Taibai MCP Server

Taibai MCP Server

Enables access to Dedao learning platform courses, transcripts, and comments, with Obsidian integration.

Category
访问服务器

README

Taibai MCP Server

A Model Context Protocol (MCP) server for accessing Dedao (得到) learning platform content via dedao-dl.

Features

  • 🎓 Download course transcripts with individual lessons and hot comments
  • 📚 Access your purchased Dedao courses library
  • 📝 Export content as Markdown, PDF, or MP3
  • 🔗 Seamless Obsidian vault integration
  • 🔄 Automatic version detection and update notifications

Prerequisites

  1. dedao-dl - The Go-based Dedao downloader

    go install github.com/yann0917/dedao-dl@latest
    
  2. Python 3.10+ with uv (recommended) or pip

Installation

Using uv (Recommended)

# Install uv if you haven't already
curl -LsSf https://astral.sh/uv/install.sh | sh

# Clone the repository
git clone https://github.com/terry-li-hm/taibai.git
cd taibai

# Install dependencies
uv pip install -e .

# For development
uv pip install -e ".[dev]"

Using pip

# Clone and install
git clone https://github.com/yourusername/taibai.git
cd taibai
pip install -e .

Configuration

1. Set up environment variables

Create a .env file or export:

# Optional: Specify where to download content (defaults to current directory)
export DEDAO_DOWNLOAD_DIR="/path/to/your/obsidian/vault/Dedao/Courses"

2. Configure Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "taibai": {
      "command": "python",
      "args": ["/path/to/taibai/server.py"],
      "env": {
        "DEDAO_DOWNLOAD_DIR": "/path/to/your/obsidian/vault/Dedao/Courses"
      }
    }
  }
}

3. Authenticate with Dedao

First time setup - login via QR code:

# In Claude, use the MCP tool:
dedao_login(qrcode=True)

Usage

Available MCP Tools

  • dedao_version - Check dedao-dl version and update availability
  • dedao_login - Authenticate with Dedao platform
  • dedao_list_courses - List all purchased courses
  • dedao_course_details - Get course information
  • dedao_download_course - Download course content
  • dedao_article_details - Get article information
  • dedao_download_article - Download articles

Example Usage in Claude

# Check dedao-dl version
dedao_version()

# List your courses
dedao_list_courses()

# Download a specific course as markdown
dedao_download_course(
    course_id="743",
    format="markdown"
)

# Get course details
dedao_course_details(course_id="743")

Development

Code Quality

# Format code
ruff format .

# Lint code  
ruff check .

# Run tests
pytest

Project Structure

taibai/
├── server.py           # Main MCP server implementation
├── pyproject.toml      # Project configuration and dependencies
├── README.md           # Documentation
└── .env.example        # Environment variables template

Output Format

Downloaded courses include:

  • Individual lesson files - Each lesson as a separate markdown file
  • Hot comments - Community insights and discussions
  • Clean filenames - No timestamp prefixes
  • Obsidian-ready - Markdown formatted for knowledge graphs

Troubleshooting

Authentication Issues

  • Ensure dedao-dl is authenticated: dedao-dl who
  • Re-login if needed: Use dedao_login(qrcode=True)

Download Location

  • Default: ~/.taibai/output/ then moved to vault
  • Override with DEDAO_DOWNLOAD_DIR environment variable

Missing dedao-dl

# Install dedao-dl first
go install github.com/yann0917/dedao-dl@latest

# Verify installation
dedao-dl --version

License

MIT

Contributing

Pull requests welcome! Please:

  1. Use ruff for formatting
  2. Add tests for new features
  3. Update documentation

Credits

Built on top of dedao-dl by yann0917.

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