Metadata-Version: 2.4
Name: video-analyzer-mcp
Version: 0.1.2
Summary: MCP server for video analysis - extracts frames, transcribes audio, analyzes visuals with Claude, and generates storyboard breakdowns
Project-URL: Homepage, https://github.com/BrightWayAI/video-analyzer
Project-URL: Repository, https://github.com/BrightWayAI/video-analyzer
Author: Zach Wagner
License-Expression: MIT
Keywords: analysis,claude,mcp,storyboard,video,whisper
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Multimedia :: Video
Requires-Python: >=3.10
Requires-Dist: anthropic>=0.39.0
Requires-Dist: mcp[cli]>=1.0.0
Requires-Dist: openai-whisper>=20231117
Requires-Dist: pillow>=10.0.0
Requires-Dist: pydantic>=2.0.0
Requires-Dist: python-docx>=1.0.0
Requires-Dist: scenedetect[opencv]>=0.6.2
Requires-Dist: yt-dlp>=2024.1.0
Provides-Extra: dev
Requires-Dist: build; extra == 'dev'
Requires-Dist: twine; extra == 'dev'
Description-Content-Type: text/markdown

# Video Analyzer MCP Server

<!-- mcp-name: io.github.BrightWayAI/video-analyzer -->

An MCP (Model Context Protocol) server that analyzes videos and generates storyboard breakdowns. Extract frames, transcribe audio, analyze visuals with Claude Vision, and compute stylistic fingerprints — all usable directly from Claude Desktop or Claude Code.

## Tools

| Tool | Description |
|------|-------------|
| `video_analyze` | Full pipeline: download, extract frames, transcribe, visual analysis, stylistic fingerprint, storyboard document |
| `video_extract_frames` | Extract representative frames using scene detection or fixed intervals |
| `video_transcribe` | Transcribe audio with OpenAI Whisper (timestamped, speaker-labeled) |
| `video_fingerprint` | Generate an 8-field Stylistic Fingerprint v3 classification |
| `video_check_deps` | Verify all required dependencies are installed |

## Prerequisites

- **Python 3.10+**
- **FFmpeg** — `brew install ffmpeg` (macOS) or `apt-get install ffmpeg` (Linux)
- **ANTHROPIC_API_KEY** — set as an environment variable

## Installation

### From PyPI

```bash
pip install video-analyzer-mcp
```

### For Claude Desktop

Add to your Claude Desktop config (`~/Library/Application Support/Claude/claude_desktop_config.json`):

```json
{
  "mcpServers": {
    "video-analyzer": {
      "command": "uvx",
      "args": ["video-analyzer-mcp"],
      "env": {
        "ANTHROPIC_API_KEY": "your-key-here"
      }
    }
  }
}
```

### For Claude Code

```bash
claude mcp add video-analyzer -s user -- uvx video-analyzer-mcp
```

## Usage Examples

Once installed, you can ask Claude:

- **"Analyze this video and create a storyboard"** — runs `video_analyze`
- **"Extract frames from this YouTube video"** — runs `video_extract_frames`
- **"Transcribe the audio from this video"** — runs `video_transcribe`
- **"What's the stylistic fingerprint of this video?"** — runs `video_fingerprint`
- **"Check if video analyzer dependencies are installed"** — runs `video_check_deps`

## Stylistic Fingerprint Fields

The fingerprint classifier produces 8 deterministic fields:

1. **Rendering Class** — Stylized 3D, Flat 2D, Minimalist Line Art, Textured 2D, Mixed Media, Photoreal
2. **World Type** — Stylized Real-World, Abstract Concept Space, Data/Presentation Space, Fictional Metaphor Universe
3. **Character Strategy** — None, Mascot-Led, Single Narrator, Single Protagonist Arc, Ensemble Cast
4. **Narrative Structure** — Direct Explanation, Step-by-Step, Problem-Solution, Analogy, Myth-Busting, etc.
5. **Visual Abstraction Index** — 1 (Photorealistic) to 5 (Maximum Abstraction)
6. **Visual Density** — Minimal, Sparse, Moderate, High
7. **Camera/Editing Language** — Cinematic, Social Vertical Punch, Presentation Deck, Static Slides, etc.
8. **Tonal Positioning** — Institutional, Corporate Professional, Gen Z Social, Child-Friendly, Dark Editorial

## License

MIT
