Douyin MCP Server

🚀 Douyin Watermark-Free Video Text Extraction MCP Server

A server based on the Model Context Protocol (MCP) that can download watermark-free videos from Douyin share links, extract audio, and convert it into text.

🚀 Quick Start

This server enables you to download watermark-free Douyin videos, extract audio, and convert it into text. Follow the steps below to get started.

✨ Features

• 🎵 Obtain watermark-free videos from Douyin share links.
• 🎧 Automatically extract audio from videos.
• 📝 Use AI speech recognition to extract text content.
• 🧹 Automatically clean up intermediate temporary files.
• 🔧 Support custom API configuration. The API uses SiliconFlow API by default.

📦 Installation

Install using uvx (Recommended)

uvx douyin-mcp-server

Install using pip

pip install douyin-mcp-server

💻 Usage Examples

Basic Usage

1. Start the server

douyin-mcp-server

2. Configure in Claude Desktop

Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "douyin-mcp": {
      "command": "uvx",
      "args": ["douyin-mcp-server"],
      "env": {
        "DOUYIN_API_KEY": "your-api-key-here"
      }
    }
  }
}

3. Use MCP tools

Get the watermark-free download link

Use the get_douyin_download_link tool:

# Use in Claude without an API key
get_douyin_download_link("https://v.douyin.com/xxx")

Extract video text

Use the extract_douyin_text tool (requires setting the environment variable DOUYIN_API_KEY):

# Use in Claude
extract_douyin_text("https://v.douyin.com/xxx")

Parse video information

Use the parse_douyin_video_info tool:

parse_douyin_video_info("https://v.douyin.com/xxx")

Advanced Usage

API Configuration

Default Configuration

The server uses SiliconFlow API by default:

• API URL: https://api.siliconflow.cn/v1/audio/transcriptions
• Model: FunAudioLLM/SenseVoiceSmall

Custom Configuration

You can customize the API configuration:

extract_douyin_text(
    share_link="your-douyin-link",
    api_base_url="https://your-custom-api.com/transcriptions",
    model="your-custom-model"
)

Environment Variable Configuration

Set environment variables in the Claude Desktop configuration file:

{
  "mcpServers": {
    "douyin-mcp": {
      "command": "uvx",
      "args": ["douyin-mcp-server"],
      "env": {
        "DOUYIN_API_KEY": "sk-your-api-key-here"
      }
    }
  }
}

Tool Explanation

get_douyin_download_link

Get the watermark-free download link for a Douyin video without an API key.

Parameters:

• share_link: Douyin share link or text containing the link.

Returns:

• JSON-formatted data containing the download link and video information.

extract_douyin_text

A complete text extraction tool that performs the following steps:

1. Parse the Douyin share link.
2. Download the watermark-free video.
3. Extract the audio.
4. Convert the audio to text.
5. Clean up temporary files.

Parameters:

• share_link: Douyin share link or text containing the link.
• api_base_url: API base URL (optional).
• model: Speech recognition model (optional).

Environment Variables:

• DOUYIN_API_KEY: Speech recognition API key (required).

parse_douyin_video_info

Only parse the basic video information without downloading the video.

Parameters:

• share_link: Douyin share link.

Resource Access

• douyin://video/{video_id}: Get detailed information by video ID.

🔧 Technical Details

Dependencies

• Python 3.8+
• ffmpeg (The system needs to have ffmpeg installed).
• requests
• ffmpeg-python
• tqdm
• mcp

Install ffmpeg

macOS

brew install ffmpeg

Ubuntu/Debian

sudo apt update
sudo apt install ffmpeg

Windows

Download and install ffmpeg.

Development

Local Development

git clone https://github.com/yzfly/douyin-mcp-server.git
cd douyin-mcp-server
pip install -e .

Run Tests

python -m douyin_mcp_server.server

Important Note

⚠️ Important Note

• Ensure that ffmpeg is installed on the system.
• You need to set a valid speech recognition API key DOUYIN_API_KEY in the environment variables.
• The function to get the download link does not require an API key.
• Intermediate files will be automatically cleaned up and will not take up disk space.
• Most Douyin video formats are supported.

⚠️ Disclaimer

• The user's use of this project is at the user's own discretion and risk. The author is not responsible for any losses, liabilities, or risks arising from the user's use of this project.
• The code and functions provided by the author of this project are the development results based on existing knowledge and technology. The author strives to ensure the correctness and security of the code at the current technical level but does not guarantee that the code is completely error-free or defect-free.
• All third-party libraries, plugins, or services that this project depends on follow their original open-source or commercial licenses. The user needs to review and comply with the corresponding agreements independently. The author is not responsible for the stability, security, and compliance of third-party components.
• When using the code and functions of this project, the user must study relevant laws and regulations independently and ensure that their use is legal and compliant. Any legal liability and risk arising from violating laws and regulations shall be borne by the user independently.
• The user shall not use this tool to engage in any intellectual property infringement, including but not limited to unauthorized downloading and dissemination of copyrighted content. The developer does not participate in, support, or approve of any illegal content acquisition or distribution.
• This project is not responsible for the compliance of the user's data collection, storage, transmission, and other processing activities. The user shall comply with relevant laws and regulations independently to ensure that the processing behavior is legal and proper; the legal liability arising from illegal operations shall be borne by the user independently.
• Under no circumstances shall the user associate the author, contributors, or other relevant parties of this project with the user's use behavior or require them to be responsible for any losses or damages caused by the user's use of this project.
• Any program developed, modified, or compiled based on this project has nothing to do with the original author. The original author is not responsible for any situations that may arise from secondary development, and the user shall be fully responsible for all possible situations caused by secondary development.
• This project does not grant the user any patent license; if using this project causes a patent dispute or infringement, the user shall bear all risks and responsibilities independently. Without the written authorization of the author or the right holder, this project shall not be used for any commercial promotion, marketing, or re-authorization.
• The author reserves the right to terminate the service to any user who violates this statement at any time and may require the user to destroy the obtained code and derivative works.
• The author reserves the right to update this statement without prior notice. Continuous use by the user shall be deemed as acceptance of the revised terms.

📄 License

MIT License

Author

• yzfly - yz.liu.me@gmail.com
• GitHub: https://github.com/yzfly

Contribution

Welcome to submit Issues and Pull Requests!

Changelog

v1.0.0

• Initial release.
• Support text extraction from Douyin videos.
• Support getting watermark-free video download links.
• Read the API key from environment variables.
• Automatically clean up temporary files.
• Support custom API configuration.

v1.1.0

• Fix the bug of long file names when extracting videos.