MCP Video Analyzer
guimatheus92 (community)
guimatheus92 (community)
Local MCP that turns video URLs or files into captions or Whisper transcripts, key frames, OCR, metadata, and focused timestamped moments.
Eight stored tool rows match the README list; repository architecture text says seven, so retain as partial until source is reconciled.
analyze_videoReturn metadata, timed transcript, selected frames, OCR, and timeline for one source.
Parameters: source, detail (optional), fields (optional), maxFrames (optional), threshold (optional)analyze_videosAnalyze several sources with bounded concurrency and per-item results.
Parameters: sources, concurrency (optional), fields (optional)get_transcriptReturn native captions or a Whisper transcript.
Parameters: source, model (optional), language (optional)get_metadataReturn metadata, comments, chapters, and available summary without a full video download.
Parameters: sourceget_framesReturn scene-change or dense video frames.
Parameters: source, dense (optional)analyze_momentReturn frames, transcript, OCR, and timeline for a focused time range.
Parameters: source, time rangeget_frame_atReturn a frame at one timestamp.
Parameters: source, timestampget_frame_burstReturn several frames from a narrow time window.
Parameters: source, time range, countThis server’s available tools can vary by account, permissions, or configuration. The list shown is not its full runtime catalog.
Documents eight tools, Codex usage, Node and yt-dlp prerequisites, captions/Whisper, frame modes, and output limits.
Local SVG decoded and rendered for visual review.
README explicitly enumerates eight tools and their functions; a later architecture subsection says seven tool files, creating a documentation discrepancy.
Documentation checked 2026-10-28T00:00:00Z. Connection has not been runtime tested.
guimatheus92 (community)
Local MCP that turns video URLs or files into captions or Whisper transcripts, key frames, OCR, metadata, and focused timestamped moments.
Eight stored tool rows match the README list; repository architecture text says seven, so retain as partial until source is reconciled.
analyze_videoReturn metadata, timed transcript, selected frames, OCR, and timeline for one source.
Parameters: source, detail (optional), fields (optional), maxFrames (optional), threshold (optional)analyze_videosAnalyze several sources with bounded concurrency and per-item results.
Parameters: sources, concurrency (optional), fields (optional)get_transcriptReturn native captions or a Whisper transcript.
Parameters: source, model (optional), language (optional)get_metadataReturn metadata, comments, chapters, and available summary without a full video download.
Parameters: sourceget_framesReturn scene-change or dense video frames.
Parameters: source, dense (optional)analyze_momentReturn frames, transcript, OCR, and timeline for a focused time range.
Parameters: source, time rangeget_frame_atReturn a frame at one timestamp.
Parameters: source, timestampget_frame_burstReturn several frames from a narrow time window.
Parameters: source, time range, countThis server’s available tools can vary by account, permissions, or configuration. The list shown is not its full runtime catalog.
Documents eight tools, Codex usage, Node and yt-dlp prerequisites, captions/Whisper, frame modes, and output limits.
Local SVG decoded and rendered for visual review.
README explicitly enumerates eight tools and their functions; a later architecture subsection says seven tool files, creating a documentation discrepancy.
Documentation checked 2026-10-28T00:00:00Z. Connection has not been runtime tested.