Video Sum (Chinese Social Media) MCP server

The Video Content Summarization MCP server extracts content from multiple video platforms like Douyin, Bilibili, Xiaohongshu, and Zhihu, generating intelligent knowledge graphs. It features OCR text recognition, specialized Chinese content processing, and context-aware extraction capabilities.

Features

Multi-Platform Support

• Douyin (TikTok China) - Short video content extraction
• Bilibili - Video and live streaming content
• Xiaohongshu (Little Red Book) - Social media posts with OCR support
• Zhihu - Q&A platform content

Advanced Capabilities

• OCR Text Recognition - Extract text from images using PaddleOCR
• Knowledge Graph Generation - Intelligent content structuring
• Chinese Content Optimization - Specialized processing for Chinese text
• Context-Aware Extraction - Smart content understanding and quality control

Installation

Prerequisites

• Python 3.8 or higher
• Anaconda (recommended for dependency management)

Setup

1. Clone the repository:

git clone https://github.com/fakad/video-sum-mcp.git
cd video-sum-mcp

2. Create and activate conda environment:

conda create -n vsc python=3.8
conda activate vsc

3. Install dependencies:

pip install -r requirements.txt

Configuration

For Claude Desktop

Add this configuration to your Claude Desktop config file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "video-sum-mcp": {
      "command": "python",
      "args": ["/path/to/video-sum-mcp/main.py"],
      "cwd": "/path/to/video-sum-mcp",
      "env": {
        "CONDA_DEFAULT_ENV": "vsc"
      }
    }
  }
}

For Other MCP Clients

The server can be started directly:

python main.py

Usage

Basic Video Processing

# Example: Process a Bilibili video
result = process_video(
    url="https://www.bilibili.com/video/BV1234567890",
    output_format="markdown"
)

Supported URL Formats

• Douyin: https://v.douyin.com/... or full URLs
• Bilibili: https://www.bilibili.com/video/...
• Xiaohongshu: https://www.xiaohongshu.com/discovery/item/...
• Zhihu: https://www.zhihu.com/question/...

Context-Enhanced Processing

For platforms with anti-crawling measures, you can provide context:

result = process_video(
    url="https://...",
    context_text="Additional context information..."
)

Features in Detail

OCR Integration

• Automatic image text extraction from Xiaohongshu posts
• PaddleOCR for accurate Chinese character recognition
• Batch processing for multiple images

Knowledge Graph Generation

• Structured content analysis
• Intelligent relationship mapping
• Quality control and validation

Anti-Crawling Strategies

• Smart fallback mechanisms
• Context-based extraction
• User guidance for optimal results

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.