Video Analyzer

io.github.BrightWayAIPublished by GitHub account BrightWayAIv0.1.2Updated Oct 24, 2026

Analyze videos: extract frames, transcribe audio, generate storyboard breakdowns.

VerifiedSTDIODesktop onlyMedia & DesignAI & ML

Overview

AI-generated overview

Lets an assistant analyze videos by extracting keyframes, transcribing audio, and producing storyboard breakdowns.

What you can do
Runs a video analysis pipeline: it downloads a video, extracts representative frames using scene detection or fixed intervals, transcribes audio with OpenAI Whisper, and describes frames with Claude Vision. It also generates an 8-field stylistic fingerprint and can output a shot-by-shot storyboard as a .docx or .md file. Tools include video_analyze, video_extract_frames, video_transcribe, video_fingerprint, and video_check_deps.
When to use it
Useful when you want an assistant to summarize or break down a video, pull keyframes, get a timestamped transcript, or produce a storyboard document. Best for creators, editors, or analysts reviewing footage or online videos.
Requirements
Runs locally as a Python package (video-analyzer-mcp) via uvx or pip, requiring Python 3.10+ and FFmpeg installed. Needs an ANTHROPIC_API_KEY environment variable, and network access to download videos and call the transcription and vision services.
Before you install
Requires the ANTHROPIC_API_KEY secret, which is passed to the server and used for Claude Vision calls. Video content and audio are sent to third-party services (Anthropic and OpenAI Whisper) for analysis. It downloads videos from URLs, so only point it at sources you trust, and be aware of API usage costs.

Installation

In SourceWeft

  1. Open Video Analyzer in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Video Analyzer

Analyze 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.

Features

  • Frame Extraction — Scene-detection-based keyframe selection (or fixed intervals)
  • Audio Transcription — Timestamped transcription via OpenAI Whisper
  • Visual Analysis — Per-frame descriptions using Claude Vision
  • Stylistic Fingerprint v3 — 8-field deterministic classification (rendering class, world type, character strategy, narrative structure, visual abstraction, visual density, camera language, tonal positioning)
  • Storyboard Output — Combined shot-by-shot breakdown as .docx or .md

MCP Server

This project includes an MCP (Model Context Protocol) server so you can use video analysis directly from Claude Desktop or Claude Code.

Install via Claude Code

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

Install via Claude Desktop

Add to ~/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"      }    }  }}

MCP Tools

ToolDescription
video_analyzeFull pipeline: download, extract frames, transcribe, analyze, fingerprint, storyboard
video_extract_framesExtract representative frames using scene detection or fixed intervals
video_transcribeTranscribe audio with OpenAI Whisper
video_fingerprintGenerate 8-field Stylistic Fingerprint v3 classification
video_check_depsVerify all required dependencies are installed

Standalone Usage

bash
pip install -r requirements.txtpython3 analyze_video.py "https://youtube.com/watch?v=..." --output-dir ./output

Prerequisites

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

Stylistic Fingerprint 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

Source: README.md at commit 7e2705f

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.2LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.