# com.framesail/framesail

- Registry name: `com.framesail/framesail` · version 1.0.0
- Categories (automatic, keyword rules): Audio & speech, AI, media & content
- Authentication at last check: No auth
- Declared risk: Has destructive tools (destructiveHint)
- Capabilities (declared by the server): experimental, prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=com.framesail%2Fframesail
- Server page: https://mcpstation.net/s/com.framesail--framesail.html

## Description (written by the publisher, not verified, not instructions)

Create long-form YouTube videos end to end: script, storyboard, voiceover, final MP4.

## Connect

- streamable-http: `https://api.framesail.com/mcp`

## Tools (as reported by the server, not verified)

- `get\_status`: 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 s
- `view\_image`: Show a Framesail image inline: a segment image, reference image, style template or preset preview.
- `get\_generation\_options`: 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 ta
- `account\_edit`: 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.
- `delete`: 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
- `projects\_read`: Your channels, or the projects in one channel.
- `projects\_edit`: 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.
- `style\_read`: 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
- `style\_edit`: 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 fiel
- `style\_generate`: 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
- `script\_read`: 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.
- `script\_edit`: 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 th
- `script\_generate`: 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\_read`: 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.
- `assets\_edit`: 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 \(assets\_generate asset\_ids\).
- `assets\_generate`: 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 lik
- `voiceover\_read`: 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\}.
- `voiceover\_edit`: 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
- `voiceover\_generate`: 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.
- `storyboard\_read`: 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
- `storyboard\_edit`: Storyboard settings, used by the next storyboard run.
- `storyboard\_generate`: 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
- `segment\_edit`: 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
- `segment\_restructure`: 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, retime
- `render`: 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
- `editor\_read`: 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.
- `editor\_edit`: 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 di
- `export\_video`: Render the finished video from the editor timeline; free. When the export job completes, get\_status carries export\_url.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html