{"server":"ai.morphareels/morpha","count":48,"changes":[{"tool":"restore_project","kind":"added","observed_at":"2026-10-13T15:44:53.058Z","fields":[],"description_before":null,"description_after":"Bring a project back from Recently deleted, with its versions, files, workspace and sharing as they were. Returns { projectId, name }. Scheduled social posts cancelled by the delete stay cancelled. Requires edit access, as delete_project does; take the id from list_trash.","description_similarity":null,"before_hash":null,"after_hash":"2054a4680ce413817254960c8d3cb8f4"},{"tool":"list_trash","kind":"added","observed_at":"2026-10-13T15:44:53.058Z","fields":[],"description_before":null,"description_after":"List the projects in Recently deleted as { id, name, trashedAt, purgeAt, deletedBy, canEdit } entries. Each can be restored with restore_project until purgeAt (epoch ms), 30 days after it was deleted. `deletedBy` is { kind: \"you\" | \"person\" | \"agent\", label }: the caller, a teammate (label is their email), or a connected assistant (label is its name). `canEdit` says whether the caller may restore it. By default lists the caller's own personal projects; pass `workspaceId` (from list_workspaces) for that workspace's.","description_similarity":null,"before_hash":null,"after_hash":"4585da2a6693de9dedc2fa8f0dea2518"},{"tool":"delete_project","kind":"changed","observed_at":"2026-10-13T15:44:53.058Z","fields":["description"],"description_before":"Ask to permanently delete a project. Returns { name, confirmUrl } and deletes nothing: the project, its saved versions, uploaded images and clips are deleted only when the signed-in account that called this opens confirmUrl and confirms there. The link lasts 30 minutes. An anonymous account, which nobody can sign into, is refused with its claim link instead. Requires edit access — the owner, a workspace editor/admin/owner, or a direct-share editor; anyone else gets the opaque not-found.","description_after":"Move a project to Recently deleted. It leaves every project list at once and can be restored for 30 days, with restore_project or from the person's projects page; after that it is deleted for good, with its saved versions, uploaded images and clips. Returns { name, purgeAt, restorable: true }, where purgeAt is when it will be deleted for good (epoch ms). Deleting for good before then is the person's own step on their projects page; no tool does it. Requires edit access — the owner, a workspace editor/admin/owner, or a direct-share editor; anyone else gets the opaque not-found. Deleting the last remaining project is allowed.","description_similarity":0.346,"before_hash":"0d1a394c62e4111cfb8efc85054b8766","after_hash":"e1544e3cbe61acade48271ba2f544da1"},{"tool":"create_upload_link","kind":"removed","observed_at":"2026-10-12T04:33:01.579Z","fields":[],"description_before":"Put a file from the caller's own disk into a project: an image (.png/.jpg/.jpeg/.gif/.webp/.svg), an audio track (.mp3/.m4a/.wav/.ogg/.aac) or a font (.woff2/.woff/.ttf/.otf). Returns { uploadUrl, filename, name, command, expiresAt, maxBytes }. Run `command` from a shell (a curl line that PUTs the file's raw bytes to uploadUrl), then pass the returned `filename` (the file's id, never shown to a person) to add_image_layer, add_audio_overlay or set_custom_font. The link takes one file, stored under the id it was minted with, for 15 minutes; a second upload in that window replaces the first. The upload is checked as an editor drag-drop is: size cap (16 MB for an image or font, 50 MB for audio), SVG safety, storage quota. A client with no shell passes a public URL to upload_image or upload_audio instead. A video clip is not taken here, because its preview proxy is built on the caller's machine: use the morphareels-sdk's client.addVideo. Reference: https://morphareels.ai/docs/tools#createuploadlinkname","description_after":null,"description_similarity":null,"before_hash":"7936baff8e1e227f100778622f4675e8","after_hash":null},{"tool":"set_video_clip","kind":"changed","observed_at":"2026-10-12T04:33:01.579Z","fields":["description"],"description_before":"Repoint an existing video layer at a different uploaded clip — keeps the layer's id, position, size, animations, styles, and trim window; only the source mp4 changes. The clip must already be uploaded (the editor's Add video, or the morphareels-sdk's client.addVideo); pass the `filename` the upload returned, and its `name` as the label. Use this to swap a video layer's source WITHOUT losing its keyframes.","description_after":"Repoint an existing video layer at a different uploaded clip — keeps the layer's id, position, size, animations, styles, and trim window; only the source mp4 changes. The clip must already be uploaded (the editor's Add video); pass the `filename` the upload returned, and its `name` as the label. Use this to swap a video layer's source WITHOUT losing its keyframes.","description_similarity":0.9,"before_hash":"746cd63897abbd153b626db70b3acf66","after_hash":"30f73f2d2839d5673835b6d7f3a0f28b"},{"tool":"set_image_filename","kind":"changed","observed_at":"2026-10-12T04:33:01.579Z","fields":["description"],"description_before":"Repoint an existing image layer at a different uploaded asset — keeps the layer's id, position, size, animations, and styles; only the bitmap changes. The asset must already exist at users//assets// (the editor's drag-drop, upload_image, create_upload_link, or POST /api/upload-asset/ with the raw bytes and an X-Upload-Name header); pass the `filename` the upload returned, and its `name` as the label. Use this to swap a layer's image WITHOUT losing its keyframes — `remove_layer` + `add_image_layer` would mint a new id and drop the animations.","description_after":"Repoint an existing image layer at a different uploaded asset — keeps the layer's id, position, size, animations, and styles; only the bitmap changes. The image must already be uploaded (upload_image for a web URL or a file attached in the chat; the editor for a file from the person's disk); pass the `filename` the upload returned, and its `name` as the label. Use this to swap a layer's image WITHOUT losing its keyframes — `remove_layer` + `add_image_layer` would mint a new id and drop the animations.","description_similarity":0.644,"before_hash":"f741e07ddd7986933ab0fbed44d66bc4","after_hash":"90051b275eb082815806e9c0c1a246db"},{"tool":"rename_layer","kind":"changed","observed_at":"2026-10-12T04:33:01.579Z","fields":["annotations"],"description_before":null,"description_after":null,"description_similarity":null,"before_hash":"61e1fb7c4637bc3d740fb57159613df0","after_hash":"9a698779c399045e6f5e091243ea9f2b"},{"tool":"set_custom_font","kind":"changed","observed_at":"2026-10-12T04:33:01.579Z","fields":["description"],"description_before":"Register a typeface Morpha does NOT ship, so text layers can use it by family name via font_family (exactly like a built-in family). Families already in the built-in catalogs (anything list_fonts returns from google/bunny/fontshare/fontsource/velvetyne) are REJECTED — they need no registration; just set font_family to them directly. `src` is EITHER a full URL (https://…) OR a font file already uploaded to the project's asset bucket (create_upload_link, or POST /api/upload-asset/ with raw bytes + an X-Upload-Name header; .woff2/.woff/.ttf/.otf): pass the filename the upload returned. Like add_image_layer, this does NOT verify an uploaded filename exists. Dedupes by family+weight+style, replacing a matching face. After registering, set a text layer's font_family to this family (add_text_layer / set_layer_text). NOTE: a pasted URL only loads if that host sends permissive CORS headers — uploading the font (served same-origin) is the robust path. A URL is not fetched when this tool runs: Morpha's renderer and every browser that opens the project download it later. Reference: https://morphareels.ai/docs/tools#setcustomfontfamily-src-weight-style","description_after":"Register a typeface Morpha does NOT ship, so text layers can use it by family name via font_family (exactly like a built-in family). Families already in the built-in catalogs (anything list_fonts returns from google/bunny/fontshare/fontsource/velvetyne) are REJECTED — they need no registration; just set font_family to them directly. `src` is EITHER a full URL (https://…) OR a font file (.woff2/.woff/.ttf/.otf) already uploaded to the project in the editor: pass the filename the upload returned. Like add_image_layer, this does NOT verify an uploaded filename exists. Dedupes by family+weight+style, replacing a matching face. After registering, set a text layer's font_family to this family (add_text_layer / set_layer_text). NOTE: a pasted URL only loads if that host sends permissive CORS headers — uploading the font (served same-origin) is the robust path. A URL is not fetched when this tool runs: Morpha's renderer and every browser that opens the project download it later. Reference: https://morphareels.ai/docs/tools#setcustomfontfamily-src-weight-style","description_similarity":0.898,"before_hash":"d61152406a89a33b705f40eac08dd92a","after_hash":"217d6e15cd27ce972150faee746de2ce"},{"tool":"add_audio_overlay","kind":"changed","observed_at":"2026-10-12T04:33:01.579Z","fields":["description"],"description_before":"Add an audio overlay (mp3/m4a/wav/ogg) scheduled at a frame-aligned start. The asset must already be uploaded (upload_audio, create_upload_link, or the editor); pass the upload's returned `filename`, and its `name` as the track's label. 30 fps; convert seconds with frames = round(s * 30). Plays in the editor preview and is mixed into the MP4 export.","description_after":"Add an audio overlay (mp3/m4a/wav/ogg) scheduled at a frame-aligned start. The asset must already be uploaded (upload_audio, or the editor for a file from the person's disk); pass the upload's returned `filename`, and its `name` as the track's label. 30 fps; convert seconds with frames = round(s * 30). Plays in the editor preview and is mixed into the MP4 export.","description_similarity":0.873,"before_hash":"8ceed7693ed2788c80ea8b822d63fb14","after_hash":"1f743cd10f8d52ffdf98909566e5082e"},{"tool":"rename_group","kind":"changed","observed_at":"2026-10-12T04:33:01.579Z","fields":["annotations"],"description_before":null,"description_after":null,"description_similarity":null,"before_hash":"86b430689c313d185dd069c0e0a75a85","after_hash":"dfef53708a5a563860acd98b765de233"},{"tool":"group_layers","kind":"changed","observed_at":"2026-10-12T04:33:01.579Z","fields":["description"],"description_before":"Wrap sibling elements in a new group. USE THIS whenever several layers are one thing — a butterfly assembled from wings + body + antennae, an icon built from primitives, a card + its title + badge, a lower-third — and name the group what the thing is; a multi-shape object left as loose siblings is a defect the user has to clean up, and the group's name is their only handle on it. The group composes its x/y/scale/rotation/opacity onto its descendants (so one track flies/spins/fades the whole thing) and pivots rotate/scale at its (pivotX, pivotY), seeded to the centroid of its children at create time. The group's x/y track values are translation offsets applied around the pivot — groups have no static body of their own. All listed elementIds must currently share the same parent (root, or one existing group).","description_after":"Wrap sibling elements in a new group, which the Layers panel shows as one named row the person can select, move and animate as one thing (a butterfly assembled from wings + body + antennae, an icon built from primitives, a card + its title + badge, a lower-third). `name` is that row's label. The group composes its x/y/scale/rotation/opacity onto its descendants (so one track flies/spins/fades the whole thing) and pivots rotate/scale at its (pivotX, pivotY), seeded to the centroid of its children at create time. The group's x/y track values are translation offsets applied around the pivot — groups have no static body of their own. All listed elementIds must currently share the same parent (root, or one existing group).","description_similarity":0.719,"before_hash":"7c457be089a19ad14a4026ff47f302bc","after_hash":"d71f39d7a03aaf1810fb4c7d3b4fb979"},{"tool":"add_video_layer","kind":"changed","observed_at":"2026-10-12T04:33:01.579Z","fields":["description"],"description_before":"Add a video layer. The clip must already be uploaded (the morphareels-sdk's client.addVideo, or the editor). An upload returns { filename, name }: pass `filename` (the stored clip's id) as `clip`, and `name` as the layer's label. To duplicate an existing layer, reuse its clip filename — the editor auto-assigns a fresh id.","description_after":"Add a video layer. The clip must already be uploaded; clips are uploaded in the MorphaReels editor. An upload returns { filename, name }: pass `filename` (the stored clip's id) as `clip`, and `name` as the layer's label. To duplicate an existing layer, reuse its clip filename — the editor auto-assigns a fresh id.","description_similarity":0.821,"before_hash":"15b92b923f62338f1e118ce49ff740ee","after_hash":"967fd13dbe8e6d7fa7ed01a1b99dfb81"},{"tool":"add_image_layer","kind":"changed","observed_at":"2026-10-12T04:33:01.579Z","fields":["description"],"description_before":"Add an image layer. The asset must already be uploaded (the editor's drag-drop, upload_image, create_upload_link, or POST /api/upload-asset/ with the raw bytes and an X-Upload-Name header). Every upload returns { filename, name, width, height }: pass `filename` (the stored file's id) here, and `name` as the layer's label. SIZE THE BOX TO THE PICTURE: pass `width` alone (or `height` alone) and the other side is filled from the image's own aspect, so the picture is never stretched; a box with both sides that does not match the image's aspect stretches the picture to fill it. To duplicate an existing layer, reuse its filename — the editor auto-assigns a fresh id.","description_after":"Add an image layer. The image must already be uploaded: upload_image takes a web URL or a file attached in the chat, and a file from the person's disk is uploaded in the editor. Every upload returns { filename, name, width, height }: pass `filename` (the stored file's id) here, and `name` as the layer's label. SIZE THE BOX TO THE PICTURE: pass `width` alone (or `height` alone) and the other side is filled from the image's own aspect, so the picture is never stretched; a box with both sides that does not match the image's aspect stretches the picture to fill it. To duplicate an existing layer, reuse its filename — the editor auto-assigns a fresh id.","description_similarity":0.75,"before_hash":"149ba5d0df6c99fa2796d9f7212017f0","after_hash":"b1a057b393a20fb77e294933901438fa"},{"tool":"render_video","kind":"changed","observed_at":"2026-10-12T04:33:01.579Z","fields":["description"],"description_before":"Render the project to an MP4 on Morpha's servers, for an agent that has no browser to drive (a chat app, a Linux box). Returns { renderId, status: 'rendering', next } — call render_status with that renderId after about 30 seconds. It needs a subscription and draws on the account's render allowance, so a longer composition and a larger scale each use more of it. Two other routes need no allowance and are usually better — give the person the editorUrl every project result carries and they choose Share, then Download (Render MP4 on a phone) in the editor, free and with no watermark; or a script runs the morphareels-sdk npm client's client.renderVideo(projectId) on macOS or Windows. Renders at 2x the canvas by default, the same as the editor and the npm client; pass scale: 1 for the canvas's own size, which is faster and uses less allowance. The allowance is checked before the render starts, so a render that would exceed it is refused up front rather than failing partway. Refused for a composition longer than 30 minutes, when the remaining allowance will not cover it, or while 3 renders are already running for this account. The finished file stays downloadable for 7 days, then it is deleted; the project stays and can be rendered again. The render downloads the project's fonts from their hosts, including a custom font's own URL (set_custom_font). Reference: https://morphareels.ai/docs/tools#rendervideopage-scale","description_after":"Render the project to an MP4 on Morpha's servers, for an agent that has no browser to drive (a chat app, a Linux box). Returns { renderId, status: 'rendering', next } — call render_status with that renderId after about 30 seconds. It needs a subscription and draws on the account's render allowance, so a longer composition and a larger scale each use more of it. The editor renders the same MP4 with no allowance: every project result carries an editorUrl, and there the person can choose Share, then Download (Render MP4 on a phone), free and with no watermark. Renders at 2x the canvas by default, the same as the editor; pass scale: 1 for the canvas's own size, which is faster and uses less allowance. The allowance is checked before the render starts, so a render that would exceed it is refused up front rather than failing partway. Refused for a composition longer than 30 minutes, when the remaining allowance will not cover it, or while 3 renders are already running for this account. The finished file stays downloadable for 7 days, then it is deleted; the project stays and can be rendered again. The render downloads the project's fonts from their hosts, including a custom font's own URL (set_custom_font). Reference: https://morphareels.ai/docs/tools#rendervideopage-scale","description_similarity":0.874,"before_hash":"fb5d235570b9d69dd4e20572d5e4bd69","after_hash":"5a8998a4e6bb5dda54e3f6bc35efea24"},{"tool":"clip_processing_status","kind":"changed","observed_at":"2026-10-12T04:33:01.579Z","fields":["description"],"description_before":"Report whether a clip — or every video clip in the project, if `clip` is omitted — has been through the browser-side video-processing pipeline: proxy build, audio split, transcription, OCR (text regions). Processing never runs on the server. The preview proxy is mandatory: every processing run builds it (client.addVideo / client.processClip / client.processProject in the morphareels-sdk npm client, which drive local Chrome), and the Morpha editor builds any missing proxy for every page's clip when the project is opened. The other steps run through the same npm client or in the editor. Returns { ok: true, data: { clips: [{ clip, processed, steps: { proxy, audio_split, transcript, text_regions } }], allProcessed } }, where each step is 'ready' | 'pending' | 'running' | 'unavailable' | 'cancelled' | 'error'. 'cancelled' is a transcript the user stopped in the editor: it stays stopped across opens, and only the editor's Re-run starts it again. audio_split stays 'pending' until the user splits the clip's audio into its own track in the editor (Inspector → Audio → Split audio) or the SDK's audio_split step runs; it never gates `processed`, and an unsplit clip plays its own sound. Use it to know whether transcribe_clip / detect_text_regions will return data, and to surface an 'unprocessed' state to the user.","description_after":"Report whether a clip — or every video clip in the project, if `clip` is omitted — has been through the browser-side video-processing pipeline: proxy build, audio split, transcription, OCR (text regions). Processing never runs on the server. The preview proxy is mandatory: every processing run builds it, and the Morpha editor builds any missing proxy for every page's clip when the project is opened. The other steps run in the editor too. Returns { ok: true, data: { clips: [{ clip, processed, steps: { proxy, audio_split, transcript, text_regions } }], allProcessed } }, where each step is 'ready' | 'pending' | 'running' | 'unavailable' | 'cancelled' | 'error'. 'cancelled' is a transcript the user stopped in the editor: it stays stopped across opens, and only the editor's Re-run starts it again. audio_split stays 'pending' until the user splits the clip's audio into its own track in the editor (Inspector → Audio → Split audio); it never gates `processed`, and an unsplit clip plays its own sound. Use it to know whether transcribe_clip / detect_text_regions will return data, and to surface an 'unprocessed' state to the user.","description_similarity":0.882,"before_hash":"314a99e5267f8a3721569715125f9495","after_hash":"a79441acd9fa0f089b4bfade130005b7"},{"tool":"upload_audio","kind":"changed","observed_at":"2026-10-12T04:33:01.579Z","fields":["description"],"description_before":"Upload an audio track into a project from a public http(s) URL or a file attached in the chat, fetched server-side — the ONLY way to get an audio file's bytes into a project over MCP/HTTP (add_audio_overlay / update_audio_overlay only reference a file that is already uploaded). Pass `url` for a public http(s) link, or `file` for a file the person attached in the chat (a host that supports file inputs, such as ChatGPT, fills `file` with a temporary download link itself; do not ask the person for a URL to something they have attached). The target is the URL you pass and nothing else: Morpha's Worker fetches it with a plain HTTP GET, following redirects, and identifies itself as \"Morpha/1.0 (+https://morphareels.ai; hello@morphareels.ai)\". No third-party API is involved. The worker downloads the .mp3/.m4a/.wav/.ogg/.aac, stores it in the project's asset bucket under a new id, and returns { filename, name, sizeBytes, contentType }. Then pass the returned `filename` (the file's id, never shown to a person) to add_audio_overlay (add a second track) or update_audio_overlay { id, filename } (replace an existing track's file — find the id via describe_video's audio_overlays), with `name` as the track's name. A url must be a direct, publicly-fetchable http(s) link (not an auth-walled page). Buffered in Worker memory, so capped at 50 MB. For a file on the caller's own disk, use create_upload_link instead. Reference: https://morphareels.ai/docs/tools#uploadaudiourl-file-name","description_after":"Upload an audio track into a project from a public http(s) URL or a file attached in the chat, fetched server-side — the ONLY way to get an audio file's bytes into a project over MCP/HTTP (add_audio_overlay / update_audio_overlay only reference a file that is already uploaded). Pass `url` for a public http(s) link, or `file` for a file the person attached in the chat (a host that supports file inputs, such as ChatGPT, fills `file` with a temporary download link itself; do not ask the person for a URL to something they have attached). The target is the URL you pass and nothing else: Morpha's Worker fetches it with a plain HTTP GET, following redirects, and identifies itself as \"Morpha/1.0 (+https://morphareels.ai; hello@morphareels.ai)\". No third-party API is involved. The worker downloads the .mp3/.m4a/.wav/.ogg/.aac, stores it in the project's asset bucket under a new id, and returns { filename, name, sizeBytes, contentType }. Then pass the returned `filename` (the file's id, never shown to a person) to add_audio_overlay (add a second track) or update_audio_overlay { id, filename } (replace an existing track's file — find the id via describe_video's audio_overlays), with `name` as the track's name. A url must be a direct, publicly-fetchable http(s) link (not an auth-walled page). Buffered in Worker memory, so capped at 50 MB. A file on the person's own disk is uploaded in the editor. Reference: https://morphareels.ai/docs/tools#uploadaudiourl-file-name","description_similarity":0.963,"before_hash":"e20545f3e8e77022bf13e0eadd32d754","after_hash":"13205c18363aaa2fc108a9d7b00c30e7"},{"tool":"upload_image","kind":"changed","observed_at":"2026-10-12T04:33:01.579Z","fields":["description"],"description_before":"Upload an image into a project from a public http(s) URL or a file attached in the chat, fetched server-side. Pass `url` for a public http(s) link, or `file` for a file the person attached in the chat (a host that supports file inputs, such as ChatGPT, fills `file` with a temporary download link itself; do not ask the person for a URL to something they have attached). The target is the URL you pass and nothing else: Morpha's Worker fetches it with a plain HTTP GET, following redirects, and identifies itself as \"Morpha/1.0 (+https://morphareels.ai; hello@morphareels.ai)\". No third-party API is involved. The worker downloads the .png/.jpg/.jpeg/.gif/.webp/.svg, stores it in the project's asset bucket under a new id, and returns { filename, name, sizeBytes, contentType, width, height }: pass the returned `filename` (the file's id, never shown to a person) to add_image_layer, and `name` is what people see; `width` and `height` are the picture's own pixel size (null when its header did not say), so size the layer from them or pass add_image_layer one side and let it keep the aspect. This tool does not search for images: pass a direct image file URL, such as one the person has given you, and respect the licence its source states. A url must be a direct, publicly-fetchable http(s) link (not an auth-walled page). SVGs are rejected if they carry a