Douyin Link

Provides an MCP server that parses Douyin links, resolves video URLs, analyzes content with豆包 models, and returns structured video descriptions and outlines.

python

1

GitHub Stars

python

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "youzhajun-douyin_link_mcp": {
      "command": "douyin-mcp-server",
      "args": [],
      "env": {
        "DOUBAO_API_KEY": "your_actual_api_key"
      }
    }
  }
}

You can run a dedicated MCP server that parses Douyin share links, resolves the actual video URL, and analyzes content using a豆包 model to return structured video descriptions, outlines, and steps. This server lets you integrate Douyin content analysis into Cursor workflows or other MCP clients with minimal setup.

How to use

You connect to the Douyin Link MCP Server from your MCP client or Cursor. Start the server using one of the available runtime methods, then point your MCP client to that local or remote endpoint. When you submit a Douyin link or口令, the server extracts the video URL, fetches the real video stream URL, runs AI analysis, and returns a structured description of the video, its type, a detailed outline, and actionable steps.

How to install

Prerequisites: Python 3.10 or newer, and a working Python environment.

Option A — Install via PyPI (recommended for quickest setup)

Run the following command to install the MCP server package.

pip install douyin-mcp-server

Configure your API key in your environment before running the server, then add the server to Cursor using the MCP configuration shown below.

{
  "mcpServers": {
    "douyin_analyzer": {
      "command": "douyin-mcp-server",
      "env": {
        "DOUBAO_API_KEY": "your_actual_api_key"
      }
    }
  }
}

Option B — Install from source (development mode)

Clone or enter the project directory.
Create and activate a virtual environment.
Install dependencies in editable mode.

# Windows:
python -m venv venv
venv\Scripts\activate
pip install -e .

# macOS/Linux:
python -m venv venv
source venv/bin/activate
pip install -e .

Create and edit the environment file to include your豆包 API Key. You can base it on an example file if provided.
Run the MCP server from source.

python -m src

Additional setup and testing

If you prefer testing isolation, you can also run a quick test script to verify link extraction, video URL retrieval, and complete video information retrieval.

Ensure your豆包 API Key is set in the environment, and check that the Douyin link input formats are complete URLs like https://v.douyin.com/xxx/.

Available tools

Link extraction

Extracts Douyin video links from input text or口令 and resolves the initial video URL for processing.

Video URL retrieval

Requests the Douyin video data endpoint to obtain a playable video URL with the minimum bitrate for efficient streaming.

AI video analysis

Sends the video content to the豆包 large model for deep content analysis to generate descriptions, outlines, and tutorials.

Structured output

Returns a formatted result containing video description, video type, outline, key scenes, and core information.