home / mcp / douyin mcp server

Douyin MCP Server

提取抖音无水印视频链接，视频文案，douyin-mcp-server，mcp，claude skill

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "yzfly-douyin-mcp-server": {
      "command": "uvx",
      "args": [
        "douyin-mcp-server"
      ],
      "env": {
        "API_KEY": "sk-xxxxxxxxxxxxxxxx"
      }
    }
  }
}

You can download short videos from share links without watermarks and automatically extract AI-generated transcripts of the spoken content. This MCP server enables you to run this workflow locally or integrate it with AI applications, providing convenient access to information extraction, video retrieval, and Markdown-friendly transcripts.

How to use

Use an MCP client to connect to the Douyin MCP Server. You can run the server locally and then call its tools from compatible applications such as Claude Desktop or other MCP-enabled clients. The server exposes three core actions: parsing video information, obtaining a watermark-free download link, and extracting transcript text from the video’s audio.

How to install

# 1. Clone the project
git clone https://github.com/yzfly/douyin-mcp-server.git
cd douyin-mcp-server

# 2. Install dependencies
uv sync

# 3. Start the WebUI (optional for local use)
uv run python web/app.py
```

Open a browser and visit http://localhost:8080 to access the WebUI.

If you prefer using the MCP integration directly, set up the MCP configuration as shown below to run the local MCP server. This enables calling the extract function from MCP-enabled clients.

{
  "mcpServers": {
    "douyin_mcp": {
      "command": "uvx",
      "args": ["douyin-mcp-server"],
      "env": {
        "API_KEY": "sk-xxxxxxxxxxxxxxxx"
      }
    }
  }
}
```

This configuration runs the server locally via UVX and provides the API key required for transcript extraction.

Additional content

Configuration details, tool usage, and practical examples are provided to help you integrate the server into your workflow. The server supports long audio files by automatically segmenting and processing each segment, ensuring you can work with lengthy videos without hitting API limits.

Available tools

parse_douyin_video_info

Parse video information such as title and ID from a Douyin share link.

get_douyin_download_link

Obtain a watermark-free download link for the video.

extract_douyin_text

Extract the transcript text from the video using AI-based speech recognition.