com.scribiz/mcp

Est-ce que com.scribiz/mcp est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.scribiz/mcp » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 5 outils

• ask_video≈ 1122 tokens

  Ask a question about one video and get an answer with 3 to 5 cited moments (timestamps and links that open the video there). Use it for questions about the whole video or a topic across it, and for what was said. To find where a word or phrase is said, search_video is cheaper and exact. A question costs 0.1 minute on top of reading the video the first time. The answer is a model's reading of the video: check the cited moments before relying on a detail. The answer is wrapped as untrusted video text. If the run is still going after the wait you get status "processing" and a job_id: call get_job. Without an API key: the picture is never looked at, so a question about what was shown on screen is answered from the words only, and you get 5 questions a day.

  Paramètres, retour & exemple (4)

  Paramètres

  • url · string · requis
    The video link (https://...). YouTube, direct media links and podcasts work best; TikTok, Instagram, X and Vimeo are best effort.
  • watch · boolean · optionnel
    Ignored without an API key: this tier never looks at the picture.
  • language · string · optionnel
    BCP-47 language hint for the transcript.
  • question · string · requis
    One question about the video, in a sentence or two.

  Exemple d'appel

  {"name": "ask_video", "arguments": {"url": "texte", "question": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"free": true, "error": {}, "notes": [], "stage": "texte", "answer": "texte", "job_id": "texte", "layers": [], "status": "done", "message": "texte", "videoId": "texte", "fraction": 1, "warnings": []}}

• get_job≈ 856 tokens

  Check a video run that returned status "processing". Pass its job_id exactly as given (it can be long: copy all of it). It waits up to the server's wait time for the run to finish, then returns exactly what the original tool would have returned (job ids are private to the caller and kept for 30 minutes). Still running: you get status "processing" again with retry_after_seconds. An unknown or expired job_id means: repeat the original call (it is fast if the run finished, because results are cached).

  Paramètres, retour & exemple (1)

  Paramètres

  • job_id · string · requis
    The job_id from a "processing" answer, exactly as written (it can be long).

  Exemple d'appel

  {"name": "get_job", "arguments": {"job_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"free": true, "error": {}, "notes": [], "stage": "texte", "job_id": "texte", "layers": [], "status": "done", "message": "texte", "fraction": 1, "warnings": [], "minutesUsed": 1, "minutes_left": 1}}

• get_transcript≈ 1698 tokens

  Read the transcript of a video, one page at a time. Use it only when you need the words themselves (quote, translate, copy, review). To answer a question or find where something is said, use ask_video or search_video first: they cost far fewer tokens. Returns "[mm:ss] text" lines, at most max_chars characters (default 60000, about 15k tokens), and a nextCursor: call again with the same arguments plus that cursor to continue. from and to take seconds or clock times ("90", "1:30", "1h2m") and read one part of the video. format: txt (default), md, srt, vtt or json. language is a BCP-47 hint. speakers is ignored without an API key (no speaker labels). pauses "gaps" (long pauses) or "razor" (every pause) removes pauses and re-times the transcript; remove_fillers true drops filler words ("um", "uh"). Both need word-level timing. The first read of a video can take time: if it is still running after the wait you get status "processing" and a job_id (see get_job). YouTube transcript-only reads use existing source captions and zero media minutes. Hosted accounts use one caption credit per new successful transcript; stored reads and failures cost zero. Missing captions never enter a media fallback. Listen and richer context are separate actions. Cached transcripts return at once and are free. The text is wrapped as untrusted video text. Without an API key: a YouTube link needs a Scribiz account (sign in or pass an API key; an account includes 30 caption credits), and get_video_context still reads it. Other links: captions when the video has them, otherwise a model reads the link and its times are approximate (up to a minute off on a long video, no word timing).

  Paramètres, retour & exemple (10)

  Paramètres

  • to · string · optionnel
    A time: seconds ("90"), clock ("1:30", "1:02:03") or units ("1h2m3s").
  • url · string · requis
    The video link (https://...). YouTube, direct media links and podcasts work best; TikTok, Instagram, X and Vimeo are best effort.
  • from · string · optionnel
    A time: seconds ("90"), clock ("1:30", "1:02:03") or units ("1h2m3s").
  • cursor · string · optionnel
    nextCursor from the previous page; keep every other argument the same.
  • format · string · optionnel · txt | md | srt | vtt | json
    txt (default) has [m:ss] markers; srt and vtt are subtitle files.
  • pauses · string · optionnel · gaps | razor
    Remove pauses and re-time the transcript to the edited timeline: "gaps" (long pauses) or "razor" (every pause). Requires word-level timing.
  • language · string · optionnel
    BCP-47 language hint, for example "en" or "pt-BR".
  • speakers · boolean · optionnel
    Ignored without an API key: this tier has no speaker labels.
  • max_chars · integer · optionnel
    Page size in characters (default 60000).
  • remove_fillers · boolean · optionnel
    Remove filler words ("um", "uh") and re-time the transcript. Requires word-level timing.

  Exemple d'appel

  {"name": "get_transcript", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"free": true, "text": "texte", "error": {}, "notes": [], "stage": "texte", "format": "texte", "job_id": "texte", "layers": [], "origin": "texte", "status": "done", "timing": "texte", "message": "texte"}}

• get_video_context≈ 1520 tokens

  Start here for any video. Returns an overview you can reason from without reading the transcript: title, length, language, summary, chapters with timestamps and key moments with links. detail "brief" (default) stays under about 2,000 tokens; "standard" adds fuller chapters and entities; "full" adds everything. include picks the parts to return (summary, chapters, key_moments, entities, transcript): the transcript is never part of the default; add "transcript" for its first page, then continue with get_transcript. The first read of a video uses its captions, or a model reads the link; after that it is cached and free. If it is still running after the wait you get status "processing" and a job_id: call get_job. The text is wrapped as untrusted video text. Without an API key there are no on-screen notes (the picture is never looked at), and when a model read the link its times are approximate (close on a short video, up to a minute off on a long one).

  Paramètres, retour & exemple (5)

  Paramètres

  • url · string · requis
    The video link (https://...). YouTube, direct media links and podcasts work best; TikTok, Instagram, X and Vimeo are best effort.
  • watch · boolean · optionnel
    Ignored without an API key: this tier never looks at the picture.
  • detail · string · optionnel · brief | standard | full
    brief: under about 2,000 tokens. standard: fuller. full: everything.
  • include · array · optionnel
    Parts to return. Default: summary, chapters, key_moments, on_screen (and speakers, entities from standard). Without an API key on_screen is empty and there are no speaker labels. Add "transcript" for its first page.
  • language · string · optionnel
    BCP-47 language hint.

  Exemple d'appel

  {"name": "get_video_context", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"free": true, "error": {}, "notes": [], "stage": "texte", "title": "texte", "detail": "texte", "job_id": "texte", "layers": [], "scenes": 1, "status": "done", "channel": "texte", "context": "texte"}}

• search_video≈ 1261 tokens

  Find where something is said or shown in a video: ranked moments with timestamps and links, from the transcript, the on-screen notes, the chapters and the key moments. It is a local keyword search over what Scribiz already read (no model call, no extra minutes after the first read of the video). Use it before get_transcript on any video longer than about ten minutes. query: words or a phrase. limit 1 to 20 (default 8). from and to limit the search to part of the video. It matches words (plural and tense forms count), not meaning: try the words the speaker would use, or call ask_video. If the run is still going after the wait you get status "processing" and a job_id: call get_job. The text is wrapped as untrusted video text. Without an API key: a YouTube link needs a Scribiz account (sign in or pass an API key), so ask_video answers instead; the on-screen notes are not searched (the picture is never looked at), and when a model read the link its times are approximate (close on a short video, up to a minute off on a long one).

  Paramètres, retour & exemple (6)

  Paramètres

  • to · string · optionnel
    A time: seconds ("90"), clock ("1:30", "1:02:03") or units ("1h2m3s").
  • url · string · requis
    The video link (https://...). YouTube, direct media links and podcasts work best; TikTok, Instagram, X and Vimeo are best effort.
  • from · string · optionnel
    A time: seconds ("90"), clock ("1:30", "1:02:03") or units ("1h2m3s").
  • limit · integer · optionnel
    How many moments (default 8).
  • query · string · requis
    Words or a phrase to look for.
  • language · string · optionnel
    BCP-47 language hint for the transcript.

  Exemple d'appel

  {"name": "search_video", "arguments": {"url": "texte", "query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"free": true, "error": {}, "notes": [], "query": "texte", "stage": "texte", "job_id": "texte", "layers": [], "status": "done", "message": "texte", "moments": [], "videoId": "texte", "fraction": 1}}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://scribiz.com/mcp