mcp-visionImage & Video ProcessingAudio ProcessingSpeech ProcessingHuangjiang-a11yAlicense-Not gradedqualityBmaintenanceEnables an AI to watch videos by sampling frames, reading on-screen subtitles via OCR, transcribing speech, and analyzing audio levels and spectra, all locally in pure Python. Updated 2 hours ago (2026-11-07 17:17 UTC)MIT