{
  "markdown": "# Video Analyzer\n\nAnalyze videos and generate storyboard breakdowns. Extracts frames via scene detection, transcribes audio with Whisper, analyzes visuals with Claude Vision, and computes 8-field stylistic fingerprints.\n\n## Features\n\n- **Frame Extraction** — Scene-detection-based keyframe selection (or fixed intervals)\n- **Audio Transcription** — Timestamped transcription via OpenAI Whisper\n- **Visual Analysis** — Per-frame descriptions using Claude Vision\n- **Stylistic Fingerprint v3** — 8-field deterministic classification (rendering class, world type, character strategy, narrative structure, visual abstraction, visual density, camera language, tonal positioning)\n- **Storyboard Output** — Combined shot-by-shot breakdown as `.docx` or `.md`\n\n## MCP Server\n\nThis project includes an MCP (Model Context Protocol) server so you can use video analysis directly from Claude Desktop or Claude Code.\n\n### Install via Claude Code\n\n```bash\nclaude mcp add video-analyzer -s user -- uvx video-analyzer-mcp\n```\n\n### Install via Claude Desktop\n\nAdd to `~/Library/Application Support/Claude/claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"video-analyzer\": {\n      \"command\": \"uvx\",\n      \"args\": [\"video-analyzer-mcp\"],\n      \"env\": {\n        \"ANTHROPIC_API_KEY\": \"your-key-here\"\n      }\n    }\n  }\n}\n```\n\n### MCP Tools\n\n| Tool | Description |\n|------|-------------|\n| `video_analyze` | Full pipeline: download, extract frames, transcribe, analyze, fingerprint, storyboard |\n| `video_extract_frames` | Extract representative frames using scene detection or fixed intervals |\n| `video_transcribe` | Transcribe audio with OpenAI Whisper |\n| `video_fingerprint` | Generate 8-field Stylistic Fingerprint v3 classification |\n| `video_check_deps` | Verify all required dependencies are installed |\n\n## Standalone Usage\n\n```bash\npip install -r requirements.txt\npython3 analyze_video.py \"https://youtube.com/watch?v=...\" --output-dir ./output\n```\n\n## Prerequisites\n\n- **Python 3.10+**\n- **FFmpeg** — `brew install ffmpeg` (macOS) or `apt-get install ffmpeg` (Linux)\n- **ANTHROPIC_API_KEY** — set as an environment variable\n\n## Stylistic Fingerprint Fields\n\n1. **Rendering Class** — Stylized 3D, Flat 2D, Minimalist Line Art, Textured 2D, Mixed Media, Photoreal\n2. **World Type** — Stylized Real-World, Abstract Concept Space, Data/Presentation Space, Fictional Metaphor Universe\n3. **Character Strategy** — None, Mascot-Led, Single Narrator, Single Protagonist Arc, Ensemble Cast\n4. **Narrative Structure** — Direct Explanation, Step-by-Step, Problem-Solution, Analogy, Myth-Busting, etc.\n5. **Visual Abstraction Index** — 1 (Photorealistic) to 5 (Maximum Abstraction)\n6. **Visual Density** — Minimal, Sparse, Moderate, High\n7. **Camera/Editing Language** — Cinematic, Social Vertical Punch, Presentation Deck, Static Slides, etc.\n8. **Tonal Positioning** — Institutional, Corporate Professional, Gen Z Social, Child-Friendly, Dark Editorial\n\n## License\n\nMIT\n",
  "bytes": 2962,
  "sha": "eabdc4411abd2fa1df32825187752274a09b38f317aabd4fa75cddfeb56b4b26",
  "repo_slug": "brightwayai/video-analyzer",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_brightwayai_video_analyzer_1b5e9600/readme"
}