Douyin MCP Server

🚀 Douyin Watermark-Free Video Text Extraction MCP Server

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

🚀 Quick Start

This server enables you to download watermark-free videos from Douyin sharing links, extract audio, and convert it into text.

✨ Features

• 🎵 Obtain watermark-free videos from Douyin sharing 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 Alibaba Cloud Bailing API by default.

📦 Installation

Install using uvx (Recommended)

uvx douyin-mcp-server

Install using pip

pip install douyin-mcp-server

💻 Usage Examples

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": {
        "DASHSCOPE_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 DASHSCOPE_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")

📚 Documentation

API Configuration

Default Configuration

The server API uses Alibaba Cloud Bailing API by default.

Go to Alibaba Cloud Bailing to activate the API service.

Environment Variable Configuration

Set environment variables in the Claude Desktop configuration file:

{
  "mcpServers": {
    "douyin-mcp": {
      "command": "uvx",
      "args": ["douyin-mcp-server"],
      "env": {
        "DASHSCOPE_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 sharing 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 sharing link.
2. Perform speech recognition directly using the video URL.
3. Return the extracted text content.

Parameters:

• share_link: Douyin sharing link or text containing the link.
• model: Speech recognition model (Optional, paraformer-v2 is used by default).

Environment Variables:

• DASHSCOPE_API_KEY: Alibaba Cloud Bailing API key (Required).

parse_douyin_video_info

Only parse the basic video information without downloading the video.

Parameters:

• share_link: Douyin sharing link.

Resource Access

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

🔧 Technical Details

Dependencies

• Python 3.10+
• requests
• ffmpeg-python
• tqdm
• mcp
• dashscope

⚠️ Important Note

• Switch to using Alibaba Cloud Bailing API for speech recognition, which is faster and more accurate.
• You need to set a valid Alibaba Cloud Bailing API key DASHSCOPE_API_KEY in the environment variables.
• The function to get the download link does not require an API key.
• Most Douyin video formats are supported.

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

Configure in Claude Desktop (Local Source Code)

Configure in the Claude Desktop configuration file:

{
  "mcpServers": {
    "douyin-mcp": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/path/to/your/douyin-mcp-server",
        "python",
        "-m",
        "douyin_mcp_server"
      ],
      "env": {
        "DASHSCOPE_API_KEY": "your-api-key-here"
      }
    }
  }
}

⚠️ Disclaimer

• Users are solely responsible for deciding whether to use this project and assume all risks associated with its use. The author shall not be liable 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 developed based on existing knowledge and technology. The author endeavors to ensure the correctness and security of the code to the best of their ability, but does not guarantee that the code is completely error-free or defect-free.
• All third-party libraries, plugins, or services on which this project depends are subject to their respective original open-source or commercial licenses. Users are required to review and comply with the relevant agreements on their own. The author shall not be responsible for the stability, security, and compliance of third-party components.
• When using the code and functions of this project, users must conduct their own research on relevant laws and regulations and ensure that their use is legal and compliant. Any legal liability and risk arising from non-compliance with laws and regulations shall be borne by the user.
• Users shall not use this tool to engage in any activities that infringe on intellectual property rights, including but not limited to unauthorized downloading and dissemination of copyrighted content. The developer does not participate in, support, or endorse the acquisition or distribution of any illegal content.
• This project shall not be responsible for the compliance of users' data collection, storage, transmission, and other processing activities. Users shall comply with relevant laws and regulations on their own to ensure that their processing activities are legal and proper. Any legal liability arising from non-compliant operations shall be borne by the user.
• Under no circumstances shall users associate the author, contributors, or other relevant parties of this project with their use of the project or require them to be responsible for any losses or damages arising from the user's use of the project.
• Any program developed, modified, or compiled based on this project is unrelated to the original author. The original author shall not be responsible for any secondary development activities or their results. Users shall be fully responsible for all possible situations arising from secondary development.
• This project does not grant users any patent licenses. If the use of this project leads to patent disputes or infringements, users shall bear all risks and responsibilities on their own. Without the written authorization of the author or the right holder, this project shall not be used for any commercial promotion, marketing, or re-licensing.
• 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. Continued use of the project by the user shall be deemed as acceptance of the revised terms.

Before using the code and functions of this project, please carefully consider and accept the above disclaimer. If you have any questions or do not agree with the above statement, please do not use the code and functions of this project. If you use the code and functions of this project, it shall be deemed that you have fully understood and accepted the above disclaimer and voluntarily assume all risks and consequences of using this project.

📄 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.

v1.2.0

• Faster and more accurate video copywriting extraction.
• Switch to Alibaba Cloud Bailing API to improve recognition accuracy.
• Update the environment variable from DOUYIN_API_KEY to DASHSCOPE_API_KEY.