Video Info MCP

🚀 Video Info MCP

A professional video information analysis tool based on the MCP (Model Context Protocol), providing powerful video file analysis capabilities for AI assistants.

🚀 Quick Start

Claude Desktop Configuration

1. Open the Claude Desktop configuration file:

   • Windows: %APPDATA%\Claude\claude_desktop_config.json
   • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Linux: ~/.config/claude/claude_desktop_config.json

2. Add the MCP server configuration:

{
  "mcpServers": {
    "video-info": {
      "command": "npx",
      "args": ["@pickstar-2002/video-info-mcp@latest"],
      "env": {}
    }
  }
}

3. Restart Claude Desktop

Configuration for Other AI Assistants

For other AI assistants that support the MCP protocol, please refer to the corresponding configuration documentation and use the following command:

npx @pickstar-2002/video-info-mcp@latest

✨ Features

• 🎯 Professional Analysis: In - depth video information extraction based on FFmpeg.
• 📊 Multi - dimensional Data: Video streams, audio streams, bitrate, and quality assessment.
• 📝 Multi - format Reports: Supports output in JSON, TEXT, and Markdown formats.
• 🔧 MCP Compatibility: Fully compliant with the Model Context Protocol specification.
• ⚡ High Performance: Average response time < 500ms.
• 🌐 Cross - platform: Supports Windows, macOS, and Linux.
• 🛡️ Type Safety: Uses TypeScript and Zod for strict type checking.

📦 Installation

As an MCP Server (Recommended)

Add the following to your AI assistant configuration file:

{
  "mcpServers": {
    "video-info": {
      "command": "npx",
      "args": ["@pickstar-2002/video-info-mcp@latest"],
      "env": {}
    }
  }
}

Global Installation

npm install -g @pickstar-2002/video-info-mcp@latest

🛠️ Function Description

Available Tools

Supported Video Formats

• Container Formats: MP4, MOV, AVI, MKV, WebM, FLV, 3GP, M4V
• Video Encodings: H.264, H.265/HEVC, VP8, VP9, AV1, MPEG - 4
• Audio Encodings: AAC, MP3, AC - 3, DTS, FLAC, Opus, Vorbis

💻 Usage Examples

Basic Usage

In an AI assistant that supports MCP, you can directly use natural language requests:

"Please analyze the information of this video file: /path/to/video.mp4"
"Generate a technical report for this video in Markdown format"
"Calculate the bitrate information of this video file"

API Call Examples

// get_video_info - Get basic information
{
  "name": "get_video_info",
  "arguments": {
    "filePath": "/path/to/video.mp4"
  }
}

// analyze_streams - Stream analysis
{
  "name": "analyze_streams", 
  "arguments": {
    "filePath": "/path/to/video.mp4",
    "includeMetadata": true
  }
}

// generate_report - Generate a report
{
  "name": "generate_report",
  "arguments": {
    "filePath": "/path/to/video.mp4",
    "format": "markdown"
  }
}

📊 Output Example

Video Information Output

{
  "filename": "sample.mp4",
  "fileSize": "20.43 MB",
  "duration": "289.4",
  "format": "mov,mp4,m4a,3gp,3g2,mj2",
  "videoStreams": [{
    "codec": "h264",
    "resolution": "1920x1080",
    "frameRate": "30/1",
    "bitRate": "423986"
  }],
  "audioStreams": [{
    "codec": "aac",
    "sampleRate": "48000",
    "channels": 2,
    "bitRate": "164221"
  }],
  "technicalReport": {
    "videoQuality": "1080p High Definition",
    "audioQuality": "Standard Quality",
    "recommendations": [
      "It is recommended to increase the video bitrate for better 1080p quality",
      "Use H.264 encoding for good compatibility"
    ]
  }
}

🔧 Troubleshooting

Common Issues

❌ Connection Error "Connection closed"

This is usually caused by npx cache issues. Please try to solve it in the following order:

1. Use the @latest tag (Preferred solution)

{
  "mcpServers": {
    "video-info": {
      "command": "npx",
      "args": ["@pickstar-2002/video-info-mcp@latest"],
      "env": {}
    }
  }
}

2. Lock to a specific version (Alternative solution)

{
  "mcpServers": {
    "video-info": {
      "command": "npx",
      "args": ["@pickstar-2002/video-info-mcp@1.1.0"],
      "env": {}
    }
  }
}

3. Clear the npx cache (Ultimate solution)

# Clear the npx cache
npx clear-npx-cache

# Or manually delete the cache directory
# Windows: %LOCALAPPDATA%\npm-cache\_npx
# macOS/Linux: ~/.npm/_npx

❌ FFmpeg Not Found

Ensure that FFmpeg is installed on your system:

Windows:

# Use Chocolatey
choco install ffmpeg

# Use Scoop  
scoop install ffmpeg

macOS:

# Use Homebrew
brew install ffmpeg

Linux:

# Ubuntu/Debian
sudo apt update && sudo apt install ffmpeg

# CentOS/RHEL
sudo yum install ffmpeg

❌ Permission Error

Ensure that the AI assistant has permission to access the video file path. It is recommended to use an absolute path.

❌ File Format Not Supported

Check if the video file is corrupted, or try to convert it to a common format (such as MP4) using other tools.

Performance Optimization Tips

• 🚀 For large files (>1GB), analysis may take longer.
• 💾 It is recommended to place frequently used video files on an SSD to improve analysis speed.
• 🔄 Avoid analyzing multiple large files simultaneously.

🤝 Contribution

Welcome to contribute code! Please follow these steps:

1. Fork this repository.
2. Create a feature branch (git checkout -b feature/AmazingFeature).
3. Commit your changes (git commit -m 'Add some AmazingFeature').
4. Push to the branch (git push origin feature/AmazingFeature).
5. Open a Pull Request.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🔗 Related Links

• Model Context Protocol
• Claude Desktop
• FFmpeg Official Website

📞 Contact

If you have any questions or suggestions, please contact us:

WeChat: pickstar_loveXX

⭐ If this project is helpful to you, please give it a Star!