mcp-server-gdrive
gdrive mcp capable of upload
README
Google Drive MCP Server
A Model Context Protocol (MCP) server for interacting with Google Drive API. This server provides a standardized interface for AI systems to access and manipulate files in Google Drive.
Features
- File Operations: List, upload, download, and delete files
- Folder Management: Create folders and organize content
- File Sharing: Share files with specific users and manage permissions
- Pagination Support: Handle large file listings efficiently
- Comprehensive Error Handling: Detailed error reporting for easier debugging
Prerequisites
- Python 3.8+
- Google Cloud project with Drive API enabled
- Service account with appropriate permissions
Setup
1. Google Cloud Setup
- Create a project in Google Cloud Console
- Enable the Google Drive API
- Create a service account with appropriate permissions
- Download the service account JSON key file
2. Local Setup
Clone the repository and install dependencies:
# Clone the repository
git clone <repository-url>
cd mcp-server-gdrive
# Create a virtual environment
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install dependencies
pip install -r requirements.txt
# Copy example environment file and edit with your settings
cp .env.example .env
Edit the .env file with your configuration:
HOST=0.0.0.0
PORT=8055
GOOGLE_SERVICE_ACCOUNT_FILE=your-service-account-file.json
3. Docker Setup
Alternatively, you can use Docker:
# Build and run with Docker Compose
docker-compose up --build
Running the Server
Local Execution
python main.py --transport sse
Docker Execution
docker-compose up
MCP Tools
This server provides the following MCP tools:
File Operations
list_files: List files in Google Drive with pagination supportget_file_info: Get detailed information about a specific fileupload_file: Upload a file to Google Drivedownload_file: Download a file from Google Drive
Folder Operations
create_folder: Create a new folder in Google Drive
Sharing and Permissions
share_file: Share a file or folder with another user
Debugging
debug_api_connection: Debug the Google Drive API connection
Client Configuration
To connect to this MCP server from a client:
{
"gdrive": {
"transport": "sse",
"serverUrl": "http://localhost:8055/sse"
}
}
Note: Make sure to include /sse at the end of the URL for SSE transport.
Security Considerations
- The service account JSON file contains sensitive credentials. Never commit it to version control.
- Use environment variables for all sensitive configuration.
- Consider implementing additional authentication if deploying publicly.
License
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
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。