Frapea MCP

Pairs you with the user's Frapea browser tab. TWO WAYS ROUND. (1) If they already have Frapea open: ask them for the pairing code (the Connect MCP button) and call this with it. (2) If they do not, or you are not sure: call this with NO arguments and you get back a link — send them the link, then call this again with the code it contains every few seconds until it returns a token (they have to acc

Lists the projects Frapea knows on this machine: id, name, lastOpenedAt, and for a project stored in a folder on disk its folder (the directory's name — files you write into its media/ subfolder join the pool by themselves). Call first to find the projectId every other tool needs. A project the browser has no permission for will surface PERMISSION_REQUIRED when used — relay the returned instru

Reads a project's timeline structure: timelines (id, name, fps, resolution) with tracks and clips. THE USER CAN COPY A CLIP'S ID from the editor's right-click menu, so a bare UUID in their message names exactly one clip — call this with NO timelineId to search every timeline and match clip.id, rather than guessing from a name. Clips carry id, name, mediaRef, kind, startFrame, endFrame (exclusive

Lists the project's media library: mediaRef (the id clips use), name, kind (video/audio/image), durationSeconds, resolution, and sceneSamples — timestamps (seconds) where the visual indexer detected distinct moments. sceneSamples is a ready-made shot map: inspect or cut at those times first. Each asset also carries visualIndex and transcript objects: {phase: 'ready'|'pending'|'queued'|'running'|'f

Returns the word-level speech transcript of one media asset: language and words [{text, startSec, endSec}]. Only assets the user has transcribed have one — NOT_FOUND means ask the user to run Transcribe on the clip in Frapea. Use the timestamps to align cuts with what is being said.

Creates a MOTION COMPOSITION — an animated graphic (infographic, title, promo end-card, chart…) written as a React TSX component. Read the 'motion' skill (read_skill {topic:'motion'}) for the exact API surface, available fonts/icons and golden examples before writing one. files maps file names to TSX source; the entry must export default the component. schema declares the editable props (type st

Updates a motion composition's TSX files and/or manifest (name, duration, schema…). Same compile-and-test gate as create; files given here MERGE over the existing set. Every clip playing the composition re-renders. preview:true returns one large frame of the result with the reply.

Returns a motion composition's manifest and full TSX sources.

Lists the project's motion compositions: id, mediaRef (for add_clips), name, size, fps, duration and the editable props schema.

Creates a new timeline in the project and returns its id. Set fps, width and height for the target format (e.g. 1080×1920 @30 for a vertical short). The new timeline starts with one video and one audio track; spare tracks appear automatically as clips land.

Places media segments on a timeline. Each clip: mediaRef (from get_media, 'timeline:<id>' to NEST another timeline as a clip, 'solid:#rrggbb' , 'motion:<id>' for a MOTION composition (create_motion_composition) for a generated solid-colour matte, 'adjustment:' for an adjustment clip — no picture of its own, its effects/masks/opacity grade everything below it — or 'text:' for a title, restyled via

Blades clips at a timeline frame. Splits every listed clip (and its linked partner) into two independent clips at atFrame. Frames are in the target timeline's fps. Use with get_timeline to find clip ids first.

Deletes clips (lift — leaves a gap). Linked partners are NOT removed automatically; pass both ids of a pair to delete it whole. To close the gap too, use ripple_delete_ranges instead.

Extracts [fromFrame, toFrame) on one track and shifts everything after it left to close the gap (sync-locked tracks follow). The go-to tool for tightening a cut or removing a bad take.

Adjusts a clip. Only the provided fields change. Mix: volume (0–2, 1 = unity), fadeInFrames / fadeOutFrames (gain or opacity ramps at the edges). Look: opacity (0–1), blend (normal | multiply | screen | overlay | darken | lighten | color-dodge | color-burn | hard-light | soft-light | difference | exclusion | add), transform, crop and speed. transform.fit picks how the picture meets the frame befor

Generates animated captions from a spoken clip's transcript (the same generator as Frapea's UI): transcript words group into caption text clips over the clip's span, word-timed so the animation follows speech. One undo, and they share a captionGroupId — restyle them all via set_clip_properties with text.wholeCaptionGroup. Needs a transcript (get_transcript tells you). Returns the created clip ids.

Edits a clip's effect stack (ordered, per-effect enable). action: 'add' (type; returns the new effect's id) | 'remove' (effectId) | 'move' (effectId + toIndex — the order IS the render order) | 'toggle' (effectId + enabled) | 'set' (effectId + params patch, clamped to the effect's ranges) | 'curve' (effectId + curve + points). Types: 'colorBasic' (Lumetri Basic Correction-compatible: temperature/t

Transitions on a track's cuts OR lone clip edges (a free head/tail takes a single-sided fade from/to nothing; its alignment is forced). action: 'add' (trackId + atFrame = the cut where one clip ends and the next starts, + type; optional durationFrames (default 30, clamped to the clips' source handles), alignment centered|start|end, params) | 'remove' (transitionId) | 'update' (transitionId + any o

Track operations on a timeline. action: 'mute' | 'unmute' | 'solo' | 'unsolo' (audio only; any solo silences non-solo tracks) | 'hide' | 'show' | 'rename' (needs name) | 'duck' | 'unduck' (audio only: dip this track under speech detected on the other audio tracks — transcript word timings when available, energy VAD otherwise) | 'merge' (needs intoTrackId: moves every clip of trackId onto another t

MULTICAM angle switch. The angles are ordinary video tracks stacked over each other (sync them beforehand — clips of the same take on V1..Vn); this razors the whole angle stack at atFrame and keeps only chosenTrackId live from there to the next cut — the other angles' clips are DISABLED, not deleted, so every switch stays re-decidable (cut again with a different angle to change your mind). Lin

Moves clips to new positions (linked partners follow automatically). Each move: clipId, toStartFrame, optional toTrackId (same-kind track). Overwrite semantics — landing on another clip trims it like a drag-drop.

Sets which timeline the project opens on (and what the user sees if the editor is open). Purely a convenience — every tool here takes an explicit timelineId regardless.

Updates a timeline's fps / width / height (clips keep their timing; content re-fits) and/or renames it. Only provided fields change.

Semantic search over the project's media. Visual scope matches what is IN the picture (describe a shot: 'aerial city at night'); spoken scope matches transcribed speech (exact words, ranked first, with a snippet). Hits: {mediaRef, timeSec (best moment), fromSec, toSec, score, scope}. Requires the user to have downloaded the picture analyzer — otherwise PERMISSION_REQUIRED tells you what to relay.

Text-based editing: cuts the given transcript words OUT of a clip as ripple deletes (everything after each cut shifts left). wordIndices are positions in get_transcript's words array for the clip's media. Contiguous indices merge into single cuts. The go-to tool for removing filler words or tightening an interview.

Cuts silent gaps inside a clip: any pause between transcribed words longer than minGapSec becomes a ripple delete (a small margin is kept so speech never clips). Typical minGapSec: 0.6 tight, 1.0 balanced, 1.5 loose.

Reverts the most recent edit THIS agent session made to the project (one step per call; repeat to go further). Cannot revert other tabs' or the user's edits.

Looks INSIDE a source asset. Returns ONE contact sheet — every requested moment as a labelled cell in a single grid image — plus a per-cell fingerprint. Pass atSec (max 12 timestamps, seconds); combine with get_media's sceneSamples for an instant storyboard of the whole file. Shows the RAW source; use inspect_timeline for the composed cut. START WITH pixels:false WHEN YOU ARE ONLY CHECKING FOR EMP

WATCHES the cut. Composites every video layer at each requested frame and returns ONE contact sheet — the frames as labelled cells of a single grid image — plus, per cell, the visibleClipIds that contributed pixels and a fingerprint. Pass frames (timeline frame numbers, max 12). Use after every edit: this is the only tool that shows what actually PLAYS, as opposed to what get_timeline says is arra

What has gone WRONG in the user's editor — renders that failed or stopped, footage that would not decode, chunks that could not be prepared for playback, exports that failed — each with WHERE (the timeline and frames, the source and its own frames, the footage and frame the engine could not decode) and the reason in the engine's own words. You also hear about new problems for free: every other too

Prepare a BUG REPORT for the user: it opens in Frapea (Problems → Create bug report) for them to read and save. The report itself is NOT returned to you — it would leave the user's machine before they have seen it. You get a summary: open problems, media counts, and how many of the user's own words remain in composition code. It contains versions, problems with engine details, the project's struct

RENDER a timeline the way an export would and report what does not work — call it before you call any timeline done. inspect_timeline shows a few frames through the preview path, which quietly substitutes a nearby picture where a frame cannot be rendered; this renders every motion segment the timeline reads (through every nested timeline) exactly, then composites every frame with every layer (foot

Ripple-inserts media segments: everything at/after atFrame shifts right to make room (clips under the cut split). Same clip shape as add_clips. Use to splice a shot INTO an existing sequence without overwriting.

Pool file operations. action: 'rename' renames the real file on disk (needs newName; clips referencing the old name go offline). 'delete' UNLINKS the file from the media pool — the real file on disk is NOT touched; clips using it go offline until it is added again.

Returns Frapea's agent guide: editing conventions, tool workflow tips, the current feature surface, and the CREATIVE MANDATE — how far to run with a terse brief (source stock footage, sounds, voiceover, motion graphics and deliver a finished video vs. when to hand control back to the user). Read once at the start of an editing session. MOTION topics: 'motion' is the API surface (imports, fonts, pr

Waits (up to ~45 s per call) for the user to resolve a pending Frapea prompt — e.g. the folder-permission dialog another tool just opened. The user cannot see tool calls: BEFORE waiting, always say in your visible reply what to click in the Frapea tab, or they will never know they must act. Returns {status: 'granted' | 'denied' | 'pending'}. On 'pending', repeat the instruction and call again; on

Navigates the user's Frapea tab to a project so they can WATCH the edit live. Not required for editing — every tool works headlessly; use this for show-your-work moments.

Navigates the user's Frapea tab back to the project manager and releases this session's headless runtime for the project.

Creates a project. By default it is created in the browser's own storage, which needs no permission and no click: the project id comes back immediately and you can start working. The user can turn it into a real folder on their disk whenever they want (Cmd/Ctrl+S, or File → Save to a Folder) without losing anything. Pass storage:'folder' only when the user asked for a folder up front — that needs

Asks the user to attach a folder of THEIR OWN source footage to the project — opens a dialog in Frapea with a 'Connect folder' button. Only a human can do this (browser security gesture): tell the user IN YOUR REPLY to click it, then call await_user_action with the returned actionId; on 'granted', get_media will list the folder's files. Use when get_media comes back empty and the user has footage

Adjusts one edge of a clip (linked A/V partners follow). edge: 'start' trims/extends the in-point, 'end' the out-point. deltaFrames > 0 moves the edge right, < 0 left — e.g. edge 'end', delta -12 shortens the clip by 12 frames. Extending is limited by the source material.

How far the project's media analysis has got. Analysis runs BY ITSELF whenever media is connected — never start it. Returns percent (0-100) — which reaching 100 only means nothing is OUTSTANDING, so always read failed beside it and call retry_analysis on anything that failed — done/total/pending item counts, runningItem {mediaRef, kind, progress}, etaSeconds (null until something has finished),

Asks the user to enable Frapea's on-device AI analyzers (picture search, speech). Opens a dialog in every Frapea tab and returns an actionId — tell the user IN YOUR REPLY to confirm it, then call await_user_action and poll get_analysis_status until models are enabled. Call this when get_media reports 'needs-models'.

Indexes the project's pictures for search_media. Usually not needed: indexing is automatic and this only nudges the queue to re-check now. When the user switched automatic indexing off, this asks for every video and image to be indexed. Returns the same payload as get_analysis_status.

Transcribes one asset even if automatic transcription is switched off. Speech transcripts otherwise appear on their own. Returns the project's analysis status; poll get_analysis_status, then read get_transcript.

Status of a background job started by a job-returning tool (generate_voiceover, verify_timeline): {state: queued|running|done|failed, progress: 0-1, detail, ...result fields such as mediaRef when done; verify_timeline puts its report in result}. Poll every few seconds while state is 'queued' or 'running' (queued = waiting for the analysis master tab, which loads the models once for the whole bro

The text-to-speech providers Frapea can generate voiceovers with. Returns providers[]: the FREE in-browser models straight from the TTS registry ({id, label, languages, voices: [{id, label, language, gender, grade}], modelAssets, state: {phase: needs-download|downloading|ready|error}}), plus the PREMIUM cloud provider flagged premium: true ({id: 'elevenlabs', label, premium, voices: [{id, label}],

Generates an AI voiceover from a script, entirely on-device. The WAV lands in the project's media library as a normal audio asset (with waveform and analysis), the script is stored as asset metadata, and a script-corrected word-level transcript is written so captions work immediately. CALL THIS BEFORE YOU CUT THE PICTURE. A script does not tell you how long it takes to SAY, so a narrated edit asse

Searches the Pexels stock library (photos or videos) with the user's connected API key. Returns items with id, dimensions, duration (videos), author, thumbnail url, available video qualities, and a downloaded flag telling whether the asset is already in the project's media pool. If no key is connected the tool errors — TELL THE USER to open Library → Generators → Stock Library and connect their

Downloads one Pexels asset into the project's media pool as a virtual file at the Library root (name pexels-<id>.jpg|.mp4). Asynchronous: the first call accepts the download and returns its state; CALL AGAIN with the same arguments to poll — state becomes 'done' with the asset's mediaRef, ready for add_clips. maxHeight picks the best video rendition not exceeding it (default: the best available)

Searches the Freesound library (SFX, ambience, foley) with the user's connected API key. Every item carries what you need to JUDGE the sound without hearing it: the uploader's full description, tags, duration, community rating and download count, format/samplerate, and — when analyzed — AudioCommons descriptors (acAnalysis: ac_loudness LUFS, ac_dynamic_range, ac_tempo, ac_tonality, ac_single_event

Downloads one Freesound sound (its HQ MP3 preview, ~128 kbps — plenty for SFX/ambience) into the project's media pool as a virtual file at the Library root (name freesound-<id>.mp3). Asynchronous: the first call accepts the download and returns its state; CALL AGAIN with the same arguments to poll — state becomes 'done' with the asset's mediaRef, ready for add_clips onto an audio track. Three fi

frapea's BUILT-IN sound-effects pack — synthesized, licence-free, no API key, no download wait. Reach for this FIRST; use search_sounds only for something the pack does not cover (ambience, foley, a specific real-world object). Call with no ids to get the catalogue: each sound carries what it sounds like AND when to use it. Call with ids to copy them into the project's media pool as `sfx-<id>.

Full control of the background work queue. action 'list' returns every queued/running item across all projects (analyses, proxies, beats) plus the visible task rows (downloads, voiceover jobs, failures) with a cancellable flag. action 'cancel' stops ONE kind of work for ONE asset — queued or already running (a running visual index stops at the next sample and keeps its checkpoint). The asset then

Runs ONE analysis of ONE asset again — picture indexing or speech transcription — clearing whatever failure was recorded for it. Use when get_media shows phase 'failed' and the error looks worth another go, or when you want a fresh result for a file that changed meaning. Returns the project's analysis status.

Animates one clip property. property: opacity | volume | positionX | positionY | scaleX | scaleY | rotationDeg | pitch | yaw | anchorX | anchorY | cropLeft | cropTop | cropRight | cropBottom | cropSoftness. Keyframes are stamped in SOURCE frames (frames into the media, i.e. timelineFrame - startFrame + trimStartFrame), so they survive moves and trims. action 'set' (default) upserts the given keyfr

Arranges clips into a screen layout by writing ordinary transform + crop values (first clipId → first cell). layout: full | side-by-side | top-bottom | pip-top-left | pip-top-right | pip-bottom-left | pip-bottom-right | grid-2x2 | main-sidebar | three-up. mode 'fit' letterboxes each source in its cell, 'cover' fills the cell and crops the overflow (bias 0–1 picks the surviving part; 0.5/0.5 = cent

Finds every FACE in a video clip and stores one independent path per person — position, size and head rotation (nod/turn/tilt) per frame. Queued, not immediate: poll list_face_tracks until state is 'ready'. Re-running on the same clip REPLACES its previous run and keeps the same trackId, so clips already bound stay bound. A person who leaves the shot and returns much later becomes a SECOND face on

Lists face-tracking runs and the people each one found: faceId, name, frame range, how many frames it was actually visible for, and how many gaps it has. Sample data is deliberately not returned. Use this to poll a queued run and to pick a faceId for bind_face.

Joins two or more faces from one run into a single person — for somebody who walked out of the shot and came back. REFUSED when any two of them appear on the same frame, since they cannot then be one person. The earliest face's id and name survive, so existing bindings keep working, and the time between sightings stays a gap for the clip's gap policy to handle.

Makes a clip FOLLOW a tracked face — the way to stick a mask, label or blur onto somebody's head. Movement is relative to where the face was first seen, so the clip keeps the framing it already had and only inherits the motion. Pick what to copy with channels, and what happens while the face is missing with gap. Pass trackId: null to unbind.

THE MEDIA POOL'S SHAPE — bins (the pool's folders) and what sits in them. Use it to tidy a project: group the footage, the voice-over, the music and the graphics instead of leaving eighty files at the root. Bins are VIRTUAL and live in the project, not on disk. Moving an item between bins NEVER touches the file or its mediaRef, so it cannot break a clip's link or make the app ask the user to reloc