# Frapea (remote · app.frapea.com) A video editor in your browser that your AI drives: cuts, captions, multicam, motion titles, export. - Trust score: 68/100 (medium) - Change this week: +5 - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-10-23 > **Recent critical change**: Authorization (2026-10-23). See the changelog below before you install this server. ## Components - remote · `app.frapea.com`: 68/100 (this document), [markdown](https://verifymcp.io/servers/com-frapea-editor/app.md), [page](https://verifymcp.io/servers/com-frapea-editor/app) ## Channel facts - Endpoint: `https://app.frapea.com/mcp` - Transports: `streamable-http` - Auth: `none` - Version: `0.2.0` ## Trust breakdown How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog) Scored 2026-10-23. - **Endpoint Security**: 63/100 - The endpoint's TLS certificate is valid, in date, and uses a strong key. - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (update_motion_composition). - HTTPS is enforced; there's no plaintext access path. - The HSTS (Strict-Transport-Security) header is present. - DNSSEC check failed: this domain isn't protected by DNSSEC. - **Transport & Reachability**: 100/100 - Verified streamable-http transport via a live MCP handshake. - **Schema Quality & AI Usability**: 62/100 - AI-judged instruction clarity (excellent). - Context-footprint check failed: tool/resource definitions use about 18160 tokens (~271/item across 67 items; 67 tools + 0 resources), over budget; trim descriptions and params. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 37/100 - Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses. - **Tool Coverage**: 99/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 98% of tool parameters carry a description. - **Tool Safety**: 100/100 - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured. - All 5 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation. - An AI judge read all 68 captured unit(s) of tool text and found none that tries to manipulate the model reading it. - **Capabilities**: 60/100 - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. ## Install ### How do I install the Frapea MCP server? Frapea is a hosted endpoint at https://app.frapea.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation. ### Claude ```bash claude mcp add --transport http com-frapea-editor 'https://app.frapea.com/mcp' ``` ### Cursor ```json { "mcpServers": { "com-frapea-editor": { "url": "https://app.frapea.com/mcp" } } } ``` ### VS Code ```json { "servers": { "com-frapea-editor": { "type": "http", "url": "https://app.frapea.com/mcp" } } } ``` ### Codex ```toml [mcp_servers.com-frapea-editor] url = "https://app.frapea.com/mcp" ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "com-frapea-editor": { "type": "remote", "url": "https://app.frapea.com/mcp", "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add com-frapea-editor --url 'https://app.frapea.com/mcp' --transport streamable-http ``` ### Hermes ```yaml mcp_servers: com-frapea-editor: url: "https://app.frapea.com/mcp" ``` ### Netclaw ```json { "McpServers": { "com-frapea-editor": { "Transport": "http", "Url": "https://app.frapea.com/mcp" } } } ``` ### Vellum ```bash assistant mcp add com-frapea-editor -t streamable-http -u 'https://app.frapea.com/mcp' ``` ### Other ```json { "mcpServers": { "com-frapea-editor": { "type": "http", "url": "https://app.frapea.com/mcp" } } } ``` The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs. ## Changelog Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims. ### 2026-10-23 (score 68, +2) - [critical regression] Authorization: unverified → fail - [security] The server rewrote its instructions, which are the text every model session reads - [security] Tool “add_sfx” rewrote its description, which is the text the model reads - [security] Tool “await_user_action” rewrote its description, which is the text the model reads - [security] Tool “close_project” rewrote its description, which is the text the model reads - [security] Tool “create_motion_composition” rewrote its description, which is the text the model reads - [security] Tool “generate_voiceover” rewrote its description, which is the text the model reads - [security] Tool “get_analysis_status” rewrote its description, which is the text the model reads - [security] Tool “get_problems” rewrote its description, which is the text the model reads - [security] Tool “get_projects” rewrote its description, which is the text the model reads - [security] Tool “inspect_timeline” rewrote its description, which is the text the model reads - [security] Tool “open_project” rewrote its description, which is the text the model reads - [security] Tool “read_skill” rewrote its description, which is the text the model reads - [security] Tool “retry_analysis” rewrote its description, which is the text the model reads - [security] Tool “search_sounds” rewrote its description, which is the text the model reads - [security] Tool “search_stock_media” rewrote its description, which is the text the model reads - [security] Tool “set_active_timeline” rewrote its description, which is the text the model reads - [security] Tool “verify_timeline” rewrote its description, which is the text the model reads - [security] Tool “add_clips” is now declared destructive - [security] Tool “apply_layout” is now declared destructive - [security] Tool “bind_face” is now declared destructive - [security] Tool “close_project” is now declared destructive - [security] Tool “manage_effects” is now declared destructive - [security] Tool “manage_queue” is now declared destructive - [security] Tool “manage_tracks” is now declared destructive - [security] Tool “manage_transitions” is now declared destructive - [security] Tool “merge_faces” is now declared destructive - [security] Tool “move_clips” is now declared destructive - [security] Tool “open_project” is now declared destructive - [security] Tool “organize_media” is now declared destructive - [security] Tool “organize_pool” is now declared destructive - [security] Tool “remove_clips” is now declared destructive - [security] Tool “remove_silence” is now declared destructive - [security] Tool “remove_words” is now declared destructive - [security] Tool “retry_analysis” is now declared destructive - [security] Tool “ripple_delete_ranges” is now declared destructive - [security] Tool “set_clip_properties” is now declared destructive - [security] Tool “set_keyframes” is now declared destructive - [security] Tool “set_project_settings” is now declared destructive - [security] Tool “track_faces” is now declared destructive - [security] Tool “trim_clips” is now declared destructive - [security] Tool “undo” is now declared destructive - [security] Tool “update_motion_composition” is now declared destructive - [functional] Destructive annotations: All 5 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation. - [functional] New tool “add_sample_media” - [functional] New tool “close_timeline” - [functional] New tool “open_timeline” - [cosmetic] Tool “add_clips” changed its title: Add clips - [cosmetic] Tool “add_sfx” changed its title: Add built-in sound effects - [cosmetic] Tool “apply_layout” changed its title: Apply layout - [cosmetic] Tool “await_user_action” changed its title: Wait for the user - [cosmetic] Tool “bind_face” changed its title: Bind clip to a face - [cosmetic] Tool “close_project” changed its title: Close project - [cosmetic] Tool “connect” changed its title: Connect to Frapea - [cosmetic] Tool “connect_media_folder” changed its title: Ask to connect a media folder - [cosmetic] Tool “create_motion_composition” changed its title: Create motion composition - [cosmetic] Tool “create_timeline” changed its title: Create timeline - [cosmetic] Tool “cut_to_angle” changed its title: Cut to camera angle - [cosmetic] Tool “download_sound” changed its title: Download Freesound sound - [cosmetic] Tool “download_stock_media” changed its title: Download Pexels stock - [cosmetic] Tool “duplicate_timeline” changed its title: Duplicate timeline - [cosmetic] Tool “generate_captions” changed its title: Generate captions - [cosmetic] Tool “generate_voiceover” changed its title: Generate voiceover - [cosmetic] Tool “get_analysis_status” changed its title: Get analysis status - [cosmetic] Tool “get_bug_report” changed its title: Prepare bug report - [cosmetic] Tool “get_job_status” changed its title: Get job status - [cosmetic] Tool “get_media” changed its title: List media - [cosmetic] Tool “get_motion_composition” changed its title: Get motion composition - [cosmetic] Tool “get_problems” changed its title: Get problems - [cosmetic] Tool “get_projects” changed its title: List projects - [cosmetic] Tool “get_timeline” changed its title: Get timeline - [cosmetic] Tool “get_transcript” changed its title: Get transcript - [cosmetic] Tool “insert_clips” changed its title: Insert clips - [cosmetic] Tool “inspect_media” changed its title: Inspect source frames - [cosmetic] Tool “inspect_timeline” changed its title: Inspect timeline frames - [cosmetic] Tool “list_face_tracks” changed its title: List face tracks - [cosmetic] Tool “list_motion_compositions” changed its title: List motion compositions - [cosmetic] Tool “list_voiceover_models” changed its title: List voiceover models - [cosmetic] Tool “manage_effects” changed its title: Manage effects - [cosmetic] Tool “manage_queue” changed its title: Manage background queue - [cosmetic] Tool “manage_tracks” changed its title: Manage tracks - [cosmetic] Tool “manage_transitions” changed its title: Manage transitions - [cosmetic] Tool “measure_loudness” changed its title: Measure loudness - [cosmetic] Tool “merge_faces” changed its title: Merge faces - [cosmetic] Tool “move_clips” changed its title: Move clips - [cosmetic] Tool “new_project” changed its title: New project - [cosmetic] Tool “open_project” changed its title: Open project in the editor - [cosmetic] Tool “organize_media” changed its title: Rename or unlink media - [cosmetic] Tool “organize_pool” changed its title: Organize media bins - [cosmetic] Tool “read_skill” changed its title: Read editing guide - [cosmetic] Tool “remove_clips” changed its title: Remove clips - [cosmetic] Tool “remove_silence” changed its title: Remove silences - [cosmetic] Tool “remove_words” changed its title: Remove spoken words - [cosmetic] Tool “request_ai_models” changed its title: Ask to enable AI models - [cosmetic] Tool “retry_analysis” changed its title: Retry analysis - [cosmetic] Tool “ripple_delete_ranges” changed its title: Ripple delete ranges - [cosmetic] Tool “search_media” changed its title: Search project media - [cosmetic] Tool “search_sounds” changed its title: Search Freesound - [cosmetic] Tool “search_stock_media” changed its title: Search Pexels stock - [cosmetic] Tool “set_active_timeline” changed its title: Set active timeline - [cosmetic] Tool “set_clip_properties” changed its title: Set clip properties - [cosmetic] Tool “set_keyframes” changed its title: Set keyframes - [cosmetic] Tool “set_project_settings” changed its title: Set timeline settings - [cosmetic] Tool “split_clips” changed its title: Split clips - [cosmetic] Tool “start_transcription” changed its title: Start transcription - [cosmetic] Tool “start_visual_indexing” changed its title: Start picture indexing - [cosmetic] Tool “track_faces” changed its title: Track faces - [cosmetic] Tool “trim_clips” changed its title: Trim clips - [cosmetic] Tool “undo” changed its title: Undo - [cosmetic] Tool “update_motion_composition” changed its title: Update motion composition - [cosmetic] Tool “verify_timeline” changed its title: Verify timeline ### 2026-10-22 (score 66, +1) No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-10-20 (score 65, +1) No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-10-19 (score 64, 0) - [cosmetic] “generate_voiceover” reworded the description of “modelId” ### 2026-10-18 (score 64, +1) No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-10-16 (score 63, +1) No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-10-15 (score 62, 0) - [security] The server rewrote its instructions, which are the text every model session reads - [security] Tool “get_job_status” rewrote its description, which is the text the model reads - [security] Tool “get_media” rewrote its description, which is the text the model reads - [security] Tool “manage_effects” rewrote its description, which is the text the model reads - [functional] New tool “duplicate_timeline” - [functional] New tool “measure_loudness” - [cosmetic] “get_media” added an optional parameter “mediaRef” - [cosmetic] “set_clip_properties” added an optional parameter “motionBlur” ### 2026-10-13 (score 62, +1) - [functional improvement] Stability: unverified → 0.03 ## MCP tools (67) ### `connect` (~185 tokens) Connect to Frapea 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 accept it in their browser first). Either way you end up with a session token to pass on every later call. Codes are single-use and expire in ten minutes; a token lasts until the user disconnects. Input parameters: - `code` (string): The 8-character code — from the user's screen, or from the link this tool gave you. Omit it to get a link to send them. ### `get_projects` (~253 tokens) List projects 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 instruction to the user, then retry. ALSO RETURNS `providers` — Pexels (stock video/photos), Freesound (music, ambience, SFX) and ElevenLabs (voiceover), each 'connected' | 'checking' | 'missing' | 'invalid'. These are the user's OWN API keys and they cannot be set from here. When any is not usable, `providersAdvice` is present: a short note for the user saying which and where they connect them (only the user can add a key). When everything is connected it is absent. A call that fails with PERMISSION_REQUIRED carries its own instruction for the user. Input parameters: - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `get_timeline` (~221 tokens) Get timeline 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), trimStartFrame and linkGroupId (linked A/V pairs share it), plus `look` (opacity, blend, transform, crop, keyframes) whenever any of it differs from the defaults — an untouched clip has no `look` key. Omit timelineId to get every timeline; frames are in that timeline's fps. Input parameters: - `projectId` (string, required): Project id from get_projects. - `timelineId` (string): Optional single timeline to read. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `get_media` (~396 tokens) List media 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'|'failed'|'no-audio'|'disabled', error, attempts, sealed}. Analysis starts by itself and retries a failure a few times before sealing it. If a phase is 'failed', read `error` and decide: call retry_analysis to run just that one analysis again, or leave it. If 'disabled', call request_ai_models. Video and audio assets also carry beats: {phase: 'ready'|'pending'|'failed'|'none', bpm, confidence}. These come from an ONSET detector (spectral flux): every energy rise — drum hits, plucks, syllables — not bars or downbeats. bpm is the tempo of those onsets, or null when there is no steady pulse (confidence 0–1 below the detector's 0.3, or too few onsets) — speech has onsets and no bpm. 'none' = no audio to analyze. Pass mediaRef to get ONE asset with beats.onsetsSec (source seconds, the first 2000; truncated + onsetCount say when there are more) — map them through the clip's trim and speed yourself. Input parameters: - `mediaRef` (string): Optional: return only this asset, as {asset}, with its onset times. Omit to list every asset (no onset times). - `projectId` (string, required): Project id from get_projects. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `get_transcript` (~126 tokens) Get transcript 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. Input parameters: - `mediaRef` (string, required): Asset reference from get_media. - `projectId` (string, required): Project id from get_projects. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `create_motion_composition` (~511 tokens) Create motion composition 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 string|number|color|boolean|select|mediaRef + default) — they become Inspector controls the user can tweak, so parameterize colors, copy and media slots. The composition is compiled and test-rendered BEFORE saving; on failure the error returns verbatim — fix the code and retry. Returns the mediaRef to place with add_clips. Creative guidance is in read_skill {topic:'motion'}. With UI-like parts (buttons, pills, progress bars, cards), write them in their own file with a partsBoard prop (default false) and look at the board first: preview:true, previewProps:{partsBoard:true} returns one large frame with the reply. Input parameters: - `durationInFrames` (number): Length in frames (default 150). - `entry` (string): Entry file (default composition.tsx); must export default. - `files` (object, required): File name → TSX source. Relative imports between them work. - `fps` (number): Composition fps (default 30). - `height` (number): Composition height px (default 1080). - `name` (string, required): Display name, e.g. 'Pink promo end card'. - `preview` (boolean): Return one large frame (≤1560 px) with the reply. Media is not loaded in a preview: media slots draw empty and the reply says how many. - `previewFrame` (number): Frame to preview (default 0). - `previewProps` (object): Merged over the schema defaults for the preview picture only, e.g. {partsBoard:true}. Nothing saved changes. - `projectId` (string, required): Project id from get_projects. - `schema` (object): Editable props: {key: {type, default, label?, min?, max?, options?, multiline?}}. type mediaRef makes a media-pool slot. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. - `width` (number): Composition width px (default 1920). ### `update_motion_composition` (~266 tokens) Update motion composition 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. Input parameters: - `compositionId` (string, required): From create/list_motion_compositions. - `durationInFrames` (number) - `files` (object): File name → TSX source (merged). - `fps` (number) - `height` (number) - `name` (string) - `preview` (boolean): Return one large frame (≤1560 px) with the reply. Media is not loaded in a preview: media slots draw empty and the reply says how many. - `previewFrame` (number): Frame to preview (default 0). - `previewProps` (object): Merged over the schema defaults for the preview picture only, e.g. {partsBoard:true}. Nothing saved changes. - `projectId` (string, required): Project id from get_projects. - `schema` (object) - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. - `width` (number) ### `get_motion_composition` (~72 tokens) Get motion composition Returns a motion composition's manifest and full TSX sources. Input parameters: - `compositionId` (string, required): Composition id. - `projectId` (string, required): Project id from get_projects. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `list_motion_compositions` (~79 tokens) List motion compositions Lists the project's motion compositions: id, mediaRef (for add_clips), name, size, fps, duration and the editable props schema. Input parameters: - `projectId` (string, required): Project id from get_projects. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `create_timeline` (~172 tokens) Create timeline 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. Input parameters: - `fps` (number): Optional frames per second (default 30). - `height` (number): Optional height in px (default 1080). - `name` (string, required): Display name, e.g. 'TikTok short'. - `projectId` (string, required): Project id from get_projects. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. - `width` (number): Optional width in px (default 1920). ### `add_clips` (~342 tokens) Add clips Places media segments on a timeline. Each clip: mediaRef (from get_media, 'timeline:' to NEST another timeline as a clip, 'solid:#rrggbb' , 'motion:' 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 set_clip_properties' `text`), atFrame (timeline position), sourceInSec/sourceOutSec (the segment of the source to use — align these with transcript words or sceneSamples), and optional trackId (from get_timeline) to target a specific same-kind track — without it clips land on V1/A1 with overwrite semantics. A spare empty track always exists above the highest used one, so V2/A2 is available before anything sits on it. Video sources with audio get a linked audio clip automatically (on the matching A track: V2 ⇒ A2). Returns the created clip ids in order. Frames are in the target timeline's fps. Input parameters: - `clips` (array, required): [{mediaRef, atFrame, sourceInSec, sourceOutSec, trackId?}] — segments in playback order; trackId targets a specific track (default V1/A1). - `projectId` (string, required): Project id from get_projects. - `timelineId` (string, required): Target timeline id from get_timeline. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `split_clips` (~139 tokens) Split clips 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. Input parameters: - `atFrame` (number, required): Timeline frame to cut at (must lie inside each clip). - `clipIds` (array, required): Clip ids to split. - `projectId` (string, required): Project id from get_projects. - `timelineId` (string, required): Timeline containing the clips. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `remove_clips` (~112 tokens) Remove clips 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. Input parameters: - `clipIds` (array, required): Clip ids to delete. - `projectId` (string, required): Project id from get_projects. - `timelineId` (string, required): Timeline containing the clips. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `ripple_delete_ranges` (~140 tokens) Ripple delete ranges 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. Input parameters: - `fromFrame` (number, required): Range start (inclusive). - `projectId` (string, required): Project id from get_projects. - `timelineId` (string, required): Target timeline. - `toFrame` (number, required): Range end (exclusive). - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. - `trackId` (string, required): Track id from get_timeline. ### `set_clip_properties` (~1709 tokens) Set clip properties 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 before scaling: contain (letterbox, default) | cover (fill + crop overflow) | fill (stretch, ignores aspect). Identity = contain fit; position is offset from centre in timeline pixels (y down), scale multiplies the fitted size, rotationDeg is clockwise about the anchor (a fraction of the cropped picture, 0.5/0.5 = centre). Crop takes fractions off each edge of the source. Retiming: `speed` (constant rate/direction) and `speedKeyframes` (source-anchored rate curve; reflows length). Shape masks: `masks` (full-list replace). `disabled` parks a clip (it stays but neither renders nor sounds — DaVinci's D). `text` restyles text clips (mediaRef 'text:'). `motion` customizes MOTION clips (mediaRef 'motion:') per clip. Input parameters: - `blend` (string): Optional blend mode (see description). - `bypass` (object): Optional section switches, true = section OFF (its values are kept but not applied) — the inspector's per-section toggles. - `clipId` (string, required): Clip to modify. - `crop` (object): Optional partial crop, fractions 0–1 of the SOURCE off each edge (the inspector shows source pixels). Crop is a window: it cuts pixels away without moving or re-fitting the picture; edges may meet (t… - `cropRetain` (boolean): Optional. True = Resolve's 'Retain Image Position': the crop window stays fixed in the frame while transforms move the picture underneath it. - `cropSoftness` (number): Optional crop-edge feather, fraction of the source width 0–0.5 (the inspector shows source pixels). Keyframable as 'cropSoftness'. - `denoise` (object): AI voice denoise (dry/wet). Setting it (or enabling the section) queues the cached background render for the clip's source file. - `disabled` (boolean): Optional. True disables the clip (and its A/V link partners): it stays on the timeline but neither renders nor sounds. False re-enables. The multicam angle switch is built on this. - `dynamicZoom` (object): Optional Ken Burns move (Resolve's Dynamic Zoom): animates the framing from `start` to `end` over the clip's WHOLE duration (retimes when the clip is trimmed). Rects: centre x/y as picture fractions… - `fadeInFrames` (number): Optional fade-in length in frames. - `fadeOutFrames` (number): Optional fade-out length in frames. - `lensDistortion` (number): Optional Lens Correction Distortion, -1–1. Positive straightens wide-angle barrel distortion, negative adds it. 0 = none. - `masks` (array): Optional shape masks, FULL-LIST replace (empty array removes all). Masks UNION (Resolve's additive Power Windows); `invert` flips one mask's coverage. Geometry in fractions of the SOURCE picture, cen… - `motion` (object): Optional MOTION clip customization (clips with mediaRef 'motion:'). props: partial patch over the composition's schema-declared props ({key: value}; a key set to null resets it to the composition… - `motionBlur` (object): Optional SHUTTER MOTION BLUR from the clip's own movement: each frame is the average of `samples` sub-frame renders spread over the open shutter, each at the position/scale/rotation (keyframes, dynam… - `opacity` (number): Optional static opacity 0–1. - `projectId` (string, required): Project id from get_projects. - `solidColor` (string): Optional, solid-colour matte clips only: recolour the matte (#rrggbb). Mattes are created by add_clips/insert_clips with mediaRef 'solid:#rrggbb'. - `speed` (object): Optional retiming (Resolve's Speed Change). rate 1 = 100 % (0.01–50); direction forward | reverse | freeze; freezeFrame = held source frame (offset from trim-in) while frozen; pitchCorrection keeps t… - `speedKeyframes` (array): Optional source-anchored speed keyframes (forward-direction clips only): [{atSourceFrame, rate}], rate 1 = 100 %. Rate is CONSTANT between points (held outside). Present, it replaces `speed.rate` AND… - `speedRipple` (boolean): Ripple Timeline for this speed edit (see `speed`). - `stabilization` (object): Optional stabilization knobs (Resolve's Stabilization). The expensive motion tracking is a per-media analysis — run it with the stabilizer; these values post-process its cached path instantly. mode p… - `text` (object): Optional TEXT clip restyle (clips with mediaRef 'text:'; create them with add_clips). Partial patch: content ( breaks lines), fontFamily (Inter | DM Sans | Space Grotesk | Bebas Neue | Playfair Disp… - `timelineId` (string, required): Timeline containing the clip. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. - `transform` (object): Optional partial transform; provided keys replace, others stay. - `volume` (number): Optional new volume (0–2). ### `generate_captions` (~398 tokens) Generate captions 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. PLACEMENT: they JOIN the existing caption track whenever they fit in its gaps, and only open a new one when they would overlap (a second language, a second layer). So captioning four narration segments in four calls leaves ONE caption track, not four — no tidying needed afterwards for this. Call manage_tracks {action:'tidy'} at the end of the build for the empty tracks left by everything else. They join the LOWEST caption track, so a picture layer you add ABOVE it after an earlier pass will cover them — captions render behind b-roll rather than looking wrong, which is the hardest kind of mistake to notice. Move the whole lane with manage_tracks {action:'merge'} if you want the captions on top. Input parameters: - `censorProfanity` (boolean): Star out profane words. - `clipId` (string, required): The spoken clip to caption. - `maxWordsPerCaption` (number): Words per caption before a new one starts (default 4). - `position` (string): bottom (default) | top. - `preset` (string): Style preset: clean (default) | boldPop | karaoke | highlight | minimal | editorial. - `projectId` (string, required): Project id from get_projects. - `textCase` (string): original (default) | upper | lower. - `timelineId` (string, required): Timeline containing the spoken clip. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `manage_effects` (~627 tokens) Manage effects 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/tint -100..100, exposure -5..5 stops, contrast/highlights/shadows/whites/blacks -100..100, saturation 0..300, vibrance -100..100), 'colorWheels' (Resolve lift/gamma/gain/offset — {group}Master/{group}R/G/B; lift/gamma 0 neutral, gain 1, offset printer points 25 neutral), 'lut' (.cube from the project library — set `resource`), 'curves' (tone curves), 'hueCurves' (hue-vs-hue/sat/lum). Also 'motionBlur' — NOT the shutter blur: a DIRECTIONAL blur filter (angle 0–360, distance 0–100) that smears every frame the same way whether the clip moves or not (a streak look, a speed effect on footage). For blur that follows the clip's own keyframed movement, use set_clip_properties motionBlur instead. Input parameters: - `action` (string, required): add | remove | move | toggle | set | curve - `clipId` (string, required): Target clip. - `curve` (string): For 'curve': which curve to replace. 'curves' effect: master|r|g|b (tone, identity = [0,0,1,1]); 'hueCurves': hueHue|hueSat|hueLum (x = hue with red at 0, y 0.5 = untouched). - `effectId` (string): Effect instance id (from a previous add or get_timeline). - `enabled` (boolean): For 'toggle'. - `params` (object): For 'set': partial param patch, e.g. { exposure: 1.5 }. - `points` (array): For 'curve': flat control points [x0,y0,x1,y1,…] in the unit square. - `projectId` (string, required): Project id from get_projects. - `resource` (string): For 'set' on resource effects ('lut'): the LUT's library name (a .cube imported into the project). Empty string clears it. - `timelineId` (string, required): Target timeline. - `toIndex` (number): Target position for 'move' (0 = applied first). - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. - `type` (string): Effect type for 'add'. ### `manage_transitions` (~343 tokens) Manage transitions 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 of type/durationFrames/alignment/params). Types: crossDissolve, dipToBlack, dipToWhite, wipe (params.angle deg, params.softness 0-100), slide (params.angle), push (params.angle). Both clips need source material past the cut — a transition that cannot fit is refused; edits that break the cut remove it. Returns {ok, transitionId?}. Input parameters: - `action` (string, required): add | remove | update - `alignment` (string): centered | start | end - `atFrame` (number): The cut frame for 'add'. - `durationFrames` (number) - `params` (object): Type params patch (e.g. { angle: 90 }). - `projectId` (string, required): Project id from get_projects. - `timelineId` (string, required): Target timeline. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. - `trackId` (string, required): Track owning the cut (get_timeline). - `transitionId` (string): Existing transition id. - `type` (string): Transition type. ### `manage_tracks` (~530 tokens) Manage tracks 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 track of the same kind; refuses the WHOLE move if any clip would overlap, or if the source carries transitions) | 'delete' (an EMPTY track; refuses one that holds clips — deleting those is remove_clips, by name) | 'tidy' (NO trackId: drops the empty leftover tracks and renumbers). Track ids come from get_timeline. TIDYING UP, AND WHY ORDER MATTERS. Track counts only ratchet up while you build: a spare appears above whatever you fill, and the video and audio counts are kept EQUAL. That last rule is the one that surprises people — five video tracks force five audio tracks, however empty. So: 1\. 'merge' the tracks that hold clips but need not be separate (captions from several passes, b-roll that never overlaps). This is what actually lowers the count. 2\. 'tidy' once at the end. It settles both sides on one spare above the taller one and reports removedTracks. 'delete' on a single empty track usually reports removedTracks: 0 — the invariant puts it straight back to keep the counts equal. That is not a failure, it is why 'tidy' exists. Neither ever touches a clip, and both keep an empty track you renamed, muted, hid, soloed, unlocked or set to duck. Input parameters: - `action` (string, required): mute | unmute | solo | unsolo | hide | show | rename | duck | unduck | merge | delete | tidy - `intoTrackId` (string): Destination track (merge only) — same kind as trackId. - `name` (string): New name (rename only). - `projectId` (string, required): Project id from get_projects. - `timelineId` (string, required): Target timeline. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. - `trackId` (string): Track to modify. Required for every action except 'tidy'. ### `cut_to_angle` (~277 tokens) Cut to camera angle 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). Linked audio follows the video by default (audioFollowsVideo: false keeps audio untouched — the usual choice when one good mic carries the sound). angleTrackIds defaults to every video track with a clip under the frame. Refused when the chosen track has no clip at the frame. Input parameters: - `angleTrackIds` (array): Optional explicit angle set (video track ids). - `atFrame` (number, required): The switch point (timeline frame). - `audioFollowsVideo` (boolean): Default true: linked audio toggles with its angle. - `chosenTrackId` (string, required): The angle to show from atFrame on. - `projectId` (string, required): Project id from get_projects. - `timelineId` (string, required): Target timeline. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `move_clips` (~123 tokens) Move clips 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. Input parameters: - `moves` (array, required): [{clipId, toStartFrame, toTrackId?}] - `projectId` (string, required): Project id from get_projects. - `timelineId` (string, required): Target timeline. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `set_active_timeline` (~103 tokens) Set active timeline Sets which timeline the project opens on (and what the user sees if the editor is open), opening its tab if it was closed. Purely a convenience — every tool here takes an explicit timelineId regardless. Input parameters: - `projectId` (string, required): Project id from get_projects. - `timelineId` (string, required): Timeline to activate. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `set_project_settings` (~138 tokens) Set timeline settings Updates a timeline's fps / width / height (clips keep their timing; content re-fits) and/or renames it. Only provided fields change. Input parameters: - `fps` (number): Optional new frames per second. - `height` (number): Optional new height in px. - `name` (string): Optional new display name. - `projectId` (string, required): Project id from get_projects. - `timelineId` (string, required): Timeline to update. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. - `width` (number): Optional new width in px. ### `search_media` (~148 tokens) Search project media 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. Input parameters: - `projectId` (string, required): Project id from get_projects. - `query` (string, required): What to look for — plain language. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `remove_words` (~164 tokens) Remove spoken words 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. Input parameters: - `clipId` (string, required): The clip whose speech is being edited. - `projectId` (string, required): Project id from get_projects. - `timelineId` (string, required): Timeline containing the clip. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. - `wordIndices` (array, required): Indices into get_transcript words, e.g. [4,5,6,12]. ### `remove_silence` (~146 tokens) Remove silences 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. Input parameters: - `clipId` (string, required): The clip to tighten. - `minGapSec` (number, required): Minimum pause length to cut (seconds). - `projectId` (string, required): Project id from get_projects. - `timelineId` (string, required): Timeline containing the clip. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `undo` (~81 tokens) Undo 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. Input parameters: - `projectId` (string, required): Project id from get_projects. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `inspect_media` (~300 tokens) Inspect source frames 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 EMPTINESS. The fingerprint answers 'is this black / flat / did it decode' for no image cost — nonBlankRatio near 0 is an empty or black frame, colorRange near 0 is a featureless one. Ask for pixels when you must judge WHAT is in the frame: subject, framing, legibility. Input parameters: - `atSec` (array, required): Timestamps in seconds, max 12. - `cellHeight` (number): Target px height per cell (default 300). Shrunk automatically if the sheet would exceed the response budget — the reply says so when that happens. - `columns` (number): Grid columns (default 3, or one row if ≤3). - `mediaRef` (string, required): Asset from get_media. - `pixels` (boolean): False = fingerprints only, no image (default true). - `projectId` (string, required): Project id from get_projects. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `inspect_timeline` (~350 tokens) Inspect timeline frames 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 it to check an edit: this is the only tool that shows what actually PLAYS, as opposed to what get_timeline says is arranged. SAMPLE THE CUT POINTS AND THE MIDDLE OF EACH SECTION, not only frame 0. An entrance animation that never resolves, a graphic clipped by its own box, an offline clip rendering black — all look perfect in get_timeline and are obvious here. USE pixels:false FOR A CHEAP SWEEP. visibleClipIds plus nonBlankRatio confirms 'the right clip is in every slot and none of them is black' across a dozen positions with no image cost; spend pixels on the few frames where you must judge typography, framing or timing. Input parameters: - `cellHeight` (number): Target px height per cell (default 300). Shrunk automatically if the sheet would exceed the response budget — the reply says so when that happens. - `columns` (number): Grid columns (default 3, or one row if ≤3). - `frames` (array, required): Timeline frame numbers, max 12. - `pixels` (boolean): False = structure + fingerprints only, no image (default true). - `projectId` (string, required): Project id from get_projects. - `timelineId` (string, required): Timeline to render. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `get_problems` (~290 tokens) Get problems 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 tool result carries a `problems` list of what changed since your last call. Call this for the whole history, or after a `moreProblems` count. A problem that is open on a timeline means that timeline does NOT play or export correctly there, whatever inspect_timeline showed: fix the named layer (e.g. update_motion_composition) to fix it. `state` is open | fixed | superseded (the thing it was about was edited and not yet re-rendered — NOT proof it works) | dismissed. Input parameters: - `detail` (boolean): Include the engine's raw diagnostic text per problem (default false — it can be long). - `includeResolved` (boolean): Also list problems that are no longer open (default false). - `projectId` (string): Project id from get_projects. Omit for every project in this browser. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `get_bug_report` (~198 tokens) Prepare bug report 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 structure with names and texts replaced, provider files by public id, the user's own files only as encoding fingerprints, and motion code. timelineIds limits it to those timelines and what they nest. Input parameters: - `projectId` (string, required): Project id from get_projects (must be open in the editor). - `timelineIds` (array): Only these timelines and the timelines they nest (default: all). - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `verify_timeline` (~281 tokens) Verify timeline Renders a timeline the way an export does and reports what fails. 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 (footage decoded), and fails where an export would. Returns {jobId}; poll get_job_status every ~5 s. When done, `result` is {verdict: ok | problems | incomplete, checked, notChecked, segments, chunks, problems: [...same shape as get_problems, with `related` warnings that often name the cause...], stale?, note}. `incomplete` is NOT a pass: something could not be checked. `stale: true` means the timeline was edited while it ran — verify again. Sound is not checked. Needs the project open in the editor tab you are paired with (error PROJECT_NOT_OPEN otherwise). Input parameters: - `cancel` (boolean): Stop the verification of this timeline that is running. - `projectId` (string, required): Project id from get_projects. - `timelineId` (string, required): Timeline to verify (nested timelines inside it are verified too). - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `insert_clips` (~136 tokens) Insert clips 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. Input parameters: - `atFrame` (number, required): Insertion point (timeline frame). - `clips` (array, required): [{mediaRef, sourceInSec, sourceOutSec}] - `projectId` (string, required): Project id from get_projects. - `timelineId` (string, required): Target timeline. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `organize_media` (~148 tokens) Rename or unlink media 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. Input parameters: - `action` (string, required): rename | delete - `mediaRef` (string, required): Asset from get_media. - `newName` (string): New file name incl. extension (rename). - `projectId` (string, required): Project id from get_projects. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `read_skill` (~401 tokens) Read editing guide Returns Frapea's editing documentation for a topic. With no topic: the editing conventions, how the tools fit together and the current feature surface. MOTION topics: 'motion' is the API surface (imports, fonts, props schema, the parts-board-first golden example) and routes to the rest — read before create_motion_composition; 'motion-examples' (two finished pieces that differ in look); 'motion-craft' (anticipation, overshoot, stagger, the tells of machine-made motion — a companion to 'motion'); 'motion-text' (size floors, fitting copy that cannot clip, per-word animation, annotations); 'motion-effects' (grain, duotone, light leaks, blurs, glow); 'motion-transitions' (TransitionSeries, presentations, cut overlays); 'motion-sound' (where sound lives, the built-in SFX pack, placement and levels); 'motion-review' (the same loop as 'review', from a motion job). The CRAFT guides teach how to actually cut: 'core' (rhythm, b-roll, audio hierarchy, restraint — read first), then the format you are making — 'shorts' | 'longform' | 'podcast' | 'tutorial' | 'montage'. Also 'voiceover' (narration in segments, not one block), 'verify' (how to check a cut before export) and 'review' (rounds of critique against rendered frames, for a piece with an audience). Input parameters: - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. - `topic` (string): Optional. Motion: motion | motion-examples | motion-craft | motion-text | motion-effects | motion-transitions | motion-sound | motion-review. Craft: core | shorts | longform | podcast | tutorial | mo… ### `await_user_action` (~154 tokens) Wait for the user 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 dialog waits for the user in the Frapea tab; the tool that opened it returned what they need to click. Returns {status: 'granted' | 'denied' | 'pending'}: 'pending' means they have not acted yet (call again to keep waiting), 'denied' that they declined. Input parameters: - `actionId` (string, required): The actionId a previous tool returned. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `open_project` (~104 tokens) Open project in the editor 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. This reloads the Frapea tab, so an export or render running there stops. Input parameters: - `projectId` (string, required): Project id from get_projects. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `close_project` (~92 tokens) Close project Navigates the user's Frapea tab back to the project manager and releases this session's headless runtime for the project. When the tab shows that project it reloads, so an export or render running there stops. Input parameters: - `projectId` (string, required): Project id from get_projects. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `new_project` (~235 tokens) New 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 a browser security gesture, so it opens a dialog in Frapea with a 'Choose folder' button, returns an actionId, and you must tell the user IN YOUR REPLY to click it, then call await_user_action; on 'granted' the project appears in get_projects. Input parameters: - `name` (string, required): Project name, e.g. from the user's brief. - `storage` (string): Where the project lives. 'browser' (default) needs no user action. 'folder' asks the user to pick a directory on their disk. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `connect_media_folder` (~281 tokens) Ask to connect a media folder 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 somewhere on their disk. NEVER call it for files YOU made or fetched. The project folder's `media/` folder is scanned: any media file placed there joins the pool by itself (within a second, or when the user returns to the tab), with no dialog. `reason` is shown in the dialog word for word — say which footage you need and what you will do with it, so the user knows what to pick. Input parameters: - `projectId` (string, required): Project id from get_projects. - `reason` (string, required): One or two sentences for the dialog, addressed to the user: which folder to pick and why — e.g. 'Pick the folder with your trip clips from Lisbon, so I can cut them into the reel you asked for.' - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `trim_clips` (~172 tokens) Trim clips 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. Input parameters: - `clipId` (string, required): Clip to trim. - `deltaFrames` (number, required): Signed frame delta for that edge. - `edge` (string, required): start | end - `projectId` (string, required): Project id from get_projects. - `timelineId` (string, required): Timeline containing the clip. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `get_analysis_status` (~164 tokens) Get analysis status How far the project's media analysis has got. Analysis runs BY ITSELF whenever media is connected. Returns percent (0-100) — 100 means nothing is OUTSTANDING, not that everything succeeded: `failed` lists items whose analysis failed (retry_analysis re-runs one) — done/total/pending item counts, runningItem {mediaRef, kind, progress}, etaSeconds (null until something has finished), blockedOnModels, and models {visual, speech}. Poll this while you wait; when blockedOnModels is above zero, call request_ai_models. Input parameters: - `projectId` (string, required): Project id from get_projects. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `request_ai_models` (~122 tokens) Ask to enable AI models 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'. Input parameters: - `projectId` (string, required): Project the work belongs to. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `start_visual_indexing` (~106 tokens) Start picture indexing 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. Input parameters: - `projectId` (string, required): Project id from get_projects. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `start_transcription` (~98 tokens) Start transcription 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. Input parameters: - `mediaRef` (string, required): Asset from get_media. - `projectId` (string, required): Project id from get_projects. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `get_job_status` (~179 tokens) Get job status Status of a background job started by a job-returning tool (generate_voiceover, verify_timeline, measure_loudness): {state: queued|running|done|failed|cancelled, progress: 0-1, detail, ...result fields such as mediaRef when done; verify_timeline, measure_loudness 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 browser). For analysis started by start_transcription or start_visual_indexing, poll get_analysis_status instead. Input parameters: - `jobId` (string, required): Id returned by the start_* tool. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `list_voiceover_models` (~342 tokens) List voiceover models 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}], models: [{id, label, creditsPerCharacter, supportsAudioTags, note}]}, voices/models empty until a key is stored). supportsAudioTags tells you whether that model understands inline audio tags like [calm], [laughs], [whispers] as delivery directions (only the v3 family does); on every other model such tags are READ ALOUD, so send those models plain text — each model's `note` restates its rule. Also returns a top-level status object `elevenlabs`: {provider: 'elevenlabs', hasApiKey, credits: {used, limit, remaining} | null, consent: 'ask' | 'always'} — READ IT BEFORE choosing the premium provider, so you know whether a key exists, what the account can afford and whether a consent dialog will be involved. A free provider whose phase is 'needs-download' cannot generate until the user enables it in the Generators panel (Voiceover) — there is no tool to force the download; ask the user. Input parameters: - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `generate_voiceover` (~1021 tokens) Generate voiceover Generates an AI voiceover from a script — on-device with the free models, or in the cloud with ElevenLabs (the user's own key and credits). 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. Narration is best generated before the picture is cut: a script does not tell you how long it takes to SAY, so a narrated edit assembled first is built on guessed cut points that the real audio then breaks — every section, graphic and transition has to be retimed. Generate the narration, read its word timings with get_transcript, then lay picture against those frames. Segments read better than one block (e.g. hook / body / close, or one per section), each laid on the timeline separately. A single long generation comes out FLAT and evenly paced, everything pressed together at one energy; segmenting gives each part its own intent, puts natural air at the joins, and lets you redo one section instead of all of it. Write for the ear: short sentences, one idea each, LINE BREAKS between them — the strongest signal the model has to actually stop. See read_skill {topic:'voiceover'}. Async: returns {jobId, fileName} — fileName is the audio file's final name in the project's media/ folder, decided up front (WAV for local providers, MP3 for ElevenLabs). The job runs on the analysis MASTER tab and its request is persisted on disk: it survives tab closes and browser restarts, and get_job_status answers from disk even in a fresh session. Poll until done; the finished job also carries the asset's mediaRef. Voices/languages come from list_voiceover_models; a local model must be downloaded first (phase 'ready'), otherwise this returns PERMISSION_REQUIRED. PREMIUM (provider 'elevenlabs' — SPENDS THE USER'S CREDITS): check list_voiceover_models' `elevenlabs` status object first. Structured refusals you must handle: NO_API_KEY… Input parameters: - `consentActionId` (string): The actionId from a CONSENT_REQUIRED refusal, after await_user_action returned 'granted'. Good for one job. - `fileName` (string): Optional base name for the audio file written into media/. - `language` (string): Language tag from the provider's manifest (e.g. 'en-us'). Ignored for ElevenLabs — its voices are multilingual. - `modelId` (string): ElevenLabs only: TTS model id from list_voiceover_models (default 'eleven_v3' — expressive, reads [calm]-style audio tags as directions; use 'eleven_multilingual_v2' only when the user asks for v2; t… - `projectId` (string, required): Project id from get_projects. - `provider` (string): TTS provider id from list_voiceover_models (default 'kokoro'; 'elevenlabs' = premium, needs the user's key + consent). - `speed` (number): Speaking rate multiplier (default 1). Local providers accept 0.5–2; ElevenLabs 0.7–1.2. - `text` (string, required): The script to speak (multi-line ok). - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. - `voice` (string): Voice id from the provider's manifest (default: its first voice for the chosen language). - `voiceSettings` (object): ElevenLabs only: voice knobs, each optional. stability, similarityBoost and style are 0–1; speakerBoost is a boolean. ### `search_stock_media` (~289 tokens) Search Pexels stock 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 it errors with PERMISSION_REQUIRED, whose message says where the user connects one (Library → Generators → Stock Library). Results are subject to the Pexels license; keep the author attribution when asked about provenance. Results match the uploader's keywords, not the picture — a search for 'earth from space' also returns the Moon and artists' renders; `thumbnail` shows the actual subject. See read_skill {topic:'verify'}. Input parameters: - `color` (string): Optional, photos only: a Pexels color name. - `kind` (string, required): photos | videos - `orientation` (string): Optional: landscape | portrait | square - `page` (number): 1-based page, 40 items per page. - `projectId` (string, required): Project id from get_projects. - `query` (string): Search phrase; empty = curated/popular feed. - `size` (string): Optional: large | medium | small - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `download_stock_media` (~320 tokens) Download Pexels stock Downloads one Pexels asset into the project's media pool as a virtual file at the Library root (name `pexels-.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). ASK FOR THE WHOLE SHOT LIST AT ONCE — three files stream at a time and the rest wait their turn, so a batch is queued for you, in the order you asked. State 'queued' is normal and needs no action but polling. ONCE DOWNLOADED, CHECK THE MOMENT YOU MEAN TO USE — not just the first frame. A clip that opens on your subject can cut away, change subject or hold a logo exactly where you planned to trim. Read the scene samples from get_media, or render frames with inspect_media, across the range you intend to cut. See read_skill {topic:'verify'}. Input parameters: - `kind` (string, required): photo | video - `maxHeight` (number): Videos only: cap the rendition height (e.g. 1080). - `pexelsId` (number, required): The item id from search_stock_media. - `projectId` (string, required): Project id from get_projects. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `search_sounds` (~369 tokens) Search Freesound 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, plus 0-100 timbre scales like ac_brightness, ac_warmth, ac_hardness, ac_depth, ac_roughness, ac_boominess, ac_sharpness, ac_reverb). A `downloaded` flag says the sound is already in the pool. Licenses: CC0 needs nothing, BY needs attribution, BY-NC excludes commercial use — prefer cc0/by via the license arg when the project may be commercial. If no key is connected it errors with PERMISSION_REQUIRED, whose message says where the user connects one (Library → Generators → Sound Library). Input parameters: - `license` (string): Optional: cc0 | by | by-nc - `maxDurationSeconds` (number): Optional upper duration bound. - `minDurationSeconds` (number): Optional lower duration bound. - `page` (number): 1-based page, 40 items per page. - `projectId` (string, required): Project id from get_projects. - `query` (string, required): Search phrase (e.g. 'door slam', 'jungle ambience'). - `sort` (string): Optional: score (default) | rating_desc | downloads_desc | created_desc - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `download_sound` (~192 tokens) Download Freesound sound 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-.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 files stream at a time and the rest wait their turn, shared with stock video, so state 'queued' is normal and needs no action but polling. Input parameters: - `projectId` (string, required): Project id from get_projects. - `soundId` (number, required): The sound id from search_sounds. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `add_sfx` (~232 tokens) Add built-in sound effects Frapea's BUILT-IN sound-effects pack — synthesized, licence-free, no API key, no download wait. Covers common UI and motion sounds; search_sounds is for what the pack does not (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-.wav` at the Library root; each result gives a mediaRef ready for add_clips on an audio track. Adding a sound already in the project is a no-op that returns its existing mediaRef. Input parameters: - `id` (string): Convenience: a single sound id. - `ids` (array): Sound ids to add (e.g. ['whip','thump','ding']). Omit to list the pack. - `projectId` (string, required): Project id from get_projects. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `manage_queue` (~217 tokens) Manage background queue 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 shows an incomplete-analysis badge; retry_analysis or the tile's retry button runs it again. kind: index | transcribe | stabilize | denoise | proxy | beats. Input parameters: - `action` (string, required): list | cancel - `kind` (string): cancel only: index | transcribe | stabilize | denoise | proxy | beats - `mediaRef` (string): cancel only: asset from get_media. - `projectId` (string): cancel only: project id from get_projects. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `retry_analysis` (~148 tokens) Retry analysis Runs ONE analysis of ONE asset again — picture indexing or speech transcription — clearing whatever failure was recorded for it. If the asset already has a finished transcript or index, that result is deleted and rebuilt. 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. Input parameters: - `kind` (string, required): index | transcribe - `mediaRef` (string, required): Asset from get_media. - `projectId` (string, required): Project id from get_projects. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `set_keyframes` (~345 tokens) Set keyframes 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 keyframes; 'remove' deletes at the given frames; 'clear' removes the property's animation (or ALL animation when property is omitted). easing is how the value LEAVES a keyframe: linear | hold | smooth. Input parameters: - `action` (string): set | remove | clear (default set). - `atSourceFrames` (array): For 'remove': source frames whose keyframes to delete. - `clipId` (string, required): Clip to animate. - `effectId` (string): Animate an EFFECT param instead of a clip property: the effect instance id (from manage_effects add / get_timeline). Use with `param`; `property` is then ignored. - `keyframes` (array): For 'set': keyframes to add or replace. - `param` (string): The effect param key to animate (e.g. 'exposure'). - `projectId` (string, required): Project id from get_projects. - `property` (string): Animatable property (see description). - `timelineId` (string, required): Timeline containing the clip. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `apply_layout` (~264 tokens) Apply layout 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 = centre). Replaces the clips' geometry animation. The clips should overlap in time on different tracks — a layout of clips that never share a frame arranges nothing visible. Input parameters: - `bias` (object): Cover-crop bias 0–1 per axis (default 0.5/0.5). - `clipIds` (array, required): Clips to arrange, in cell order. - `layout` (string, required): Layout id (see description). - `mode` (string): fit | cover (default fit). - `projectId` (string, required): Project id from get_projects. - `timelineId` (string, required): Timeline containing the clips. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `track_faces` (~261 tokens) Track faces 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 purpose — use merge_faces if they are the same person. Input parameters: - `clipId` (string, required): The video clip to scan, from get_timeline. - `holdSeconds` (number): How long a vanished face is still 'the same face' when it comes back (default 1). - `name` (string): Display name for the run. - `projectId` (string, required): Project id from get_projects. - `scoreThreshold` (number): Detection confidence floor, 0.3–0.95 (default 0.6). - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. - `travelFaces` (number): How far it may reappear from where it vanished, in face widths (default 0.8). ### `list_face_tracks` (~123 tokens) List face tracks 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. Input parameters: - `clipId` (string): Only runs made from this clip. - `projectId` (string, required): Project id from get_projects. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `merge_faces` (~158 tokens) Merge faces 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. Input parameters: - `faceIds` (array, required): Two or more faceIds within that run. - `projectId` (string, required): Project id from get_projects. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. - `trackId` (string, required): The run, from list_face_tracks. ### `bind_face` (~300 tokens) Bind clip to a face 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. Input parameters: - `channels` (object): What to copy: {position, scale, pitch, yaw, roll} booleans. Default position and scale on, the three rotations off. - `clipId` (string, required): The clip that should follow the face. - `faceId` (string): Which person in that run. - `gap` (string): While the face is missing: 'hold' stays put then jumps, 'hide' disappears, 'glide' travels smoothly to where it reappears. One of: hold | hide | glide. - `maxGlideSeconds` (number): Longest gap 'glide' will cross before hiding instead (default 1.8). - `projectId` (string, required): Project id from get_projects. - `smooth` (number): Jitter filtering 0–1 (default 0.25). - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. - `trackId` (string): The run; null unbinds this clip. ### `organize_pool` (~485 tokens) Organize media bins 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 relocate anything — organise freely. actions: 'list' returns the bin tree and every item with the bin it shows in (call it first — you need the ids). 'create_bin' {name, parentBinId?}. 'rename_bin' {binId, name}. 'move_bin' {binId, toBinId} nests one bin inside another. 'delete_bin' {binId} — its children and items reparent, nothing is lost, no file is deleted. 'move_items' {itemKeys[], toBinId} moves files, timelines and motion compositions alike. Item keys: a media file's mediaRef, 'timeline:', 'motion:'. The Library root is the empty-string bin id. Bins that MIRROR a real folder (mirrorsFolder: true) can be RENAMED — a mirror is matched by the folder it tracks, not by its name — but they cannot be moved or deleted, because their place in the tree follows the folder. Move the items out instead, or make your own bins alongside. Input parameters: - `action` (string, required): list | create_bin | rename_bin | move_bin | delete_bin | move_items - `binId` (string): Target bin (rename/move/delete). - `itemKeys` (array): move_items: mediaRefs / 'timeline:' / 'motion:' to move together. - `name` (string): Bin name (create_bin, rename_bin). - `parentBinId` (string): Parent for create_bin. Omit or '' = Library root. - `projectId` (string, required): Project id from get_projects. - `toBinId` (string): Destination bin for move_bin / move_items. Omit or '' = Library root. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `measure_loudness` (~566 tokens) Measure loudness MEASURE THE MIX — you cannot hear it; this is how you check it. Mixes the timeline's audio offline exactly as an export does (every audio track, nested timelines, fades, volume keyframes, clip audio effects, ducking, mute/solo) and measures it with EBU R128 / ITU-R BS.1770 — the same meter export loudness normalization uses. The mix is measured AS MIXED: an export's loudnessTargetLufs would then shift all of it by one gain. Returns {jobId}; poll get_job_status every few seconds. When done, `result` is {durationSec, integratedLufs, truePeakDbtp (4× oversampled, BS.1770-4), samplePeakDbfs, loudnessRangeLu, maxShortTermLufs, windows: [{fromSec, toSec, integratedLufs, maxShortTermLufs}] one per windowSec, sections?: [...same per requested section], speech: {source: transcript|none, speechSec, gapSec, mixDuringSpeechLufs, mixInGapsLufs, transcribedClips, untranscribedClips}, tracks: [{trackId, name, carriesSpeech, integratedLufs, samplePeakDbfs, duringSpeechLufs, inGapsLufs}]} (true peak is measured on the whole mix). SPEECH comes from transcript word timings mapped onto the timeline (trims, nests, speed): a GAP is a stretch of at least 0.6 s with no word within 0.25 s of it. `inGapsLufs` of a music/ambience track is the bed's level where nobody talks; compare it with the speech track's `duringSpeechLufs`. Without a transcript (speech.source 'none') the speech/gap fields are null — run start_transcription on the dialogue first. Integrated values are gated (−70 LUFS absolute, −10 LU relative), so silence does not drag them down; null means too short (under 0.4 s) or silent. Needs the project open in the editor tab you are paired with (PROJECT_NOT_OPEN otherwise). Input parameters: - `projectId` (string, required): Project id from get_projects. - `sections` (array): Optional named spans to report on their own — e.g. the intro, each interview answer. Timeline seconds. - `timelineId` (string, required): Timeline to measure (what an export of it would sound like). - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. - `windowSec` (number): Length of each entry in `windows` (3–600 s, default 10). ### `duplicate_timeline` (~230 tokens) Duplicate timeline Copy a timeline under a new name — a backup of the cut before a review round changes it, or a variant to try something on. A DEEP copy: new ids for the timeline, its tracks, clips and transitions; links between clips (A/V pairs, caption groups) are kept, inside the copy. Nested timelines are copied too by default (includeNested), so editing a nest in the original does not change the backup; motion compositions and media are referenced, not copied. The original is not touched and stays the active timeline; one undo removes the copy. Returns {timelineId, name, clips, nestedCopies?}. Input parameters: - `includeNested` (boolean): Copy nested timelines too (default true). false = the copy shares them with the original. - `name` (string): Name of the copy. Default ' copy'. - `projectId` (string, required): Project id from get_projects. - `timelineId` (string, required): Timeline to copy. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `add_sample_media` (~200 tokens) Add sample media Frapea's SAMPLE MEDIA, for trying the editor without your own footage: a short talking clip with speech and pauses (for transcripts, captions, removing words or silences), a b-roll shot, a photo and a music bed. No API key, no download from elsewhere. Call with no `ids` to list them; call with `ids` (or `all: true`) to copy them into the project's media pool at the Library root — each result gives a mediaRef for add_clips. Adding one already in the project returns its existing mediaRef. Input parameters: - `all` (boolean): Add every sample. - `ids` (array): Sample ids to add (talk, broll, photo, music). Omit to list them. - `projectId` (string, required): Project id from get_projects. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `open_timeline` (~150 tokens) Open timeline tab Opens a timeline's TAB in the editor (the user can close tabs to keep the tab row short; a closed timeline is not deleted and every tool works on it as before). By default it does not change what the user is looking at; activate:true also shows it, like set_active_timeline. get_timeline reports `open` per timeline, as last saved. Input parameters: - `activate` (boolean): Also show it (default false). - `projectId` (string, required): Project id from get_projects. - `timelineId` (string, required): Timeline whose tab to open. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ### `close_timeline` (~126 tokens) Close timeline tab Closes a timeline's TAB in the editor — hides it from the tab row, does NOT delete it: it stays in the media pool, and you (or anyone) can still edit, verify, nest and export it. When it was the one shown, the editor shows the next open tab, or none. Input parameters: - `projectId` (string, required): Project id from get_projects. - `timelineId` (string, required): Timeline whose tab to close. - `token` (string, required): The session token `connect` returned. Pass it on every call — it says which browser to drive. ## Diagnostics Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-frapea-editor/app#diagnostics ## Score history - 2026-10-23: 68 - 2026-10-22: 66 - 2026-10-21: 65 - 2026-10-20: 65 - 2026-10-19: 64 - 2026-10-18: 64 - 2026-10-17: 63 - 2026-10-16: 63 - 2026-10-15: 62 - 2026-10-14: 62 - 2026-10-13: 62 - 2026-10-12: 61 ## Common questions ### What is the Frapea MCP server? Frapea is an MCP server listed in the public MCP registry as com.frapea/editor. A video editor in your browser that your AI drives: cuts, captions, multicam, motion titles, export. This page covers its hosted endpoint (https://app.frapea.com/mcp). ### Is the Frapea MCP server safe to use? Frapea scores 68 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm. ### What tools does the Frapea MCP server expose? Frapea exposes 67 tools: connect, get_projects, get_timeline, get_media, get_transcript, and 62 more. Their descriptions and schemas cost roughly 17,950 tokens of context every time the server is loaded. ### Does the Frapea MCP server require authentication? No. We connected to Frapea without credentials and it answered, so anything it exposes is reachable by anyone who knows the address. ### Is the Frapea MCP server still maintained? Frapea is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced. ## Links - Remote endpoint: https://app.frapea.com/mcp - Website: https://frapea.com/ - Changelog RSS feed: https://verifymcp.io/servers/com-frapea-editor/app.xml - Changelog JSON feed: https://verifymcp.io/servers/com-frapea-editor/app.json - HTML version of this page: https://verifymcp.io/servers/com-frapea-editor/app