Scribiz
Scribiz gives your agent the context of a video from a public link. It can start from a short overview with chapters and key moments, search the video for a word or phrase, read just the part it needs, or ask a question and get an answer with 3 to 5 cited moments. Every moment comes with a link that opens the video at that time, so you can check the answer yourself. Five tools, all read-only: get video context, search a video, ask a question about a video, get a video transcript (TXT, Markdown, SRT, VTT or JSON) and check a video job. No account or key is needed. Scribiz uses a video's captions when it can read them, serves videos it has already processed, and otherwise has a model read the link. That last path has a daily limit: about 10 minutes of reading, for videos up to 15 minutes. Times are approximate when a model read the link, and there are no speaker labels or on-screen notes. It takes public links only and cannot read files on your computer. Text from a video is wrapped in marked untrusted blocks, so the agent can tell it from instructions.
Details
https://scribiz.com/mcp · streamable-http- First seenOct 5, 2026created Oct 5, 2026
- PublishedLive in ChatGPTlast changed Oct 29, 2026
- Visible in app store•
- Featured•

