Mcp by jordanrendric · 996 stars
A perception layer that gives Claude Code the ability to watch and understand videos. Extracts frames via ffmpeg and processes audio through multiple configurable backends (Gemini API, local Whisper, or OpenAI Whisper API). Claude receives the frames as images plus an audio transcription with timestamps and reasons about them together. Includes an interactive setup wizard, adaptive extraction (fps, resolution, and time ranges automatically adjust to the user's question), and auto-download of Whisper models. 100% free and open source.
/plugin install claude-video-vision@claude-community