useful for processing generated files.
Setup & Installation
- Clone the repository:
git clone https://github.com/Themetralla3000/google-drive-mcp-server.git cd google-drive-mcp-server - Install dependencies:
npm install - Copy the environment template and configure your credentials:
cp .env.example .env - Build the project:
npm run build
Configuration
You must provide Google Drive API credentials via the .env file. These can be obtained from the Google Cloud Console by creating an OAuth 2.0 Client ID.
GOOGLE_DRIVE_CLIENT_ID=your-client-id
GOOGLE_DRIVE_CLIENT_SECRET=your-client-secret
GOOGLE_DRIVE_REFRESH_TOKEN=your-refresh-token
Usage with Claude Desktop / Cursor
To use this MCP with Claude Desktop or Cursor, add the following configuration to your MCP config file (e.g., claude_desktop_config.json):
{
"mcpServers": {
"google-drive": {
"command": "node",
"args": ["/absolute/path/to/google-drive-mcp-server/build/src/index.js"],
"env": {
"GOOGLE_DRIVE_CLIENT_ID": "your-client-id",
"GOOGLE_DRIVE_CLIENT_SECRET": "your-client-secret",
"GOOGLE_DRIVE_REFRESH_TOKEN": "your-refresh-token"
}
}
}
}
License
MIT License
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。