zerodrive-mcp-server

zerodrive-mcp-server

A Model Context Protocol (MCP) server for ZeroDrive file management. It enables AI assistants like Claude to interact with ZeroDrive cloud storage through a standardized interface.

Category
访问服务器

README

ZeroDrive MCP Server

A Model Context Protocol (MCP) server for ZeroDrive file management. This server enables AI assistants like Claude to interact with ZeroDrive cloud storage through a standardized interface.

Features

  • 28 MCP Tools across 4 categories:

    • File Operations (8 tools): List, get, upload, download, move, share files
    • Folder Operations (7 tools): Create, list, update, delete, move, share folders
    • Workspace Operations (10 tools): Manage collaborative workspaces with files and folders
    • Trash Operations (3 tools): List, restore, and empty trash
  • Production-Ready:

    • Zod validation for all inputs
    • Structured logging with pino
    • Comprehensive error handling
    • TypeScript with strict mode

Requirements

  • Node.js 22.0.0 or higher
  • ZeroDrive API key

Installation

Via npm (Recommended)

npx @futurixai-labs/zerodrive-mcp-server

From Source

# Clone the repository
git clone https://github.com/futurixai/zerodrive-mcp-server.git
cd zerodrive-mcp-server

# Install dependencies
npm install

# Build
npm run build

Configuration

Set the required environment variable:

export ZERODRIVE_API_KEY="your-api-key-here"

Optional environment variables:

Variable Default Description
ZERODRIVE_BASE_URL https://drive.futurixai.com API base URL
LOG_LEVEL info Log level (trace, debug, info, warn, error, fatal, silent)
NODE_ENV production Environment mode

Usage with Claude Desktop

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

{
  "mcpServers": {
    "zerodrive": {
      "command": "npx",
      "args": ["@futurixai-labs/zerodrive-mcp-server"],
      "env": {
        "ZERODRIVE_API_KEY": "your-api-key-here"
      }
    }
  }
}

Available Tools

File Tools

Tool Description
list_files List files with filtering, pagination, and sorting
get_file Get detailed file metadata
upload_file Upload a file from local path
download_file Generate download URL for a file
generate_signed_url Generate time-limited signed URL
fetch_file_content Fetch text content of a file
move_file Move file to different folder
share_file Share file with other users

Folder Tools

Tool Description
list_folders List folders with filtering and pagination
create_folder Create a new folder
get_folder Get folder details
update_folder Update folder properties
delete_folder Delete folder (to trash or permanent)
move_folder Move folder to different parent
share_folder Share folder with other users

Workspace Tools

Tool Description
list_workspaces List all accessible workspaces
create_workspace Create a new workspace
get_workspace Get workspace details
upload_workspace_file Upload file to workspace
list_workspace_files List files in workspace
list_workspace_folders List folders in workspace
create_workspace_folder Create folder in workspace
get_workspace_folder Get workspace folder details
update_workspace_folder Update workspace folder
delete_workspace_folder Delete workspace folder

Trash Tools

Tool Description
list_trash List trashed items
restore_from_trash Restore item from trash
empty_trash Permanently delete all trashed items

Development

# Install dependencies
npm install

# Run type checking
npm run typecheck

# Build
npm run build

# Run linting
npm run lint

# Run tests
npm test

# Format code
npm run format

Project Structure

src/
├── index.ts              # Entry point
├── api/                  # HTTP client layer
│   ├── client.ts         # API client with auth
│   └── endpoints.ts      # API endpoint constants
├── config/               # Configuration
│   ├── env.ts            # Environment validation
│   └── constants.ts      # Application constants
├── errors/               # Error handling
│   └── base.ts           # Error classes
├── logging/              # Structured logging
│   └── logger.ts         # Pino logger setup
├── schemas/              # Zod validation schemas
│   ├── common.ts         # Shared schemas
│   ├── files.ts          # File tool schemas
│   ├── folders.ts        # Folder tool schemas
│   ├── workspaces.ts     # Workspace tool schemas
│   └── trash.ts          # Trash tool schemas
├── server/               # MCP server setup
│   ├── server.ts         # Server creation
│   └── handlers.ts       # Request handlers
├── tools/                # Tool implementations
│   ├── files/            # File tools
│   ├── folders/          # Folder tools
│   ├── workspaces/       # Workspace tools
│   ├── trash/            # Trash tools
│   └── registry.ts       # Tool dispatcher
├── types/                # TypeScript types
│   ├── entities.ts       # Domain types
│   └── api.ts            # API types
└── utils/                # Utilities
    ├── query-builder.ts  # URL query builder
    ├── request-builder.ts # Request body builder
    ├── upload-handler.ts # File upload logic
    └── response-formatter.ts # Response formatting

Contributing

See CONTRIBUTING.md for contribution guidelines.

License

MIT License - see LICENSE 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
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
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
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
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
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
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
mcp-server-qdrant

mcp-server-qdrant

这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。

官方
精选
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选