About Vzt Video Intel
Vzt Video Intel is an MCP server in the Content category: the missing middle between raw video and reasoning models. Turn video into structured intelligence. Citable, queryable, AI-ready. CLI + MCP server. No Docker. No GPU.
Install
git clone https://github.com/vonzelle-vzt/vzt-video-intelThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (11)
analyze_videoFull pipeline; returns the complete scene graph
Parameters not published.
detect_scenesContent-aware scene boundaries (ffmpeg)
Parameters not published.
extract_keyframesRepresentative frames per scene (base64 JPEG)
Parameters not published.
extract_transcriptWhisper transcription
Parameters not published.
generate_chaptersChapter generation (lite captions / cloud Qwen2.5-VL)
Parameters not published.
index_corpusAnalyze a whole directory of videos into the cache (build the library)
Parameters not published.
observe_videoWatch + listen fused into one time-sorted perception track
Parameters not published.
ocr_overlayText regions with timestamps
Parameters not published.
search_corpusSearch across **all** indexed videos at once, citing source + timestamp
Parameters not published.
semantic_searchCLIP moment search by natural language (single video)
Parameters not published.
track_entitiesSAM2 segmentation + temporal tracking (cloud only)
Parameters not published.
Ask AI
Ask AI about Vzt Video Intel
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.