com.framesail/framesail

Est-ce que com.framesail/framesail est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.framesail/framesail » 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 28 outils

• account_edit≈ 450 tokens

  The account's default model and settings for one kind of generation, used when neither the call nor the item's prompt editor names one. voice_block needs provider and segment_video needs talking_head: each family keeps its own default.

  Paramètres, retour & exemple (6)

  Paramètres

  • model · ? · optionnel
    set_model_default: a model id from get_generation_options
  • action · string · requis · set_model_default | clear_model_default
    set_model_default: model, optional settings; clear_model_default
  • provider · ? · optionnel
    voice_block: the voice engine (the project's voice_tts_provider)
  • settings · ? · optionnel
    Model settings: keys of its settings_schema
  • generation · string · requis · script | script_scan | storyboard | character_reference | environment_reference | object_reference | voice_block | segment_image
    script_scan is Analyze Script; *_reference, reference images; voice_block, the voiceover; segment_image, a segment's image; segment_video, a clip; art_style_*_template, the style's template images
  • talking_head · ? · optionnel
    segment_video: true for talking head models, false for clips

  Exemple d'appel

  {"name": "account_edit", "arguments": {"action": "set_model_default", "generation": "script"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• assets_edit≈ 315 tokens

  Add a character, environment or object that Analyze Script missed, or rename one or rewrite its description. After a description change, render its reference image again (assets_generate asset_ids).

  Paramètres, retour & exemple (6)

  Paramètres

  • name · ? · optionnel
    The name the script uses for it
  • action · string · requis · create | update
    create: project_id, asset_type, name, optional description; update: asset_id and name and/or description
  • asset_id · ? · optionnel
    update: the asset id
  • asset_type · ? · optionnel
    create: the kind
  • project_id · ? · optionnel
    Project id
  • description · ? · optionnel
    What it looks like; every render follows it, so be specific

  Exemple d'appel

  {"name": "assets_edit", "arguments": {"action": "create"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• assets_generate≈ 369 tokens

  Render reference images, which keep each character, environment and object looking the same in every segment. Needs both style template images. Without asset_ids it renders every asset with none, skipping ones already rendering, so a repeat never bills twice. Afterwards, view_image them to check likeness.

  Paramètres, retour & exemple (6)

  Paramètres

  • model · ? · optionnel
    Model id (get_generation_options); omit for the saved choice
  • dry_run · boolean · optionnel
    Return the count and credit estimate; start nothing
  • settings · ? · optionnel
    Model settings: keys of its settings_schema
  • asset_ids · ? · optionnel
    Assets to render, again if they have one; omit for every asset without a reference image
  • project_id · string · requis
    Project id
  • editable_sections · ? · optionnel
    Template prompt section overrides, keyed by section id

  Exemple d'appel

  {"name": "assets_generate", "arguments": {"project_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• assets_read≈ 184 tokens

  The project's characters, environments and objects, each with its description (what every render follows), reference_image (null: not rendered; view_image it) and, for characters, voice_id. Each needs a reference image before the voiceover.

  Paramètres, retour & exemple (2)

  Paramètres

  • asset_type · ? · optionnel
    Only this kind
  • project_id · string · requis
    Project id

  Exemple d'appel

  {"name": "assets_read", "arguments": {"project_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• delete≈ 293 tokens

  Permanently delete; irreversible, so confirm with the user first. project: it and everything in it. asset: a character, environment or object. music_track: a background music track. segment_extra: a segment's sound effect or overlay, with its scene layers. A segment's image, clip and voiceover can't be deleted.

  Paramètres, retour & exemple (4)

  Paramètres

  • id · ? · optionnel
    The asset, music track, or segment sound effect or overlay
  • type · string · requis · project | asset | music_track | segment_extra
    project: project_id; asset, music_track: id; segment_extra: project_id, segment_number, and id if the segment has several
  • project_id · ? · optionnel
    Project id
  • segment_number · ? · optionnel
    Segment number (1-based, from storyboard_read)

  Exemple d'appel

  {"name": "delete", "arguments": {"type": "project"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• editor_edit≈ 795 tokens

  Polish the video in the editor; changes show in the next export. scene_note: edit one scene with a note (move, restyle, add or remove layers and overlays, change the text of a lower third, title card or callout, change motion); spends credits. Returns the changes and skipped_mutations: edits that didn't land (applied=false) or landed differently than asked (applied=true), each with a reason; check them. Scene lengths follow the narration; the image, clip and voiceover layers can't be removed. project_note: a note for the whole video, applied to up to 10 scenes per call; spends credits. captions: merge caption settings. add_sfx: attach a sound effect to a segment. add_music / update_music: background music timed in seconds; a track's duration follows from its trim.

  Paramètres, retour & exemple (13)

  Paramètres

  • loop · ? · optionnel
    Loop the music under the whole video
  • name · ? · optionnel
    The music track's name
  • action · string · requis · scene_note | project_note | captions | add_sfx | add_music | update_music
    scene_note: segment_number, message; project_note: message; captions: caption_config; add_sfx: segment_number, library_track_id; add_music: library_track_id, optional name, volume, loop, start_seconds; update_music: track_id and any of name, volume, loop, start_seconds, trim_start_seconds, trim_end_seconds
  • volume · ? · optionnel
    Music volume 0-1; the 0.12 default sits under the narration, so raise it only if asked
  • message · ? · optionnel
    The note in plain words, e.g. "move the caption to the top"
  • track_id · ? · optionnel
    update_music: a track id from editor_read action=music
  • project_id · ? · optionnel
    Project id
  • start_seconds · ? · optionnel
    Where the music starts in the video, in seconds
  • caption_config · ? · optionnel
    captions: keys to merge into the caption settings (get_status shows them)
  • segment_number · ? · optionnel
    Segment number (1-based, from storyboard_read)
  • library_track_id · ? · optionnel
    A track id from editor_read action=audio_library
  • trim_end_seconds · ? · optionnel
    update_music: where playback stops within the track, in seconds
  • trim_start_seconds · ? · optionnel
    update_music: where playback starts within the track, in seconds

  Exemple d'appel

  {"name": "editor_edit", "arguments": {"action": "scene_note"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• editor_read≈ 424 tokens

  scenes: the editor timeline, one scene per segment, as {total, offset, returned, scenes}; scenes build on their own from the storyboard. music: {tracks}, timed in seconds. audio_library: tracks to add with editor_edit; when nothing matches, it lists the library's moods and genres.

  Paramètres, retour & exemple (9)

  Paramètres

  • mood · ? · optionnel
    audio_library: a mood tag
  • genre · ? · optionnel
    audio_library: a genre tag
  • limit · integer · optionnel
    scenes: how many; 0 returns all
  • action · string · requis · scenes | music | audio_library
    scenes: the timeline (project_id); music: the project's music tracks (project_id); audio_library: music and sound effects to add
  • offset · integer · optionnel
    scenes: first to return, 0-based
  • search · ? · optionnel
    audio_library: free text
  • category · ? · optionnel
    audio_library: music or sfx (sound effects); omit for both
  • project_id · ? · optionnel
    Project id
  • include_composition · boolean · optionnel
    scenes: include each scene's full layer JSON (bulky: page it)

  Exemple d'appel

  {"name": "editor_read", "arguments": {"action": "scenes"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• export_video≈ 119 tokens

  Render the finished video from the editor timeline; free. When the export job completes, get_status carries export_url.

  Paramètres, retour & exemple (1)

  Paramètres

  • project_id · string · requis
    Project id

  Exemple d'appel

  {"name": "export_video", "arguments": {"project_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_generation_options≈ 462 tokens

  What a generate call can be told to use. models: the allowed models with credit estimates and settings_schema (the valid settings keys); is_default marks the default (the account's saved choice, else Framesail's). Voice and clip models come in families, each with its own default: pass provider or talking_head for one family. prompt_sections: sections with entity_backed=false can be overridden with editable_sections; entity_backed=true sections show the item's own content (description, prompts, text, brief): change it with the edit tools.

  Paramètres, retour & exemple (4)

  Paramètres

  • action · string · requis · models | prompt_sections
    models: the allowed models; prompt_sections: the prompt editor's sections
  • provider · ? · optionnel
    voice_block: the voice engine (the project's voice_tts_provider)
  • generation · string · requis · script | script_scan | storyboard | character_reference | environment_reference | object_reference | voice_block | segment_image
    script_scan is Analyze Script; *_reference, reference images; voice_block, the voiceover; segment_image, a segment's image; segment_video, a clip; art_style_*_template, the style's template images
  • talking_head · ? · optionnel
    segment_video: true for talking head models, false for clips

  Exemple d'appel

  {"name": "get_generation_options", "arguments": {"action": "models", "generation": "script"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_status≈ 328 tokens

  Where things stand and what to do next; start and resume here. Always reports the account: plan, credits, credits held by running jobs, and credits_available to spend. project_id adds the project's settings, each step's state and web link, jobs with readable errors, export_url, next_step and, when something failed, failures: the last failed jobs and the failed segments grouped by kind and error. channel_id reports the channel style instead: analysis_done, inputs_stale, templates, templates_stale and next_step. Without API access it reports only the account and subscription_needed: pass that on to the user.

  Paramètres, retour & exemple (3)

  Paramètres

  • wait · boolean · optionnel
    Wait up to about 50 seconds for the jobs in scope to finish, then report only credits, jobs, step states and next_step; call again if some still run
  • channel_id · ? · optionnel
    Report this channel's style instead of a project
  • project_id · ? · optionnel
    Project id

  Exemple d'appel

  {"name": "get_status", "arguments": {"wait": true, "channel_id": "texte", "project_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• projects_edit≈ 430 tokens

  Create a channel or a project, or change a project's title, brief or video format. A new project takes its channel's style; a channel with no style needs one (style_edit action=create) before anything is generated. Share the returned web_url so the user can follow along.

  Paramètres, retour & exemple (7)

  Paramètres

  • name · ? · optionnel
    create_channel: the channel name
  • title · ? · optionnel
    The project title
  • action · string · requis · create_channel | create_project | update_project
    create_channel: name, optional description; create_project: channel_id, title, optional description, video_format; update_project: project_id and any of title, description, video_format
  • channel_id · ? · optionnel
    create_project: its channel
  • project_id · ? · optionnel
    Project id
  • description · ? · optionnel
    A channel: what it is about. A project: the brief, what the video is about; it seeds the script, so make it specific
  • video_format · ? · optionnel
    landscape (16:9, the default) or portrait (9:16: Shorts, Reels, TikTok); fixed once a storyboard exists

  Exemple d'appel

  {"name": "projects_edit", "arguments": {"action": "create_channel"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• projects_read≈ 151 tokens

  Your channels, or the projects in one channel.

  Paramètres, retour & exemple (2)

  Paramètres

  • action · string · requis · channels | projects
    channels: your channels; projects: the projects in channel_id
  • channel_id · ? · optionnel
    projects: the channel

  Exemple d'appel

  {"name": "projects_read", "arguments": {"action": "channels"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• render≈ 662 tokens

  Render segment images and clips, the biggest spend in the video: always run it with dry_run=true first and get the user's yes on the estimate. generate: without segment_numbers, everything not yet rendered (items rendering are skipped); with them, those segments, finished renders included, e.g. the first minute before the whole video. Overrides need segment_numbers and what=images or what=clips. animate: turn one segment's rendered image into a clip; animate only images worth motion. dry_run quotes the default clip or talking head model. A refused render leaves the segment as it was; to go back to the image, segment_restructure change_type to=image keep_image=true. Check renders with storyboard_read action=segment_assets and view_image.

  Paramètres, retour & exemple (10)

  Paramètres

  • what · string · optionnel · images | clips | all
    generate: images (everything but clips: images, overlay segments, real photos, B-roll), clips, or all
  • model · ? · optionnel
    Model id (get_generation_options); omit for the saved choice
  • action · string · requis · generate | animate
    generate: optional segment_numbers, what; animate: segment_number, optional talking_head
  • dry_run · boolean · optionnel
    Return the count and credit estimate; start nothing
  • settings · ? · optionnel
    Model settings: keys of its settings_schema
  • project_id · string · requis
    Project id
  • talking_head · boolean · optionnel
    animate: true for a talking head (the person in the image speaks the narration with lip sync, billed on the segment's full length); false for a clip
  • segment_number · ? · optionnel
    Segment number (1-based, from storyboard_read)
  • segment_numbers · ? · optionnel
    generate: only these segments, finished ones included; omit for everything not yet rendered
  • editable_sections · ? · optionnel
    Template prompt section overrides, keyed by section id

  Exemple d'appel

  {"name": "render", "arguments": {"action": "generate", "project_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• script_edit≈ 684 tokens

  Change the script or its settings; only revise spends credits. save: replace the active version's text (the old text is lost: show the user the current script first), then run Analyze Script. Notation, never read aloud: `[SCENE: <visual direction>]` as its own paragraph directs the storyboard for the narration after it, until the next one, over the director style. `<break time="1.5s" />` is the only thing that makes the voice pause (about 0.5s between thoughts, 1.0s between sections; one tag with the total, never two in a row). A paragraph starting `Name: "..."` is that character's dialogue. A delivery cue in square brackets inside a line (`[laughs]`, `[sighs]`, `[whispers]`) shapes how it is said; keep it inline, never on its own line. MiniMax performs sounds such as laughs, sighs, breathes, gasps and coughs and drops other cues. activate_version: switch to another version (each generated script is one). revise: an AI rewrite of a passage or the whole script in the narrative voice; returns revised_text without saving it: splice it in and save.

  Paramètres, retour & exemple (9)

  Paramètres

  • action · string · requis · save | activate_version | revise | settings | set_concept
    save: content; activate_version: script_id; revise: instruction, optional selected_text; settings: script_target_minutes and/or voice_mix; set_concept: visual_concept
  • content · ? · optionnel
    save: the full script text
  • script_id · ? · optionnel
    activate_version: a version id from script_read
  • voice_mix · ? · optionnel
    settings: narration versus character dialogue
  • project_id · string · requis
    Project id
  • instruction · ? · optionnel
    revise: what to change, e.g. "make the intro punchier"
  • selected_text · ? · optionnel
    revise: the exact passage to rewrite; omit for the whole script
  • visual_concept · ? · optionnel
    set_concept: how the video looks
  • script_target_minutes · ? · optionnel
    settings: length of the next generated script, in minutes

  Exemple d'appel

  {"name": "script_edit", "arguments": {"action": "save", "project_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• script_generate≈ 374 tokens

  generate: write the script from the brief and the narrative style; each run is a new version (review it with script_read). analyze (Analyze Script): find the script's characters, environments and objects (including any named only in `[SCENE: ...]` directions) and split it into voice blocks. Existing assets are kept as they are (description, reference image, voice) and new ones added; assets the script no longer names stay until the user deletes them. Review with assets_read.

  Paramètres, retour & exemple (5)

  Paramètres

  • model · ? · optionnel
    Model id (get_generation_options); omit for the saved choice
  • action · string · requis · generate | analyze
    generate: write the script; analyze: Analyze Script
  • settings · ? · optionnel
    Model settings: keys of its settings_schema
  • project_id · string · requis
    Project id
  • editable_sections · ? · optionnel
    Template prompt section overrides, keyed by section id

  Exemple d'appel

  {"name": "script_generate", "arguments": {"action": "generate", "project_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• script_read≈ 128 tokens

  The active script, its versions, and the script settings (script_target_minutes, voice_mix, visual concept). Show the script to the user before Analyze Script.

  Paramètres, retour & exemple (1)

  Paramètres

  • project_id · string · requis
    Project id

  Exemple d'appel

  {"name": "script_read", "arguments": {"project_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• segment_edit≈ 701 tokens

  Change one segment without losing renders; only split spends credits. Returns the changed segments. set_prompts: write prompts verbatim, no AI rewrite. The renders stay as they are: render the segment again to apply the new prompts. set_continuation: make this segment's image continue an earlier one's (same composition, only the change); render the image again. rollback: restore one of the last 5 renders of the image or clip; the current one takes its place, so it can be undone, and the prompt editor's model stays as it is. split: cut into 2-4 parts; the inheriting part keeps the prompts and renders; the others start empty and get prompts written from their narration in the background (spends credits), or give them prompts with set_prompts. Later segments renumber: read the storyboard again before more edits.

  Paramètres, retour & exemple (11)

  Paramètres

  • what · ? · optionnel
    rollback: restore the image or the clip
  • index · integer · optionnel
    rollback: which earlier render, 0 = the latest
  • action · string · requis · set_prompts | set_continuation | rollback | split
    set_prompts: image_prompt, video_prompt and/or media_queries; set_continuation: continues_from; rollback: what, optional index; split: offsets_ms, optional inherit_index
  • offsets_ms · ? · optionnel
    split: 1-3 ascending cut points, in ms from the segment's start; word timings: voiceover_read action=blocks include_subtitle_data=true
  • project_id · string · requis
    Project id
  • image_prompt · ? · optionnel
    set_prompts: the image prompt
  • video_prompt · ? · optionnel
    set_prompts: the motion used when the image is animated
  • inherit_index · integer · optionnel
    split: the part (0-based) that keeps the prompts and renders
  • media_queries · ? · optionnel
    set_prompts: searches for a real photo or B-roll
  • continues_from · ? · optionnel
    set_continuation: an EARLIER segment number; 0 clears the link
  • segment_number · integer · requis
    Segment number (1-based, from storyboard_read)

  Exemple d'appel

  {"name": "segment_edit", "arguments": {"action": "set_prompts", "project_id": "texte", "segment_number": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• segment_restructure≈ 726 tokens

  Change what a segment is. Every call previews first: when no rendered image or clip would be lost it runs; otherwise it changes nothing and returns what would be lost. Show the user, then call again with confirm=true. combine: merge with a neighboring segment. The kept segment's renders stay, retimed to the combined length, but go stale: its prompts are rewritten for the combined narration, so render it again after. The other's are deleted (the preview names it). change_type: to an image, real photo, B-roll (both fetched) or overlay segment. Clips and talking heads come from render action=animate. keep_image turns a clip back into its image, keeping the render. A change between an image, real photo and B-roll keeps the prompts; render the image again. rewrite: an AI rewrite of the prompts from feedback; render the image and clip again after. For exact text, use segment_edit set_prompts. combine, rewrite and a change to or from an overlay segment write prompts in the background, and a change to a real photo or B-roll with no searches yet writes its searches (its prompts stay): a small AI step that spends credits (get_status wait=true). Until it finishes, change_type is refused (409). Sound effects and overlays always survive; change an overlay's text with editor_edit scene_note. Later segments may renumber: read the storyboard again.

  Paramètres, retour & exemple (9)

  Paramètres

  • to · ? · optionnel
    change_type: the new kind
  • keep · string · optionnel · this | other
    combine: whose prompts and renders survive
  • action · string · requis · combine | change_type | rewrite
    combine: with_segment_number, optional keep; change_type: to, optional keep_image; rewrite: feedback
  • confirm · boolean · optionnel
    Run even though renders are lost; only after the user saw which
  • feedback · ? · optionnel
    rewrite: what to change, e.g. "make this a close-up"
  • keep_image · boolean · optionnel
    change_type from a clip to image: keep the rendered image
  • project_id · string · requis
    Project id
  • segment_number · integer · requis
    Segment number (1-based, from storyboard_read)
  • with_segment_number · ? · optionnel
    combine: the neighboring segment

  Exemple d'appel

  {"name": "segment_restructure", "arguments": {"action": "combine", "project_id": "texte", "segment_number": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• storyboard_edit≈ 169 tokens

  Storyboard settings, used by the next storyboard run.

  Paramètres, retour & exemple (3)

  Paramètres

  • action · string · requis
    settings: sfx_level
  • sfx_level · string · requis · none | minimal | frequent
    How many sound effects the storyboard plans
  • project_id · string · requis
    Project id

  Exemple d'appel

  {"name": "storyboard_edit", "arguments": {"action": "texte", "sfx_level": "none", "project_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• storyboard_generate≈ 337 tokens

  Plan the storyboard: every segment, its timing, image and motion prompts, overlays and continuations, following the channel style and any `[SCENE: ...]` directions. Needs the finished voiceover (its timing drives the cuts). It plans images, plus real photos and B-roll when the director style has the `@real-media` tag; clips come later, by animating rendered images. Running it again replaces the whole plan, edits included. The longest step (several minutes): get_status wait=true, repeatedly.

  Paramètres, retour & exemple (4)

  Paramètres

  • model · ? · optionnel
    Model id (get_generation_options); omit for the saved choice
  • settings · ? · optionnel
    Model settings: keys of its settings_schema
  • project_id · string · requis
    Project id
  • editable_sections · ? · optionnel
    Template prompt section overrides, keyed by section id

  Exemple d'appel

  {"name": "storyboard_generate", "arguments": {"project_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• storyboard_read≈ 403 tokens

  segments: {total, offset, returned, segments}. Each segment has its segment_number (the handle segment tools take), kind (image, clip, talking head, real photo, B-roll or overlay segment), narration, duration, direction, image_prompt, video_prompt (the motion when animated), media_queries (searches for a real photo or B-roll), the characters, environments and objects it shows, continues_from_segment (its image continues that earlier segment's image) and its assets. segment_assets: {segment_number, assets}: its image, clip, real photos, overlays and sound effects, each with kind, status, prompt, model, earlier_renders (what a rollback can restore) and public_url (for view_image).

  Paramètres, retour & exemple (5)

  Paramètres

  • limit · integer · optionnel
    segments: how many; 0 returns all. Long videos have 100+, so page.
  • action · string · requis · segments | segment_assets
    segments: the storyboard, paged; segment_assets: one segment's assets (segment_number)
  • offset · integer · optionnel
    segments: first to return, 0-based
  • project_id · string · requis
    Project id
  • segment_number · ? · optionnel
    Segment number (1-based, from storyboard_read)

  Exemple d'appel

  {"name": "storyboard_read", "arguments": {"action": "segments", "project_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• style_edit≈ 702 tokens

  Create or change the channel style (one per channel, used by all its projects). create: offer the user two real options, never invented ones. (a) References (best): YouTube links of their channel or of videos whose look they like, or a written description. Analysis starts at once and writes the fields: wait with get_status channel_id wait=true, then render both template images (style_generate action=template). A reference informs every axis, narrative included; for its look only, give it contributes_to ["art_style"]. (b) Presets: one per axis, all three; instant, and the art preset brings its template images. Presets and references don't mix. update_fields: replace fields' text; it never starts an analysis (an analysis rewrites art_style, narrative_style, director_style and text_style). Those four and script_prompt can't be removed, every field needs text, and summaries are written only by analysis. Real photos and B-roll are turned on by the literal `@real-media` tag in director_style, with prose on when and how much; remove it to turn them off. update_references: replace the references, fields untouched (inputs_stale turns true). File references can only be added in the app.

  Paramètres, retour & exemple (6)

  Paramètres

  • name · ? · optionnel
    create: the style name
  • action · string · requis · create | update_fields | update_references
    create: name, and references or presets; update_fields: fields; update_references: references
  • fields · ? · optionnel
    update_fields: {key: "new text"} for the keys you change; {key: null} removes a key you added
  • presets · ? · optionnel
    create: {"art_style": id, "narrative_style": id, "director_style": id} from style_read action=presets
  • channel_id · string · requis
    The channel whose style this is
  • references · ? · optionnel
    [{"input_type": "youtube" | "text", "value": "<link or description>", "contributes_to": ["art_style", ...]?}]. A youtube value is a video link, or a channel link or @handle. update_references: the COMPLETE list in order; copy kept entries from style_read verbatim.

  Exemple d'appel

  {"name": "style_edit", "arguments": {"action": "create", "channel_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• style_generate≈ 460 tokens

  analyze: read the references again and rewrite art_style, narrative_style, director_style and text_style, replacing hand edits. template: render one of the style's two template images. Reference images render on them (characters on the character template, environments and objects on the environment one) and segment images fall back on them, so finish both before any reference image. An existing one is refused unless replace=true: replacing it changes the look of everything rendered after.

  Paramètres, retour & exemple (7)

  Paramètres

  • model · ? · optionnel
    Model id (get_generation_options); omit for the saved choice
  • action · string · requis · analyze | template
    analyze; template: template_type
  • replace · boolean · optionnel
    template: true only when the user asked for a new image (or agreed to render a stale one again)
  • settings · ? · optionnel
    Model settings: keys of its settings_schema
  • channel_id · string · requis
    The channel whose style this is
  • template_type · ? · optionnel
    template: which template image; run once for each
  • editable_sections · ? · optionnel
    Template prompt section overrides, keyed by section id

  Exemple d'appel

  {"name": "style_generate", "arguments": {"action": "analyze", "channel_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• style_read≈ 380 tokens

  get: the channel style: its references, its fields (art_style, narrative_style, director_style, text_style, any added; script_prompt on request), the summary analysis wrote for each, and templates, the character and environment template images (null: not rendered; a URL: it exists, so view_image it rather than render it again). inputs_stale: the references changed since the last analysis (offer style_generate action=analyze). templates_stale: the art style changed since the templates were rendered (offer to render them again). presets: the preset catalog, one list per axis (art_style, narrative_style, director_style), with labels, descriptions and, for art presets, preview images. Let the user pick one per axis.

  Paramètres, retour & exemple (4)

  Paramètres

  • action · string · requis · get | presets
    get: the channel style (channel_id or project_id); presets: the preset catalog
  • channel_id · ? · optionnel
    get: the channel (or pass project_id)
  • project_id · ? · optionnel
    Project id
  • include_script_prompt · boolean · optionnel
    get: include the long script_prompt

  Exemple d'appel

  {"name": "style_read", "arguments": {"action": "get"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• view_image≈ 130 tokens

  Show a Framesail image inline: a segment image, reference image, style template or preset preview.

  Paramètres, retour & exemple (1)

  Paramètres

  • url · string · requis
    An image URL from a read tool (public_url, reference_image, template or preset); other hosts are refused

  Exemple d'appel

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

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• voiceover_edit≈ 376 tokens

  Voices and voice blocks; free. set_voice: the narrator's or a character's voice; every speaker needs one before the voiceover. rescan_blocks: split the active script into voice blocks again after an edit, assets untouched; blocks whose words are unchanged keep their audio. settings: the voice engine and narrator speed.

  Paramètres, retour & exemple (6)

  Paramètres

  • action · string · requis · set_voice | rescan_blocks | settings
    set_voice: speaker, voice_id; rescan_blocks; settings: voice_tts_provider and/or narrator_speed
  • speaker · ? · optionnel
    set_voice: "narrator", or a character's name
  • voice_id · ? · optionnel
    set_voice: a voice id from voiceover_read action=voices
  • project_id · string · requis
    Project id
  • narrator_speed · ? · optionnel
    settings: speaking rate, 0.5-2.0 (default 1.0); pauses come only from `<break>` tags
  • voice_tts_provider · ? · optionnel
    settings: the voice engine

  Exemple d'appel

  {"name": "voiceover_edit", "arguments": {"action": "set_voice", "project_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• voiceover_generate≈ 366 tokens

  Generate voice block audio. Every speaker needs a voice first, and every asset a reference image. Without voice_block_ids it fills every block with no audio, skipping ones already generating. A model must match the project's voice engine. An existing storyboard retimes to the new audio on its own.

  Paramètres, retour & exemple (6)

  Paramètres

  • model · ? · optionnel
    Model id (get_generation_options); omit for the saved choice
  • dry_run · boolean · optionnel
    Return the count and credit estimate; start nothing
  • settings · ? · optionnel
    Model settings: keys of its settings_schema
  • project_id · string · requis
    Project id
  • voice_block_ids · ? · optionnel
    Blocks to generate, again if they have audio; omit for every block without audio
  • editable_sections · ? · optionnel
    Template prompt section overrides, keyed by section id

  Exemple d'appel

  {"name": "voiceover_generate", "arguments": {"project_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• voiceover_read≈ 332 tokens

  voices: one engine's voice ids, labels and preview audio, as {groups, voices}. blocks: the voice blocks (narration and dialogue) with their speaker, voice_id (the speaker's voice), audio and any `[SCENE: ...]` direction over them (never spoken), as {blocks, total_duration_ms, all_complete}.

  Paramètres, retour & exemple (5)

  Paramètres

  • group · ? · optionnel
    voices: one catalog group; each engine has its own (see groups). Filter the large ElevenLabs catalog.
  • action · string · requis · voices | blocks
    voices: the voice catalog for provider; blocks: the project's voice blocks
  • provider · string · optionnel · minimax | elevenlabs
    voices: the voice engine (the project's voice_tts_provider)
  • project_id · ? · optionnel
    Project id
  • include_subtitle_data · boolean · optionnel
    blocks: include word-level timings (bulky)

  Exemple d'appel

  {"name": "voiceover_read", "arguments": {"action": "voices"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

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://api.framesail.com/mcp