{"data":{"name":"io.clueso/video","title":"Clueso","description":"Make videos and docs with your AI agent — describe what you need, every output stays editable.","version":"1.0.2","websiteUrl":"https://help.clueso.io/mcp-setup","repositoryUrl":"https://github.com/clueso-ai/clueso-mcp","remotes":[{"url":"https://connect.clueso.io/mcp","type":"streamable-http"}],"packages":[],"status":"active","isLatest":true,"publishedAt":"2026-08-19T12:26:06.099Z","updatedAt":"2026-08-19T12:26:06.099Z","source":"official-registry","verification":"official","confidence":100,"stars":null,"sources":[{"stars":null,"title":"Clueso","source":"official-registry","sourceId":"io.clueso/video","updatedAt":"2026-08-19T12:26:06.099Z","confidence":100,"websiteUrl":"https://help.clueso.io/mcp-setup","description":"Make videos and docs with your AI agent — describe what you need, every output stays editable.","verification":"official","repositoryUrl":"https://github.com/clueso-ai/clueso-mcp"}],"toolIndex":{"tools":[{"serverName":"io.clueso/video","endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","name":"add_article_media","title":"Add article media (image or GIF)","description":"Add a screenshot or GIF to the article. It goes right after the block holding the screenshot named in `after` (\"start\" for the top), in place of the screenshot named in `replace`, or else at the end of the article. Returns its screenshot_id (it appears in the article as `<SCREENSHOT screenshot_id>`) and the new article_version.\n\n- kind=\"image\": one of `timestamp` (capture a frame from the project's base video), `mcp_upload_id` (an uploaded image: `mup_…` from upload_file, or a Clueso upload_id), `source_url` (an image URL, e.g. one generate_media returned) or `prompt` (generate an AI illustration for the article; optional `style_id` and `aspect_ratio`, default 16:9). A generated image costs AI credits like generate_media's and takes a few seconds; ask for little or no text in it, since generated text is often misspelled.\n- kind=\"gif\": pass `timestamp` (start) and `duration` (seconds). Captures a short GIF clip from the base video. Requires the project to have a video clip. A GIF still rendering after ~20s returns `status: \"processing\"` and a `job_id`: it is added to the article when ready (follow it with get_media_job).","inputSchema":{"type":"object","properties":{"kind":{"type":"string","enum":["image","gif"],"description":"'image' or 'gif'."},"project_id":{"type":"string","description":"Project ID."},"timestamp":{"description":"kind='image': capture frame at this timestamp (seconds). kind='gif': GIF start time.","type":"number","minimum":0},"duration":{"description":"kind='gif' only: GIF duration in seconds.","type":"number","exclusiveMinimum":0},"mcp_upload_id":{"description":"kind='image' only: attach an uploaded image (mcp_upload_id from upload_file, or a Clueso upload_id) instead of capturing from video.","type":"string"},"source_url":{"description":"kind='image' only: an https image URL to download and attach.","type":"string","format":"uri"},"prompt":{"description":"kind='image' only: generate an AI illustration from this prompt instead of capturing or attaching one.","type":"string","minLength":1},"style_id":{"description":"kind='image' with prompt only: an image style pack ID from find(type='image_gen_style_packs').","type":"string"},"aspect_ratio":{"description":"kind='image' with prompt only: the illustration's shape. Default 16:9.","type":"string","enum":["16:9","1:1","4:3","3:4","9:16","21:9"]},"after":{"description":"Put it right after the block holding this screenshot_id, or 'start' / 'end' (the default).","type":"string","minLength":1},"replace":{"description":"Put it in place of this screenshot_id, wherever that sits; the old one is removed from the article.","type":"string","minLength":1}},"required":["kind","project_id"],"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":{"title":"Add article media (image or GIF)","readOnlyHint":false,"destructiveHint":false,"openWorldHint":true},"definitionHash":"a56232b899e6c2109eaa945de045e571a16d67da3f36209ee1310aa67516032e","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-18T11:47:04.042Z","metadataTrust":"untrusted"},{"serverName":"io.clueso/video","endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","name":"add_audio","title":"Add audio track","description":"Add a music track or sound effect that plays as a project-level audio layer over all clips. Does NOT consume a clip slot. Use this for background music or a soundtrack that should play under the existing timeline. Sound for an HTML animation goes here, not in its page: guide_start_time = the element's start + the cue's t. (For inserting an audio file as its own sequential clip with auto-transcription, use add_clips(kind='video') with an audio mime_type instead.)\n\n- type=\"music\": requires src. `src` is the `src` from a find(type='music') result (pass with its name and duration as source_duration), or an upload: an mcp_upload_id (`mup_`) from upload_file or a Clueso upload_id, whose name and duration are filled in for you. For a Freesound result the `src` is an opaque handle; pass it through unchanged and Clueso downloads + hosts the original server-side (do not try to fetch it yourself). Anything not from find has its duration probed. Optional: guide_start_time, guide_end_time, music_start_time, music_end_time (trim the source track), volume, loop, fade_in, fade_out. A user's own upload is also saved to the project's media panel (saved_to_media_panel).\n- type=\"sfx\": pass the `src`, `name`, and `source_duration` from a find(type='sfx') result (or an upload as `src`), plus guide_start_time (Freesound `src` is an opaque handle, resolved server-side just like music). Optional: volume. (Legacy: a fixed-library `sfx_key` like 'whoosh' still works instead of src.)\n\nConcurrency: whole-project mutation (conflict domain: the entire project) — serialize; do not run in parallel with ANY other mutation on the same project_id (including element/voiceover edits). Size your clips BEFORE calling add_audio, or pass guide_end_time explicitly — the default ('end of project') is captured at call time and will NOT auto-extend if clips are added or resized afterwards.","inputSchema":{"type":"object","properties":{"project_id":{"type":"string","description":"The project ID"},"type":{"type":"string","enum":["music","sfx"],"description":"Audio type: 'music' or 'sfx'"},"src":{"description":"Audio source. For type='music' (required) or a stock type='sfx': the `src` from a find(type='music'|'sfx') result (may be an opaque Freesound handle — pass as-is), or an upload id (mcp_upload_id 'mup_…' or a Clueso upload_id). Not needed for legacy fixed-library sfx (use sfx_key).","type":"string"},"name":{"description":"Track/effect name. From the find result; for an upload it defaults to the file name.","type":"string"},"source_duration":{"description":"Source duration in seconds, from the find result. Uploads and other URLs are probed.","type":"number","exclusiveMinimum":0},"guide_start_time":{"description":"When to start playing in the guide timeline (seconds). Required for type='sfx', optional for music (default 0).","type":"number","minimum":0},"guide_end_time":{"description":"When to stop playing (seconds). Music only. Default = end of project AT CALL TIME — captured once at insert and NOT recomputed when clips are later added or resized. Pass an explicit value (e.g. the intended final project duration) when adding audio before clips are sized.","type":"number","exclusiveMinimum":0},"music_start_time":{"description":"In-point within the SOURCE track (seconds) — trims where playback begins in the music file. Music only. Default 0 (start of source).","type":"number","minimum":0},"music_end_time":{"description":"Out-point within the SOURCE track (seconds) — trims where playback ends in the music file. Music only. Default = source_duration.","type":"number","exclusiveMinimum":0},"volume":{"description":"Volume as percent (0–100). Default: 20 for music (under narration), 80 for sfx.","type":"number","minimum":0,"maximum":100},"loop":{"description":"Loop the track if project is longer than the source. Music only. (default: false)","type":"boolean"},"fade_in":{"description":"Fade-in duration in seconds. Music only. (default: 0.5)","type":"number","minimum":0},"fade_out":{"description":"Fade-out duration in seconds. Music only. (default: 0.5)","type":"number","minimum":0},"sfx_key":{"description":"LEGACY fixed-library SFX key (e.g. 'whoosh', 'pop', 'click'). Optional alternative to src for type='sfx'. Prefer the src/name/source_duration from a find(type='sfx') result.","type":"string"}},"required":["project_id","type"],"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":{"title":"Add audio track","readOnlyHint":false,"destructiveHint":false,"openWorldHint":false},"definitionHash":"196d751a6944ef50e84b03c5e101615175aebf72fb3bbf668ff11ead69145fa3","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-18T11:47:04.042Z","metadataTrust":"untrusted"},{"serverName":"io.clueso/video","endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","name":"add_clips","title":"Add clips to project","description":"Create new clips on a project. One tool, four sources:\n\n- kind=\"blank\": empty slide clips you'll populate with add_elements / generate_media. Pass `clips: [{title?, duration?}, ...]`. Note: create_project already creates clip 0; calling with N blank entries gives N+1 clips total.\n- kind=\"pptx\": extract slides from an uploaded .ppt/.pptx. Pass `mcp_upload_id` (from upload_file), optional `slide_indices`. Each slide becomes a slide_clip with native text/image/shape elements pre-populated.\n- kind=\"video\": cut clips from an uploaded video/audio. Pass `mcp_upload_id` and optionally `mime_type` (default video/mp4), `title`, `voiceover_text`, `cuts: [{start_seconds, end_seconds, heading?}]`, `auto_elements`. Without `cuts` the whole upload becomes one clip. Pipeline (download → transcribe → insert) runs in the background; subsequent calls on the same upload hit a 24h cache and return synchronously. (To overlay a video ONTO an existing clip — picture-in-picture, b-roll, background loop — rather than insert it as its own clip, use add_elements(element_type='video') instead.)\n  - Re-cut clips already on the timeline: pass `source_start_clip_id`, `source_end_clip_id` (a run of video clips from one recording, inclusive) and `cuts` instead of an upload. The run is replaced in place by one clip per cut; cut seconds are on the run's own clock (0 = start of the first clip). Recording cut out between the clips counts back in, so a cut across it restores that footage (`restored_gap_seconds`).\n- kind=\"template\": one clip from a clip template (find(type='clip_templates')). Pass `template_id` and `text_overrides` (strings for the template's text elements in document order; a missing or empty one keeps the placeholder — fill them with the user's words). `after_clip_id` is REQUIRED: ask the user where it goes, never guess. Insert only; a template whose aspect ratio differs from the project is refused (`aspect_mismatch` — pick another). The clip inherits the project's voice.\n\nAll variants accept `after_clip_id` to control insertion position; appends at end if omitted (except kind=\"template\").\n\nConcurrency: whole-project mutation (conflict domain: the entire project) — serialize. Do not run it in parallel with ANY other mutation on the same project_id, including element/voiceover edits; run them one at a time. (Mutations to different projects run in parallel freely.)","inputSchema":{"type":"object","properties":{"kind":{"type":"string","enum":["blank","pptx","video","template"],"description":"Source for the new clips: 'blank' | 'pptx' | 'video' | 'template'."},"project_id":{"type":"string","description":"Project (guide) ID."},"after_clip_id":{"description":"Insert after this clip ID; appends at end if omitted. kind='video': '' inserts at the front.","type":"string"},"clips":{"description":"kind='blank' only: one entry per blank clip. Optionally set background_color/background + transition per clip at creation — no follow-up update_clips needed.","type":"array","items":{"type":"object","properties":{"title":{"description":"Clip title shown in the timeline.","type":"string"},"duration":{"description":"Clip length in seconds. Defaults to a short blank-clip duration.","type":"number","exclusiveMinimum":0},"background_color":{"description":"Hex background set at creation, e.g. '#0B0E1A'.","type":"string"},"background":{"description":"Background set at creation: an object from find(type='backgrounds'), or { src, media_type?, padding?, border_radius?, shadow?, volume? } as in update_clips.","type":"object","propertyNames":{"type":"string"},"additionalProperties":{}},"transition":{"description":"Transition at the END of this clip, into the next one.","type":"object","properties":{"type":{"type":"string","enum":["circleWipe","rainbowWipe","cornerWipe","stack","colorWipe","dissolve","pushPull","fadeToColor","flip"],"description":"Plays at the END of this clip into the next (between clips 2 and 3 → set it on clip 2)."},"duration":{"type":"number","exclusiveMinimum":0,"description":"Transition length in seconds."},"direction":{"description":"rainbowWipe/cornerWipe: topLeft/topRight/bottomLeft/bottomRight (default topRight). colorWipe: left/right (default right). stack/pushPull: left/right/top/bottom (default right). flip (3D card turn): horizontalLeft/horizontalCenter/horizontalRight/verticalTop/verticalCenter/verticalBottom (default horizontalCenter; horizontal = turns left↔right, edge or centre line). Others ignore it.","type":"string"},"color":{"description":"Hex. fadeToColor (default #000000), colorWipe (#073cad), rainbowWipe (#D43F8C), flip (backdrop, #000000).","type":"string"},"bezier":{"description":"flip only: CSS cubic-bezier [x1, y1, x2, y2] (e.g. [0.34, 1.56, 0.64, 1] bounces); default ease-in-out.","minItems":4,"maxItems":4,"type":"array","items":{"type":"number"}}},"required":["type","duration"]}}}},"mcp_upload_id":{"description":"kind='pptx' or 'video': mcp_upload_id from upload_file, or a Clueso upload_id (or its S3 key).","type":"string"},"slide_indices":{"description":"kind='pptx' only: 0-based slide indices to insert. Omit to insert all slides.","type":"array","items":{"type":"integer","minimum":0,"maximum":9007199254740991}},"mime_type":{"description":"kind='video' only: MIME type (default 'video/mp4'). Audio MIME types insert the file as a sequential clip with auto-TTS; for background music, use add_audio instead.","type":"string"},"title":{"description":"kind='video' only: clip title (default 'Video').","type":"string"},"voiceover_text":{"description":"kind='video' only: post-AI voiceover script (saved as v2). Original audio is always retained as the base transcript. Bracketed emotion tags ([excited], [whispers]) are performed, not spoken; <pause:1.5s> is exact timed silence.","type":"string"},"cuts":{"description":"kind='video' only: per-clip cuts. Each entry becomes one inserted clip. Omit to insert the full upload as a single clip.","type":"array","items":{"type":"object","properties":{"start_seconds":{"type":"number","minimum":0,"description":"Cut start in original-source seconds (inclusive)."},"end_seconds":{"type":"number","exclusiveMinimum":0,"description":"Cut end in original-source seconds (exclusive)."},"heading":{"description":"Optional clip title for this cut.","type":"string"}},"required":["start_seconds","end_seconds"]}},"source_start_clip_id":{"description":"kind='video' re-cut: first clip of the run to re-cut (inclusive).","type":"string"},"source_end_clip_id":{"description":"kind='video' re-cut: last clip of the run (inclusive).","type":"string"},"auto_elements":{"description":"kind='video' only: when true, run auto-element detection (zooms, spotlights, blurs). Default false. Only meaningful on cache miss; cache hits clone the originating run's auto-elements.","type":"boolean"},"template_id":{"description":"kind='template' only: template_id from find(type='clip_templates').","type":"string"},"text_overrides":{"description":"kind='template' only: text for the template's text elements, in document order.","type":"array","items":{"type":"string"}}},"required":["kind","project_id"],"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":{"title":"Add clips to project","readOnlyHint":false,"destructiveHint":false,"openWorldHint":false},"definitionHash":"33c9f813e4a28367f13b24b8a3373c6c8cd36bd5da3411fdffff81a769ad0368","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-18T11:47:04.042Z","metadataTrust":"untrusted"},{"serverName":"io.clueso/video","endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","name":"add_elements","title":"Add elements to clips","description":"Add elements to one or more clips in ONE call (always batch). Items apply in order; one result per item (partial success ok). type_data shape: get_element_schema.\n\n- `defaults`: hoist what repeats (clip_index, element_type, font_setting, alignment…); items carry only what differs. `returning` shapes the reply.\n- Native elements by default (editable, translatable); compute boxes and keyframes in run_script (layout.row/grid/split, anim.stagger, native.box/text/tween). HTML animation (edit_animation place, animation.place) only where native can't: charts, product UI, diagrams, illustration, 3D, shaders, complex choreography. Recording effects (zoom, blur, spotlight, cursor, callouts), captions and translated copy: always native.\n- Reuse: `component_id` inserts a saved component; `continue_from` carries an element/group across a cut.\n- x/y/width/height required except: zoom (ignored; type_data.centerX/centerY), animation (default full canvas), avatar (omit for default bottom-right and size; width sets size; read get_element_schema('avatar') first; result `avatar` = will it render + cost; avatarId from find(type='avatars')).\n- Text: x/y origin follows alignment; send y_anchor with every y.\n- Keyframes: top-level `keyframes` (not in type_data); clip seconds ≥0 (a wind-up goes inside the clip); positionX/Y use the same origin as x/y.\n\nZ-order: list order = z (later on top; new → front). insert_at {before|after: id} also joins that node's group. reorder_elements rewrites a whole clip's order.\n- group + insert_at {before|after}: reference INSIDE the group → the element takes that slot; OUTSIDE → the GROUP takes it (seat a backdrop group at a depth: hoist both into defaults). Moving an existing group this way is refused: seat it in the call that creates it. front/back with group move the GROUP only while it is new (element alone in it); after that they position the element inside it.\n- Grouping keeps coordinates; members render contiguously at the group's slot; a new group takes its first member's slot (scattered members gather at the lowest).\n\nConcurrency: one call = one save. Parallel calls are fine on DIFFERENT clips; on the same clip the later is REJECTED ('changed since this edit was based on') and writes nothing: batch per clip, or re-read and re-apply. Don't overlap with whole-clip/project writes on the same project (update_clips on that clip, add_clips, remove_clip, split_clip, duplicate_clip, add_audio, update_project).","inputSchema":null,"annotations":{"title":"Add elements to clips","readOnlyHint":false,"destructiveHint":false,"openWorldHint":false},"definitionHash":"95ad28138e73c557b0d4a690c7f884dc60ab7dc5aa7929d76bfd12cdca448788","schemaStatus":"too-large","origin":"official-registry","observedAt":"2026-11-18T11:47:04.042Z","metadataTrust":"untrusted"},{"serverName":"io.clueso/video","endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","name":"add_sync_point","title":"Add a sync point at a word + timestamp","description":"Insert one sync marker on a clip's transcript.\n\nUse this when:\n- The user is explicit about WHERE the camera should pause / cut (e.g. \"sync the word 'submit' to 4.2s of the demo\").\n- `auto_sync` ran but missed a step you care about.\n\nHow matching works:\n- `word`: case-insensitive, punctuation-stripped. The first match in the transcript is used unless `occurrence > 1`.\n- `occurrence`: 1-indexed — pass 2 to target the SECOND time that word appears, 3 for the third, etc. Required when the word repeats.\n- `timestamp_seconds`: clip-relative seconds. When the clip has run TTS already (`generated_timestamps` present), the server inverse-maps this to original-recording seconds automatically.\n\nConstraints: the clip MUST be a video clip with a source recording (otherwise the frame thumbnail can't be extracted). The transcript must already contain the word — if not, you'll get `word_not_found` with a 200-char excerpt of the transcript to help you retry.","inputSchema":{"type":"object","properties":{"project_id":{"type":"string","description":"Project ID."},"clip_id":{"description":"Clip ID (preferred). If omitted, clip_index is used.","type":"string"},"clip_index":{"description":"Zero-based clip index. Ignored if clip_id is provided.","type":"integer","minimum":0,"maximum":9007199254740991},"word":{"type":"string","minLength":1,"description":"Target word (case-insensitive; trailing punctuation is stripped)."},"occurrence":{"default":1,"description":"1-indexed match number when the word repeats. Defaults to 1 (first occurrence).","type":"integer","minimum":1,"maximum":9007199254740991},"timestamp_seconds":{"type":"number","minimum":0,"description":"Clip-relative timestamp in seconds. Auto-mapped to original-recording seconds when the clip has generated_timestamps."},"sync_point_name":{"description":"Optional label (e.g. 'Click submit'). Defaults to 'Sync point N' using the next order number.","type":"string"}},"required":["project_id","word","timestamp_seconds"],"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":{"title":"Add a sync point at a word + timestamp","readOnlyHint":false,"destructiveHint":false,"openWorldHint":false},"definitionHash":"3b983348ac601181c83863ad9a19984228bc07a3db135a2d067f2c22e5f63970","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-18T11:47:04.042Z","metadataTrust":"untrusted"},{"serverName":"io.clueso/video","endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","name":"analyze_audio","title":"Analyze audio","description":"Analyze an audio file. Modes:\n- transcript: Speech-to-text with word-level timestamps — returns `{language, full_text, words}` where each word is `{word, start_ms, end_ms, punctuated_word}`. ⚠ MILLISECONDS here; get_clip's `voiceover_words` gives the same words in SECONDS as `{word, start, end}`. Use for caption timing, script editing, or word-level visual sync. Works on narration and on sung lyrics: the provider is picked from the content, and if it returns nothing the other one is tried automatically. So an empty `words` means the audio genuinely has no intelligible speech, not that the wrong engine ran.\n- silences: returns `{silences, total_silence_ms}`, each span `{start_ms, end_ms, peak_db}`. Use for auto-trim, smart-split, or pause-aware editing.\n- beats: returns `{tempo_bpm, beats_ms}` — beats_ms is an array of MILLISECOND positions. Empty for non-music. Use to align animations/zooms to a beat.\n- features: returns `{duration_ms, peak_db, rms_db, lufs, has_music, has_speech, speech_share}` — loudness plus two INDEPENDENT hints — `has_music` (beats hold a steady period) and `has_speech` (at least 40% of the audible seconds sound like talking; `speech_share` is that share, 0-1). Instrumentals read false; so do sung vocals and narration under a loud bed, so when the words matter, use transcript. Cheap dispatcher — call once to pick a mode, or for duration_ms to pass as add_audio's source_duration.\n- energy: loudness over time — `{samples_per_second, start_ms, db}`, db one RMS dBFS value per 1/samples_per_second s from start_ms (default 4 a second; energy_options.samples_per_second 1-20). Read builds, dips and hits from it.\n- sections: how a track is built — `{loud_db, sections: [{label, start_ms, end_ms, db, onsets_per_s}], drops: [{t_ms, rise_db, quiet_start_ms?, quiet_end_ms?}]}`, label intro | build | drop | main | breakdown | outro; a drop's t_ms is the hit (within ~10 ms), quiet_* the dip just before it. Set animation cues on beats (beats mode) or drops.\n- describe: what the audio IS — `{kind: speech|music|mixed, classification_confidence, duration_seconds, music?: {tempo_bpm, key, mood, genre, energy, instruments, description, suggested_search_query}, speech?: {...}}`. Pass suggested_search_query to find(type='music') for a similar track. Speech is not transcribed here; use transcript for the words.\n\nSource: provide exactly one of mcp_upload_id (from upload tool) or file_url (already-public URL, e.g. a find(type='music') result or Clueso CDN file).\nOptional time range: range_start_ms / range_end_ms crops the analysis window.","inputSchema":{"type":"object","properties":{"mcp_upload_id":{"description":"mcp_upload_id from upload_file, or a Clueso upload_id. Use this OR file_url, not both.","type":"string"},"file_url":{"description":"Public http(s) URL to the audio. Use when the file is already accessible (e.g. find(type='music') result, Clueso CDN). Validated against private/loopback ranges.","type":"string"},"mode":{"type":"string","enum":["transcript","silences","beats","features","energy","sections","describe"],"description":"Which analysis to run."},"range_start_ms":{"description":"Start of analysis window in milliseconds. Default 0 (beginning).","type":"integer","minimum":0,"maximum":9007199254740991},"range_end_ms":{"description":"End of analysis window in milliseconds. Default: whole file.","type":"integer","minimum":0,"maximum":9007199254740991},"transcript_options":{"description":"Options for mode='transcript'.","type":"object","properties":{"language":{"description":"Language code hint (e.g. 'en', 'es'). Auto-detected if omitted.","type":"string"}}},"silences_options":{"description":"Options for mode='silences'.","type":"object","properties":{"min_pause_ms":{"description":"Minimum pause length to report. Default 250ms.","type":"integer","exclusiveMinimum":0,"maximum":9007199254740991},"threshold_db":{"description":"Silence threshold in dBFS. Default -40.","type":"number"}}},"energy_options":{"description":"Options for mode='energy'.","type":"object","properties":{"samples_per_second":{"description":"Loudness values per second. Default 4.","type":"number","minimum":1,"maximum":20}}}},"required":["mode"],"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":{"title":"Analyze audio","readOnlyHint":true,"destructiveHint":false,"openWorldHint":false},"definitionHash":"e2c4e2996934eedf876fccbadfb973ff60583e12e0e67c475443d77e2109d51e","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-18T11:47:04.042Z","metadataTrust":"untrusted"},{"serverName":"io.clueso/video","endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","name":"auto_sync","title":"Auto-generate sync points","description":"Run the agentic auto-sync pipeline on a clip with a source recording: detects natural sync points (UI changes, narrated steps) and inserts sync-marker nodes into its transcript. Required before voiceover TTS on video clips (clueso://docs/sync-points).\n\nSkips (no run): \"audio_extracted\" (read-only transcript); \"clip_busy\" + held_by (retry later); \"clip_too_long\" + {clip_id, duration_label} (trimmed window over 5 min; never quote the limit): split_clip it into shorter clips and auto_sync each.\n\nReturns once started; markers land a few seconds later, so poll get_clip before TTS.","inputSchema":{"type":"object","properties":{"project_id":{"type":"string","description":"Project ID."},"clip_id":{"type":"string","description":"Clip ID to auto-sync."}},"required":["project_id","clip_id"],"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":{"title":"Auto-generate sync points","readOnlyHint":false,"destructiveHint":true,"openWorldHint":false},"definitionHash":"8e2e11a38d13dd1e109b644ab919034da406fa85732c4650cf2d72dab924747a","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-18T11:47:04.042Z","metadataTrust":"untrusted"},{"serverName":"io.clueso/video","endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","name":"captions","title":"Edit captions","description":"Read and edit a clip's CAPTIONS (subtitles) — what they say, where one caption ends and the next begins, when each shows, captions not tied to the voiceover, and translation. Captions are built from the clip's voiceover words: each caption is a run of words, addressed by its `start_word_index`.\n\nStart with action=\"list\" on the clip — it returns `blocks` (voiceover captions: start_word_index, end_word_index, start/end in clip seconds, text, transcript_text, words, edited, retimed, mergeable), `manual_captions` ({caption_id, start, end, text}), `active_language` and `translated_languages`. Then:\n\n- edit (start_word_index, text) — change what ONE caption says on screen. The voiceover audio, its words and timing are untouched; to change what is SPOKEN use voiceover_batch. reset (start_word_index) restores the transcript text.\n- split (start_word_index, split_word_index) — cut a caption in two; split_word_index is the word that STARTS the second caption (block word i = start_word_index + i; not the first word). Edited text, per-caption style and custom timing are divided between the halves — re-check both and edit them if the cut landed badly. merge (start_word_index of the SECOND caption) only undoes a split (`mergeable: true`); other boundaries come from the transcript's sentences and pauses.\n- timing (start_word_index, start_time, end_time) — when one caption shows, in seconds from the START OF THE CLIP. timing_reset returns it to its words' own timing.\n- manual_add (start_time, end_time, text) → caption_id; manual_edit (caption_id, and text and/or start_time/end_time); manual_remove (caption_id). Manual captions have their own text and window — use them on clips with NO voiceover (list returns no blocks there) or to fill a gap. Adding/editing one turns captions on for the clip. They show without word highlighting.\n- translate (language: id like \"fr\" or name like \"French\") — translate caption TEXT (edited and manual captions included) using the workspace's translation rules and glossary (read or change them with translation_glossary). Omit clip_index for every clip. The new language becomes the one shown; earlier languages are kept. The voiceover stays in its language (use set_voice for that). One translation call per clip, so a long project takes a while — do one clip first if only one was asked about.\n- language (language: an already-translated id, or \"original\") — switch which translation is shown, instantly, without re-translating. Omit clip_index for every clip.\n\nRules: a caption lasts at least 0.1s, stays inside the clip, and never overlaps another caption; anything else is REFUSED with the allowed range — read it and retry. While a translation is shown, edit/manual_edit change the translated text and split is refused (switch to \"original\" first). Custom timing is tied to a caption's exact words and stops applying if the voiceover is regenerated.\n\nTo burn captions into an exported video use export_project(captions=true).\n\nConcurrency: clip-scoped mutation (conflict domain: the clip's caption settings) — serialize calls on the SAME clip; different clips run in parallel. translate/language without clip_index touch every clip: run them alone.","inputSchema":{"type":"object","properties":{"project_id":{"type":"string","description":"The project ID"},"action":{"type":"string","enum":["list","edit","reset","split","merge","timing","timing_reset","manual_add","manual_edit","manual_remove","translate","language"],"description":"What to do — see the tool description"},"clip_index":{"description":"The clip. Required for every action except translate/language, where omitting it means every clip.","type":"integer","minimum":0,"maximum":9007199254740991},"start_word_index":{"description":"edit/reset/split/merge/timing/timing_reset — the caption, exactly as list returned it.","type":"integer","minimum":0,"maximum":9007199254740991},"split_word_index":{"description":"split — the word that starts the new second caption.","type":"integer","minimum":1,"maximum":9007199254740991},"text":{"description":"edit / manual_add / manual_edit — the caption text.","type":"string"},"start_time":{"description":"timing / manual_add / manual_edit — seconds from the start of the clip.","type":"number","minimum":0},"end_time":{"description":"timing / manual_add / manual_edit — seconds from the start of the clip.","type":"number","minimum":0},"caption_id":{"description":"manual_edit / manual_remove — from list's manual_captions.","type":"string"},"language":{"description":"translate — language id (\"fr\") or name (\"French\"). language — a translated id, or \"original\".","type":"string"}},"required":["project_id","action"],"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":{"title":"Edit captions","readOnlyHint":false,"destructiveHint":false,"openWorldHint":false},"definitionHash":"7919f687d1ebc43a59a5a5c6ee3003d334891a368f86890e3f30e322dd509b03","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-18T11:47:04.042Z","metadataTrust":"untrusted"},{"serverName":"io.clueso/video","endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","name":"check_uploads","title":"Check upload status","description":"Fetch all files the user uploaded via the hosted upload page. Returns one mcp_upload_id per file — pass each to the appropriate tool (add_clips, add_article_media, etc.). Call this once after the user confirms they are done uploading; the token covers all files they dropped on the page.","inputSchema":{"type":"object","properties":{"upload_token":{"type":"string","description":"The upload_token returned by upload_file(request_hosted_upload: true)"}},"required":["upload_token"],"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":{"title":"Check upload status","readOnlyHint":true,"destructiveHint":false,"openWorldHint":false},"definitionHash":"ab0d76ce082cfa7cdbba79c35c232b17ab0641646c92d070374f779ad944c12e","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-18T11:47:04.042Z","metadataTrust":"untrusted"},{"serverName":"io.clueso/video","endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","name":"create_clueprint","title":"Create clueprint","description":"Create a new clueprint (reusable video template). A clueprint is a structured file directory with design notes, composition rules, and screenshots that can be used to generate videos.\n\nUse human-readable folder categories: design/ (colors, typography, backgrounds, animation), rules/ (composition, voiceover, editing), screenshots/ (rendered clip previews). See the \"Creating Clueprints\" section in the system instructions for the full structure.\n\nIf source_guide_ids are provided, guide data is extracted clip-by-clip into the clueprint (animations and images described, auto-element rules learned; can take minutes). Each non-empty decision list in the reply (animations_pending_mode, logo_animations, images_pending_mode, clips_pending_voiceover_policy, multi_split_summary, slide_count_strategy, the *_by_role groups, discovered_element_types_by_clip_type) is a choice to ask the user, then record with update_clueprint(decisions).\n\nA clueprint is THE FORMAT (layouts, pacing, motion, transitions, voiceover style, music, captions, effects); a project built from it takes its colors, fonts and logos from that project's brand kit. brand_locked: true keeps the clueprint's own colors, fonts and logos for projects in this workspace (for a template made for one brand, e.g. a co-marketing piece).","inputSchema":{"type":"object","properties":{"name":{"type":"string","description":"Name of the clueprint"},"description":{"description":"Description of what this clueprint does","type":"string"},"visibility":{"type":"string","enum":["private","workspace"],"description":"'workspace' shares it with your workspace; 'private' is stored as 'workspace'."},"source_guide_ids":{"description":"IDs of existing projects to extract template data from","type":"array","items":{"type":"string"}},"brand_locked":{"description":"true: projects in this workspace built from this clueprint keep its own colors, fonts and logos instead of their brand kit's. Default false (re-skinned to the project's kit).","type":"boolean"}},"required":["name","visibility"],"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":{"title":"Create clueprint","readOnlyHint":false,"destructiveHint":false,"openWorldHint":false},"definitionHash":"ef7be893e5ab05da489076feead1c21592a07ad402b9d9e10c79758efe386d9b","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-18T11:47:04.042Z","metadataTrust":"untrusted"},{"serverName":"io.clueso/video","endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","name":"create_folder","title":"Create folder","description":"Create a folder in the workspace, optionally inside another folder, to organize projects.\n\nReturns { folder_id, name, parent_folder_id, already_existed }. If a folder with the same name (case-insensitive) already exists in that parent, it is returned with already_existed=true instead of creating a duplicate — so it is safe to call to \"ensure\" a folder exists.\n\nPut projects in it with create_project(folder_id=...) or update_project(project_id, folder_id=...). List existing folders with find(type='folders').","inputSchema":{"type":"object","properties":{"name":{"type":"string","minLength":1,"maxLength":255,"description":"Folder name"},"parent_folder_id":{"description":"Create the folder inside this folder (use find(type='folders') for IDs). Omit for the workspace root.","type":"string"},"description":{"description":"Optional folder description","type":"string","maxLength":500}},"required":["name"],"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":{"title":"Create folder","readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"definitionHash":"71437ee0f228e84b11f7100690420957b288d17edc8c74c6119b080cefdd2446","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-18T11:47:04.042Z","metadataTrust":"untrusted"},{"serverName":"io.clueso/video","endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","name":"create_project","title":"Create project","description":"Create a new blank Clueso project. Returns the projectId and initialClipId — the project starts with one blank clip already at index 0 (default short duration). Use update_clips to resize/retitle clip 0, add_clips(kind='blank') to append more clips, add_elements to place content, and add_audio to attach a project-level music track.\n\nOptionally place the project inside a folder (use find(type='folders') to find folder IDs, or create_folder to make one) and set a description at creation time.\n\nFrom a clueprint: it sets the format (layouts, pacing, motion, voiceover, music, captions) and this project's brand kit the identity (colors, fonts, logos, icons); see get_clueprint's `brand`.\n\nBrand kit: a project follows the workspace's default brand kit unless given one (a workspace with no kit uses none). Pass brand_kit_id (from find(type='brand_kits')) to build this project with that kit, e.g. one project per brand, or 'none' to make it without a brand kit; the reply's brandKit says which kit it uses. Then get_design_guide({project_id, select: [...]}) returns that kit's colors, fonts, logos and guidelines.\n\nStart it voiced (one or the other):\n  • script — one blank clip per paragraph (blank-line separated), each with AI voiceover generated from it; clip lengths follow the speech (generation runs in the background, ~seconds per clip). Returns clip_ids.\n  • audio — an audio upload (an mcp_upload_id or a Clueso upload_id): it becomes clip 0's voiceover as the original narration, transcribed (script + captions), and the clip takes its length. Returns duration and word_count.","inputSchema":{"type":"object","properties":{"title":{"description":"Project title","type":"string"},"folder_id":{"description":"Optional folder ID to nest the project under. Use find(type='folders') to discover IDs. Omit to create at workspace root.","type":"string"},"description":{"description":"Optional project description (max ~500 chars)","type":"string"},"brand_kit_id":{"description":"Brand kit for this project: an id from find(type='brand_kits'), 'default' (the same as omitting it: follow the workspace default kit), or 'none' for no brand kit. Setting a kit needs an editor or admin.","type":"string"},"script":{"description":"Voiceover script; one blank clip per paragraph. Not with `audio`.","type":"string"},"audio":{"description":"An audio upload (an mcp_upload_id or a Clueso upload_id) to use as the voiceover (original narration, transcribed). Not with `script`.","type":"string"}},"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":{"title":"Create project","readOnlyHint":false,"destructiveHint":false,"openWorldHint":false},"definitionHash":"637da15aba7247c6cfa145731eb3384c5f32a0a3920f1161adba4dc477c3d389","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-18T11:47:04.042Z","metadataTrust":"untrusted"},{"serverName":"io.clueso/video","endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","name":"duplicate_clip","title":"Duplicate a clip","description":"Clone one clip — within the same project, or **from another project** — into a target project.\n\n- Same project: pass `target_project_id` and `source_clip_id` (omit `source_project_id`).\n- Cross-project: pass `target_project_id`, `source_project_id`, `source_clip_id`. The source clip's S3 assets (voiceover audio, original video footage, generated video, etc.) are re-hosted into the target guide's S3 namespace, so the new clip is independent of the source — deleting the source project later won't break it.\n\nInsertion: pass `after_clip_id` to place immediately after a specific clip in the target. Omit to append at end.\n\nReturns the new clip_id and its final index. Concurrency: whole-project mutation (conflict domain: the entire target project) — serialize; do not run in parallel with any other mutation on the same target_project_id.","inputSchema":{"type":"object","properties":{"target_project_id":{"type":"string","description":"Project (guide) ID to insert the duplicate into."},"source_clip_id":{"type":"string","description":"ID of the clip to duplicate."},"source_project_id":{"description":"Cross-project mode: ID of the project the source clip lives in. Omit for same-project duplication.","type":"string"},"after_clip_id":{"description":"Insert after this clip ID in the target. Appends at end if omitted.","type":"string"}},"required":["target_project_id","source_clip_id"],"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":{"title":"Duplicate a clip","readOnlyHint":false,"destructiveHint":false,"openWorldHint":false},"definitionHash":"627c62bb5b7dbf83e791d90f3d1b295a2d16290a5e52826ab456d50fd448c07a","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-18T11:47:04.042Z","metadataTrust":"untrusted"},{"serverName":"io.clueso/video","endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","name":"duplicate_project","title":"Duplicate project","description":"Clone an entire project — every clip, voiceover, asset, and metadata field — into a fresh project. The copy has its own S3 namespace, so changes or deletions to the source never affect the duplicate.\n\nDefaults:\n- new_title omitted → \"{source title} (copy)\" when no folder_id is given (or it's empty) and the source stays in the same org; pass an explicit non-empty folder_id and the title is preserved.\n- folder_id omitted → copy lives in the same folder as the source.\n\nA copy's export costs the workspace's export minutes in full, while re-exporting the same project only costs what it grew by: to make versions of one video, keep editing the one project rather than duplicating it per version.\n\nReturns the new project's id and title. Concurrency: whole-project read+create — serialize against other mutations on the same source_project_id; do not run them in parallel.","inputSchema":{"type":"object","properties":{"source_project_id":{"type":"string","description":"Project (guide) ID to duplicate."},"new_title":{"description":"Override the title of the duplicate.","type":"string"},"folder_id":{"description":"Place the duplicate in this folder. Omit to keep the same folder as the source. Pass '' (empty string) to move to workspace root.","type":"string"}},"required":["source_project_id"],"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":{"title":"Duplicate project","readOnlyHint":false,"destructiveHint":false,"openWorldHint":false},"definitionHash":"5c2912e16ace0d2710dd7b96e9a6ea2d4bee25753ef03dfc9440833c7564af24","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-18T11:47:04.042Z","metadataTrust":"untrusted"},{"serverName":"io.clueso/video","endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","name":"edit_animation","title":"Edit an HTML animation","description":"Change an HTML animation's site: ONE revision, linted, checked and probed. A passing save with project_id moves that project's uses; a failing one is kept but moves nothing; your next edit continues from it. Saves return a contact sheet (preview: false skips it); preview: true | {filmstrip, video, test} renders the moved element in place (dry run: unsaved page).\n\nSend changes against your copy (server can't read your disk; no read first):\n  patch: '<git diff or diff -ruN of your copy>'   any number of files\n  files: [{path, edits: [{old, new, replace_all?}]}] · {path, content} · {path, patch} · {path, upload_id}\n  upload_ids: [...]   from upload_file(file_names) + one curl; names are paths (media ≤200 MB too, linked relatively: media/clip.mp4)\n  edits: [{op: delete|move, path, to?}]\nA hunk or edit that doesn't match saves nothing (the reply shows the lines around it).\n\nRead get_design_guide({topic: \"pages\"}) before writing or editing a page: the timing, scope, determinism and checking rules.\nRules: timing from cues, not voiceover words; sound: add_audio, not in-page; save to the project (library only when asked, then say where); one page per scene, split for own timing; a backdrop that runs on across clips reads window.__frame.filmTime (film seconds), not time.\n\nReply: rev, probe (passing|failing|pending), checks/errors ({path, line, column, code, message}), files_changed, uses_moved, note; detail 'full' adds hunks. dry_run: true saves nothing (a preview token). animation: 'new' creates one (name, scope).\n\nplace: {clip_index | continue_from: <element_id>, x/y/width/height?, start_time/end_time?, entry?, name?} → on that clip after a passing save: placed + element_id. No changes: the site as it is. checkpoint: '<name>' keeps a state as a version.\n\nRefusals: stale_base, check_failed, breaking_unconfirmed (confirm_breaking: true). Edits change only this project's copy. Placed elements' parameters, actions, cues: update_elements.\nA canvas Mograph becomes a page first (reply: upgraded; code in index.html).","inputSchema":{"type":"object","properties":{"project_id":{"description":"The project: a passing save moves its uses (one undo step).","type":"string"},"element_id":{"description":"The element whose page to edit (from the version it shows); a canvas Mograph is upgraded to a page first. Needs project_id.","type":"string"},"animation":{"description":"The site to edit when there is no element; 'new' makes one (name, scope).","type":"string","minLength":1},"scope":{"description":"animation 'new' only: 'project' (default with project_id), 'element' (with for_element), or 'library' ONLY when the user asks to keep it for other videos.","type":"string","enum":["element","project","library"]},"name":{"description":"animation 'new': its name.","type":"string"},"slug":{"description":"animation 'new': its site name (a-z, 0-9, -).","type":"string"},"folder":{"description":"animation 'new' with scope 'library': folder path, e.g. 'Brand/Intros'.","type":"string"},"for_element":{"description":"animation 'new' with scope 'element'.","type":"string"},"base_rev":{"description":"The revision you read; a save made since is refused (stale_base).","type":"integer","minimum":1,"maximum":9007199254740991},"confirm_breaking":{"description":"Move this project's uses even when the new version drops something they use (a removed or retyped parameter, action, cue or page, a new size); without it such a save moves nothing and lists `breaking`.","type":"boolean"},"patch":{"description":"A unified diff of any number of files (git diff / diff -ruN), from the site folder.","type":"string","minLength":1},"files":{"description":"Per-file changes: exactly one of edits, content, patch or upload_id each.","minItems":1,"maxItems":100,"type":"array","items":{"type":"object","properties":{"path":{"type":"string","minLength":1,"description":"File path in the site, e.g. 'index.html'."},"edits":{"description":"Exact-match replaces, applied in order.","minItems":1,"maxItems":100,"type":"array","items":{"type":"object","properties":{"old":{"type":"string","minLength":1,"description":"Exact text to find (without the 'N| ' numbers); must occur once unless replace_all."},"new":{"type":"string","description":"The text to put in its place."},"replace_all":{"description":"Replace every occurrence.","type":"boolean"}},"required":["old","new"]}},"content":{"description":"The whole file (new file or rewrite).","type":"string"},"patch":{"description":"A unified diff of this one file.","type":"string"},"upload_id":{"description":"A file sent with upload_file: text is used as the whole content (UTF-8, at most 2 MB); media (video, audio, image, font, model) is added as is (at most 200 MB).","type":"string","pattern":"^mup_"}},"required":["path"]}},"upload_ids":{"description":"Whole files sent with upload_file(file_names); each upload's name is its path.","minItems":1,"maxItems":100,"type":"array","items":{"type":"string","pattern":"^mup_"}},"edits":{"description":"Ops applied first: delete and move (replace and write work too).","minItems":1,"maxItems":100,"type":"array","items":{"type":"object","properties":{"op":{"type":"string","enum":["replace","write","delete","move"]},"path":{"type":"string","minLength":1},"old":{"type":"string"},"new":{"type":"string"},"all":{"type":"boolean"},"content":{"type":"string"},"to":{"description":"move: the new path.","type":"string"}},"required":["op","path"]}},"dry_run":{"description":"Check without saving; returns a preview token for get_clip render.preview.","type":"boolean"},"probe":{"description":"With dry_run: also render it in the probe (slower; returns its contact sheet).","type":"boolean"},"detail":{"description":"'full' adds the diff hunks and thumbnail records.","type":"string","enum":["summary","full"]},"preview":{"description":"Omitted: the probe's contact sheet (the page at its defaults). true: render what the save produced IN PLACE -- the element it moved (a dry run: its unsaved page), cropped, at four moments. {filmstrip, video, test, element_id}: the same as a filmstrip, with a short MP4 link, or with test settings. false: no image.","anyOf":[{"type":"boolean"},{"type":"object","properties":{"filmstrip":{"anyOf":[{"type":"boolean","const":true},{"type":"object","properties":{"from":{"description":"Window start, element-local seconds, or clip seconds for a whole clip (default 0).","type":"number","minimum":0},"to":{"description":"Window end, element-local seconds, or clip seconds for a whole clip (default the end).","type":"number","exclusiveMinimum":0},"around":{"description":"Center the window on a cue ('cue:land') or an action clip ('action:hop', by name or id) instead of from/to. On a whole clip, a cue several animations share is 'cue:land@<element name>'.","type":"string","pattern":"^(cue|action):.+"},"span":{"description":"With around: the window's length in seconds (default 2 around a cue; the clip plus 0.5 around an action).","type":"number","exclusiveMinimum":0},"frames":{"description":"How many frames across the window, first and last included (default 12, max 16).","type":"integer","minimum":2,"maximum":16},"fps":{"description":"Frames per second instead of a count, e.g. 8 over 2 s is 17, capped at 16.","type":"number","exclusiveMinimum":0,"maximum":60},"seam":{"description":"get_clip of a whole clip only: the cut from this clip into the next, as the player shows it: this clip's last second, its transition, and the next clip's first second, in this clip's seconds; takes frames, no window. Every cut of the film at once: get_project({render: {seams: true}}).","type":"boolean","const":true}},"additionalProperties":false}],"description":"Motion in ONE image: evenly spaced labelled frames (default 12 over the whole animation) with a timeline of cues (lines) and action clips (bars): judge pacing, easing, beats on cues. true, or {from, to} / {around, span}, with frames or fps. Replaces timestamps. get_clip without element_id/preview: the whole clip in clip seconds, ticks for each element's start/end. HTML animations are drawn from their pages, the next clip's across a seam included."},"video":{"description":"For people: a low-res MP4 of the same window (filmstrip's, else first 10 s) as video_url (1 h link). You can't watch it: judge from the filmstrip.","type":"boolean"},"test":{"type":"object","properties":{"parameter_values":{"description":"Values to try, over the element's own (an image or video value: a URL or upload).","type":"object","propertyNames":{"type":"string"},"additionalProperties":{}},"param_tracks":{"description":"Keyframes to try for animatable parameters: {key: [{t, value, interpolation?}]}.","type":"object","propertyNames":{"type":"string"},"additionalProperties":{"minItems":1,"type":"array","items":{"type":"object","properties":{"t":{"type":"number","minimum":0,"description":"Element-local (page) seconds."},"value":{},"interpolation":{"type":"string"}},"required":["t","value"],"additionalProperties":{}}}},"actions":{"description":"Action clips to try instead of the element's: [{name, start, duration?, args?}].","type":"array","items":{"type":"object","properties":{"name":{"type":"string","minLength":1},"start":{"type":"number","minimum":0},"duration":{"type":"number","exclusiveMinimum":0},"args":{"type":"object","propertyNames":{"type":"string"},"additionalProperties":{}}},"required":["name","start"],"additionalProperties":false}},"cues":{"description":"Cue times to try: {key: seconds}.","type":"object","propertyNames":{"type":"string"},"additionalProperties":{"type":"number","minimum":0}}},"additionalProperties":false,"description":"Try other settings on the one animation rendered (element_id or preview), nothing saved; element-local (page) seconds. Check a value or cue before setting it with update_elements."},"element_id":{"description":"Which use to render when the save moved several (default the first).","type":"string","minLength":1}},"additionalProperties":false}]},"request":{"description":"One line: what the user asked for (history).","type":"string"},"checkpoint":{"description":"A name for a state worth keeping (e.g. 'v1 layout'): labels the saved revision and adds it as a version to the animation's Generations history, where the user can find and restore it.","type":"string","minLength":1,"maxLength":80},"place":{"description":"Put the saved page on a clip in this call (after a passing save): returns element_id. Needs project_id. Without file changes: places the site as it is.","type":"object","properties":{"clip_index":{"description":"The clip, 0-based.","type":"integer","minimum":0,"maximum":9007199254740991},"clip_id":{"description":"Or the clip by id.","type":"string","minLength":1},"x":{"description":"Canvas px; default 0.","type":"number"},"y":{"description":"Canvas px; default 0.","type":"number"},"width":{"description":"Canvas px; default full frame.","type":"number","exclusiveMinimum":0},"height":{"description":"Canvas px; default full frame.","type":"number","exclusiveMinimum":0},"start_time":{"description":"Clip seconds; default 0.","type":"number","minimum":0},"end_time":{"description":"Clip seconds; default the page's duration.","type":"number","exclusiveMinimum":0},"entry":{"description":"Another page of the site, e.g. 'outro.html'.","type":"string","minLength":1},"name":{"description":"The element's label in the editor (default: the site's name, or site/entry).","type":"string","minLength":1},"continue_from":{"description":"An animation element of an earlier clip: carry it on into the next clip (or clip_index) from where it stopped, with its box, values and timeline.","type":"string","minLength":1}},"additionalProperties":false},"wait_s":{"description":"How long to wait for the probe's verdict (default the server's).","type":"number","minimum":0,"maximum":170}},"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":{"title":"Edit an HTML animation","readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false},"definitionHash":"ed3110ad6841e826dfeff1ebc259ef726f8b42259e57c03134653685765297d5","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-18T11:47:04.042Z","metadataTrust":"untrusted"},{"serverName":"io.clueso/video","endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","name":"export_project","title":"Export project","description":"Export the project as a video. Exports spend the workspace's export minutes\n(the user's paid allowance), so only export when the user asked for one, never as a\nstep of your own (to get audio or a merged file, say).\n\nTwo calls. The first starts nothing: it returns what the export costs, the minutes\nleft, and a confirm_token. Tell the user the cost and ask; once they say yes, call\nagain with the same arguments plus confirm_token. Re-exporting a project that hasn't\ngrown costs nothing and starts on the first call. Cost is per project: a duplicate\nexports at its full length.\n\nOnce started it returns an export_id; the export renders in the background (~5 min)\nand the user gets the result in the editor's Exports tab. Start it, tell the user it has started (with the export_id), and\nstop: do not call get_export in a loop or hold run_script open waiting for it. Call\nget_export only when the user asks for the link (it then returns download_url, or\nembed_url for destination=\"embed\").\n\ndestination:\n  • \"download\" (default) — an mp4 file; once done, get_export returns a time-limited download_url.\n  • \"embed\" — publish the project as an embeddable video player (the same embed the\n    editor's Share → Embed creates). The embed URL is permanent: re-publishing after\n    edits updates the video behind the SAME URL, so pages and LMS lessons that embed it\n    update in place. Use get_embed(project_id) to read the URL and iframe code of an\n    already-published project without re-rendering.\n\nformat:\n  • \"mp4\" (default) — the video.\n  • \"mp3\" — the project's whole soundtrack as one MP3: voiceover, music, extracted\n    audio and video audio, mixed as the video plays them. Billed like a video export.\n    Download only; resolution, fps and captions are ignored. There is no voiceover-only\n    file: to leave music or video audio out, mute or remove it first.\n\nDefaults: 1080p / 30fps / no captions / English. Pass overrides only when needed; a resolution or fps above the workspace's plan is capped to it.\nRefused while a job (speech, sync, the build) still holds the project, since the render would catch it mid-change: export once they finish.\n`captions` burns subtitles into a download; an embed instead carries captions the\nviewer toggles in the player, so `captions` is ignored for destination=\"embed\".","inputSchema":{"type":"object","properties":{"project_id":{"type":"string","description":"The project ID to export"},"resolution":{"description":"Output resolution (default 1080p)","type":"string","enum":["720p","1080p","2k","4k"]},"fps":{"description":"Frames per second (default 30)","anyOf":[{"type":"number","const":24},{"type":"number","const":30},{"type":"number","const":60}]},"captions":{"description":"Burn subtitles into the video (default false)","type":"boolean"},"format":{"description":"\"mp4\" (video, default) or \"mp3\" (the whole soundtrack, no picture; download only)","type":"string","enum":["mp4","mp3"]},"language":{"description":"Language code of the voiceover and captions to render, e.g. 'de' for a translated project (default 'en'). Downloads only.","type":"string","minLength":2},"destination":{"description":"Where the render goes: \"download\" (mp4 file, default) or \"embed\" (publish/update the project's embeddable player; its URL never changes). Publishing an embed needs an editor or admin role.","type":"string","enum":["download","embed"]},"confirm_token":{"description":"The confirm_token the first call returned, passed only after the user agreed to the cost. Omit on the first call.","type":"string"}},"required":["project_id"],"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":{"title":"Export project","readOnlyHint":false,"destructiveHint":true,"openWorldHint":true},"definitionHash":"645f9966eedab35a21dbb8f44c6aa0a3e18a54cc0793b11b96aa074ee62bfd7c","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-18T11:47:04.042Z","metadataTrust":"untrusted"},{"serverName":"io.clueso/video","endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","name":"extract_audio","title":"Extract a clip's audio onto its own layer","description":"The editor's \"Extract Audio\": a clip's own audio — the recording's sound on a video clip, or its generated voiceover — becomes a separate audio track (returns music_id), and the clip goes silent.\n\n- The track starts where the clip starts and plays at normal speed. Shape it with update_audio (trim music_start_time / music_end_time, move guide_start_time, fade, volume); analyze_audio(file_url=<its src from get_project.audio_tracks>) reads it.\n- The track stays in sync through later edits — yours, and voiceover landing on other clips: clips before it moving or resizing, and cuts inside it (split_clip + remove_clip of a part re-cuts the track to what's left; removing a middle part splits it in two). Removing every clip it played under leaves the track where it was; a track you moved or trimmed out of sync stays where you put it.\n- While extracted, the clip's voiceover is locked: voiceover_batch skips it, and an update_clips voiceover_volume on it is not applied (that entry comes back as an error).\n- restore: true gives the clip its own audio back at 100%. The extracted track stays — remove it with remove_from_project(target='audio') if unwanted.\n\nKeep-the-audio, swap-the-visual (e.g. a webinar segment over stock footage):\n1. Cut the recording to the segment(s) with split_clip + remove_clip (before or after extracting).\n2. extract_audio on the clip(s).\n3. Cover, don't delete: add_elements a full-canvas, fully opaque visual on that clip for its whole duration — a stock video (find) with volume 0, an image, or a background shape + text. The recording keeps playing underneath unseen, and the clip's captions still follow the extracted audio's words.\n\nErrors if the clip is already extracted, has no audio (a slide with no generated voiceover), or speech is generating on it.\n\nConcurrency: whole-project mutation — serialize; do not run in parallel with other mutations on the same project_id.","inputSchema":{"type":"object","properties":{"project_id":{"type":"string","description":"The project ID"},"clip_index":{"description":"Zero-based clip index. Ignored if clip_id is provided.","type":"integer","minimum":0,"maximum":9007199254740991},"clip_id":{"description":"Clip ID (preferred over clip_index).","type":"string"},"restore":{"description":"true = undo: the clip plays its own audio again at 100%.","anyOf":[{"type":"boolean"},{"type":"string","enum":["0","1","true","false","yes","no"]}]}},"required":["project_id"],"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":{"title":"Extract a clip's audio onto its own layer","readOnlyHint":false,"destructiveHint":false,"openWorldHint":false},"definitionHash":"9f7ce35a9a51eab607b904c6bcfbc6f2c8193a9a15598a83987056fdb425b5de","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-18T11:47:04.042Z","metadataTrust":"untrusted"},{"serverName":"io.clueso/video","endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","name":"find","title":"Find resources","description":"Find any resource by `type`; filter by `query` (name substring unless noted) or exact `id`. Returns {type, count, items: [{id, name, type, ...}]} (+ total, has_more for projects/folders); pass ids straight to the consuming tool. Any `duration` is in SECONDS (= add_audio source_duration).\n\n- projects | folders | workspaces | backgrounds.\n- tags: project tags (color, project_count; apply with update_project). Project rows carry `tags`; filter with tags + tag_match.\n- clueprints: `query` = relevance search over workspace + community (search_summary, relevance_reason, tags, is_community, fork_count). Cut at `limit` with no marker: page through.\n- clip_templates: one-clip intro/outro/chapter covers (a clueprint is a whole video). Reply in sections: `defaults` {intro, outro}, `folders` + `templates` (workspace), `library_templates` (Clueso's, unnamed: use template_id). Insert: add_clips(kind='template').\n- voices: choose on `description` (tone, age, accent, use); `tags` is a small closed vocabulary. `query` matches names only (descriptive words go in `tags`); query/tags also search the shared catalog (row source org|catalog), else workspace voices only. saved: true = workspace picks; custom: true = clones. Voiceover is the clock: regenerating it later rescales the clip, element times and keyframes.\n- images | videos | music | sfx: row `source` org (saved media) | stock (a short described shortlist; use its `src`). Stock video: use `safe_src` (or the `recommended` video_files tier); tiers above 1080p can exceed add_elements' ~200MB cap. Freesound `src` is an OPAQUE handle: pass it to add_audio as is; detail:'full' adds preview_url. Music/sfx: `query` = 2-5 words for how it SOUNDS (\"warm acoustic upbeat\", \"fast air whoosh\"), never the video's topic; other filters only for what the brief says; under voiceover vocals:false. Choose on returned labels (mood, genre, energy 1-5, vocals none|wordless|lyrics, sfx_type, bpm) + description, never the name.\n- brand_kits: default first (is_default, source_domain, accent, title_font, logo_count (real logos; generated = sample_logo_count), icon_library, updated_at, edit_url). Nothing implicit: pass the id as brand_kit_id to get_design_guide / create_project / update_project. detail:'full' = the whole kit (palette by role, logos, fonts with their font_setting, icons, captions, voices, guidelines, knowledge, reference images).\n- icons: names in the kit's icon set for `query`, drawn the kit's way, pinned ones first; kit = project_id's (built-in set if none) or brand_kit_id's. A kit with its own uploaded icons: use those first (get_design_guide 'brand.icons'). Reply carries `usage` (how to draw one). One set + style per video: missing icon → search again with other words, never switch sets. detail:'full' adds each `src` (SVG in kit color, for an add_elements image).\n- fonts: this workspace's uploaded brand fonts (id, name; add with upload_file purpose:'font'). Pass `name` as font_setting.font. The ONLY list of non-Google families: a family in neither this list nor Google Fonts silently renders Inter (layout then measures the wrong face).\n- animations: the project's own first (project_id; a query searches every project's). kind: 'page' = HTML animations (row `id` = the `animation` for edit_animation / animation.place; title, site, scope, tier, rev, probe, uses, entries). kind: 'canvas' = older canvas kits (ref, title, entries, scope, rev, uses): place as is with add_elements(element_type='animation', type_data: {animation: ref, entry}); editing converts it to a page. Read with read_animation.\n- image_gen_style_packs: presets for generate_media(kind='image') style_id (`ready`). code_style_packs = looks for animation code (`examples` count); `id` + `query` (what you'll animate) returns its style_prompt + closest examples whole.\n- element_components: this workspace's saved components (param_keys). Insert as is: add_elements(component_id); a variant: base_component_id.\n- avatars: looks for an add_elements avatar (type_data.avatarId). No query = one default look per character; query matches character/look names. Rows: styles, engine, credits_per_minute, preview_image.","inputSchema":{"type":"object","properties":{"type":{"type":"string","enum":["projects","folders","tags","clueprints","workspaces","backgrounds","voices","fonts","brand_kits","icons","image_gen_style_packs","code_style_packs","element_components","animations","avatars","images","videos","music","sfx","clip_templates"],"description":"Resource type to find."},"query":{"description":"Name substring (case-insensitive). Stock media: the search phrase. Clueprints: relevance search.","type":"string"},"id":{"description":"Exact id: just that record (music/sfx: a stock id or src).","type":"string"},"folder_id":{"description":"projects/images/videos/music/clip_templates: restrict to a folder; projects: 'root' = outside every folder.","type":"string"},"source":{"description":"Media: 'org' (saved media) | 'stock' | 'all' (default; stock added only with a query). sfx: stock only. clip_templates: 'defaults' | 'org' | 'library' | 'all'. voices: 'saved' | 'own' (saved + custom; neither searches the catalog).","type":"string","enum":["org","stock","all","defaults","library","saved","own"]},"clip_label":{"description":"clip_templates only: one kind of cover.","type":"string","enum":["intro","outro","chapter break","others"]},"engine":{"description":"voices only: 'eleven' | 'cartesia' | 'google'.","type":"string"},"language":{"description":"voices only: e.g. 'en'.","type":"string"},"tags":{"description":"voices: descriptive words ('calm', 'british', 'narration'; list or comma-separated), any one matches. projects: tag names, ignoring case (see tag_match).","anyOf":[{"maxItems":50,"type":"array","items":{"type":"string","minLength":1,"maxLength":40}},{"type":"string"}]},"creator_id":{"description":"clueprints only: filter by creator id.","type":"string"},"mine_only":{"description":"clueprints only: only ones I created.","type":"boolean"},"orientation":{"description":"stock images/videos only: result orientation.","type":"string","enum":["landscape","portrait","square"]},"color":{"description":"stock images only: color name or hex, e.g. 'blue'.","type":"string"},"size":{"description":"stock videos only: minimum resolution bucket.","type":"string","enum":["large","medium","small"]},"min_duration":{"description":"stock videos only: minimum clip length in seconds.","type":"integer","minimum":0,"maximum":9007199254740991},"max_duration":{"description":"stock videos + freesound audio: maximum clip length in seconds.","type":"integer","minimum":0,"maximum":9007199254740991},"provider":{"description":"Stock library, one per call. images/videos: 'pexels' (default; realistic) | 'pixabay' (illustration, vector, clip-art, motion graphics; set image_type/video_type). music: 'clueso' (default; curated, best search) | 'freesound' (niche). sfx: 'freesound' (default) | 'clueso'. Offering the user options → search both in parallel, offer the best 3-5; picking yourself → clueso first.","type":"string","enum":["pexels","pixabay","clueso","freesound"]},"image_type":{"description":"Pixabay images: illustration/vector for graphic looks (flat, icons, clip-art); photo (or Pexels) for realism.","type":"string","enum":["photo","illustration","vector"]},"video_type":{"description":"Pixabay videos: 'film' (live footage) | 'animation' (motion graphics).","type":"string","enum":["film","animation"]},"tier":{"description":"animations: 'org' (workspace) | 'official' (Clueso's) | 'community'; default all.","type":"string","enum":["org","official","community"]},"project_id":{"description":"animations: this project's own, listed first. icons: this project's brand kit's set.","type":"string"},"brand_kit_id":{"description":"icons: this brand kit's set (find(type='brand_kits')) instead of the project's.","type":"string"},"library":{"description":"icons: another set id ('lucide', 'ph', 'tabler', ...); only for a video using no other set.","type":"string"},"tag_match":{"description":"projects with tags: 'any' (default) | 'all'. An unknown name matches nothing.","type":"string","enum":["any","all"]},"mood":{"description":"music/sfx: rank first (misses not hidden).","maxItems":3,"type":"array","items":{"type":"string","enum":["uplifting","hopeful","happy","playful","quirky","confident","inspiring","epic","energetic","laid-back","calm","dreamy","warm","sentimental","focused","serious","mysterious","suspenseful","dark","sad"]}},"genre":{"description":"music: rank first.","maxItems":3,"type":"array","items":{"type":"string","enum":["corporate","electronic","pop","rock","indie","hip-hop","lo-fi","house","funk","rnb","jazz","acoustic-folk","ambient","cinematic","classical","world"]}},"energy":{"description":"music: 1 still, 2 gentle, 3 steady, 4 driving, 5 intense; ranks.","type":"integer","minimum":1,"maximum":5},"vocals":{"description":"music: false = instrumental only, true = with vocals.","anyOf":[{"type":"boolean"},{"type":"string","enum":["0","1","true","false","yes","no"]}]},"bpm_min":{"description":"music: tempo floor.","type":"integer","minimum":1,"maximum":400},"bpm_max":{"description":"music: tempo ceiling.","type":"integer","minimum":1,"maximum":400},"avoid":{"description":"music/sfx: exclude (unlabelled tracks pass).","maxItems":6,"type":"array","items":{"type":"string","enum":["uplifting","hopeful","happy","playful","quirky","confident","inspiring","epic","energetic","laid-back","calm","dreamy","warm","sentimental","focused","serious","mysterious","suspenseful","dark","sad","corporate","electronic","pop","rock","indie","hip-hop","lo-fi","house","funk","rnb","jazz","acoustic-folk","ambient","cinematic","classical","world"]}},"sfx_type":{"description":"sfx: the kind of effect.","type":"string","enum":["whoosh","riser","impact","sub-drop","click","pop","typing","swipe","notification","success","error","glitch","shimmer","camera-shutter","ambience"]},"similar_to":{"description":"music/sfx: an earlier result's id (or a Freesound src, not a clueso src) → sounds like it, instead of text search (e.g. a rejected pick). No other filters.","type":"string"},"detail":{"description":"voices, music, sfx, fonts, brand_kits, icons: 'compact' (default; what you need to choose and use one) | 'full' (every field: preview urls, thumbnails, attribution, rhythm, full descriptions; whole brand kits; icon src).","type":"string","enum":["compact","full"]},"page":{"description":"Page (default 1) — projects/element_components/clueprints.","type":"integer","minimum":1,"maximum":9007199254740991},"limit":{"description":"Page size; caps every type, stock media included (default 8 for voices, music, sfx; every font for fonts; 50 otherwise). A '_more' item or note says when more exist.","type":"integer","minimum":1,"maximum":100}},"required":["type"],"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":{"title":"Find resources","readOnlyHint":true,"destructiveHint":false,"openWorldHint":true},"definitionHash":"a226bb53bd61d162f5886b7f4b13b6a1d0c94f4c21bb6f6bada5a7facfe9ce90","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-18T11:47:04.042Z","metadataTrust":"untrusted"},{"serverName":"io.clueso/video","endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","name":"generate_media","title":"Generate AI media (image or animation)","description":"Generate an AI image or a canvas-code-based animation directly into a clip.\n\n- kind=\"image\": text-to-image. Pass `prompt`. Optional: `animation_setting` (entry/exit — set it HERE, see below), `style_id` (from find type='image_gen_style_packs'), `reference_image_url` or `mcp_upload_id` for image-to-image grounding.\n\n- kind=\"animation\": canvas-code animation rendered from a prompt. Pass `prompt`. Optional: `voiceover_text` (drives timing), `base_component_id` (reuse a saved animation as the starting point), `reference_image_url` or `mcp_upload_id` for visual grounding.\n\nGeneration is asynchronous: the element is created immediately with a stable `element_id` and rendered in the background. Poll `get_clip(select:['busy'])`: an EMPTY `busy` means the render has landed. (This previously said to watch the `phantom` flag; `phantom` has never been a key get_clip returns, so there was nothing to poll.)\n\nSet presentation up front. `animation_setting` is applied to the element as it is created, so the image enters correctly the first time it renders. Doing it afterwards with `update_elements` means writing to the element that is still generating, which is the write most likely to be refused while the generation holds it.\n\n`group` is NOT accepted here, unlike `add_elements`: a generated element is built in the background, and the grouping would be overwritten when the render lands. Add it ungrouped, then call `update_elements` with `group` once it appears.\n\nTIMING: images land in seconds; animations take tens of seconds to a few minutes. Poll `get_clip(select:['busy'])` until `busy` is empty. A slow animation is still rendering, not stuck: do not call `generate_media` again for it, because each call is a new generation and uses credits again.\n\nTip: use this tool whenever the user asks for a \"generated\", \"AI\", or \"create me a\" visual. For uploaded photos / logos / icons / GIFs, use `add_elements` with `element_type='image'` and a `src` or `mcp_upload_id` instead.","inputSchema":{"type":"object","properties":{"kind":{"type":"string","enum":["image","animation"],"description":"'image' = AI text-to-image; 'animation' = canvas-code-based motion graphic."},"project_id":{"type":"string","description":"Project ID."},"clip_id":{"type":"string","description":"Clip ID to place the generated element into."},"prompt":{"type":"string","minLength":1,"description":"Generation prompt. For animations, be SPECIFIC: name the UI elements, interaction sequence, timing feel, and visual style. Vague prompts produce bad output."},"x":{"type":"number","description":"Top-left X in canvas pixels."},"y":{"type":"number","description":"Top-left Y in canvas pixels."},"width":{"type":"number","exclusiveMinimum":0,"description":"Width in pixels."},"height":{"type":"number","exclusiveMinimum":0,"description":"Height in pixels."},"start_time":{"description":"Appear at (seconds).","type":"number","minimum":0},"end_time":{"description":"Disappear at (seconds).","type":"number","minimum":0},"style_id":{"description":"Image only. Style preset ID from find(type='image_gen_style_packs'). See resource clueso://docs/generation-styles.","type":"string"},"model":{"description":"Image only. Default `gemini-3-pro-image` (Nano Banana Pro; usually leave it). Faster/cheaper: `gemini-3.1-flash-image`, `gemini-nano-banana-2.1` (newest), `gemini-3.1-flash-lite-image` (cheapest), `gemini-2.5-flash-image`. `gpt-image-2.5-flare` (fast), `gpt-image-2.5-sunburst` (precise edits), `gpt-image-2` (legible text, several reference images). `gpt-image-1` / `gpt-image-1.5`: square-ish only, a wide box snaps to 4:3 (not for banners).","type":"string","enum":["gemini-3-pro-image","gemini-3.1-flash-image","gemini-nano-banana-2.1","gemini-3.1-flash-lite-image","gemini-2.5-flash-image","gpt-image-2.5-flare","gpt-image-2.5-sunburst","gpt-image-2","gpt-image-1.5","gpt-image-1"]},"background":{"description":"Image only. `false` = transparent cut-out (icons, logos, stickers). Honoured ONLY with `model` set in the same call to `gpt-image-2.5-flare` (default pick), `gpt-image-2.5-sunburst`, `gpt-image-1` or `gpt-image-1.5`; other models are always opaque. Asking for transparency in the prompt paints a checkerboard as real pixels.","anyOf":[{"type":"boolean"},{"type":"string","enum":["0","1","true","false","yes","no"]}]},"aspect_ratio":{"description":"Image only. Overrides the ratio inferred from width/height (usually leave it; set when the box is a placeholder). Clamped per model: gpt-image-1/1.5 only 1:1, 4:3, 3:4; gpt-image-2.5 pair adds 16:9, 9:16; gpt-image-2 has no 3:2 or 2:3 (→ 4:3, 3:4). Not reported back.","type":"string","enum":["1:1","4:3","3:4","16:9","9:16","3:2","2:3"]},"base_component_id":{"description":"Animation only. Reuse a saved animation component as the starting point (from find(type='element_components')). To re-skin its tunable parameters, set parameter_values via update_elements after it renders.","type":"string"},"voiceover_text":{"description":"Animation only. Paces the motion to the spoken script — and as a side effect sets this clip's voiceover text and triggers speech generation for the clip. If the clip's current voiceover_text (get_clip) has <SYNC_MARKER N> tokens, this text must carry each of them once, in order, or the animation is refused.","type":"string"},"reference_image_url":{"description":"Public URL of a reference image. Mutually exclusive with mcp_upload_id.","type":"string"},"mcp_upload_id":{"description":"mcp_upload_id from upload_file, or a Clueso upload_id. Resolved server-side to a presigned URL before generation.","type":"string"},"animation_setting":{"description":"Image only. Entry/exit animation, same shape as add_elements' type_data.animation_setting. The design guide asks AI images to enter with `masked_reveal` or a slow fade, so set it here rather than following up with update_elements — that follow-up targets the element while it is still generating. Ignored for kind='animation', which animates through its generated code.","type":"object","properties":{"entry":{"description":"Entry (appear) animation phase.","type":"object","properties":{"preset":{"description":"Preset for this phase. 'typewriter' is char-only and has no direction.","type":"string","enum":["slide","fade","pop","scale","masked_reveal","typewriter","none"]},"apply_to_unit":{"description":"Granularity. 'typewriter' is restricted to 'char'.","type":"string","enum":["char","word","line","box"]},"duration_per_unit_ms":{"description":"TOTAL phase duration in ms (NOT per unit, despite the name; default 400), split across the N units with ~50% overlap. Per-unit rhythm → scale with the count (typewriter on N chars ≈ N × 100–200 ms).","type":"number","minimum":0},"direction":{"description":"Slide direction for this phase. Ignored by fade/scale/pop/typewriter; pass 'none' when the preset has no direction.","type":"string","enum":["left","right","top","bottom","center_all","center_vertically","center_horizontally","none"]}}},"exit":{"description":"Exit (disappear) animation phase.","type":"object","properties":{"preset":{"description":"Preset for this phase. 'typewriter' is char-only and has no direction.","type":"string","enum":["slide","fade","pop","scale","masked_reveal","typewriter","none"]},"apply_to_unit":{"description":"Granularity. 'typewriter' is restricted to 'char'.","type":"string","enum":["char","word","line","box"]},"duration_per_unit_ms":{"description":"TOTAL phase duration in ms (NOT per unit, despite the name; default 400), split across the N units with ~50% overlap. Per-unit rhythm → scale with the count (typewriter on N chars ≈ N × 100–200 ms).","type":"number","minimum":0},"direction":{"description":"Slide direction for this phase. Ignored by fade/scale/pop/typewriter; pass 'none' when the preset has no direction.","type":"string","enum":["left","right","top","bottom","center_all","center_vertically","center_horizontally","none"]}}}}}},"required":["kind","project_id","clip_id","prompt","x","y","width","height"],"$schema":"https://json-schema.org/draft/2020-12/schema","additionalProperties":{}},"annotations":{"title":"Generate AI media (image or animation)","readOnlyHint":false,"destructiveHint":false,"openWorldHint":false},"definitionHash":"3886cbd9557f52cb25353015412cf9509ee93da1324f156eb23788a7179d314b","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-18T11:47:04.042Z","metadataTrust":"untrusted"},{"serverName":"io.clueso/video","endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","name":"get_article","title":"Get article","description":"Get the article content as markdown. Screenshots appear as <SCREENSHOT {id}> placeholders, and things markdown can't show (an embedded video, a pasted image) as <EMBED {id}> placeholders. Returns the markdown text, a list of screenshot IDs and the article_version to pass to update_article.","inputSchema":{"type":"object","properties":{"project_id":{"type":"string","description":"Project ID"}},"required":["project_id"],"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":{"title":"Get article","readOnlyHint":true,"destructiveHint":false,"openWorldHint":false},"definitionHash":"bc7d3cd08d18f13ae9a009c5051cebbe87c57900bfa263bd6df0a6702aaa91f5","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-18T11:47:04.042Z","metadataTrust":"untrusted"},{"serverName":"io.clueso/video","endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","name":"get_clip","title":"Get clip details","description":"Read one clip: elements (canvas px), voiceover (text, voice, duration, voiceover_volume), background, transition (null if none). Three independent axes:\n- `select` shapes the JSON. Full reads are large (word timings and type_data dominate); ask only for what you need.\n- `element_ids` picks which element rows (e.g. element_ids: ['el_9'], select: ['elements.x','elements.y']).\n- `render` returns a PNG; omit it and nothing renders.\n\nrender cheat sheet:\n  {}                                  → t=0 (entry animations not yet in: check several mid-clip moments instead)\n  {timestamps: [0.5, 2, 4]}           → one labelled grid (~¼ the tokens of separate frames)\n  {element_id: 'e1'}                  → that animation cropped, four moments\n  {element_id: 'e1', test: {cues: {land: 1.2}}} → with other values/timeline, nothing saved\n  {preview: '<token>'}                → an edit_animation dry run, cropped (a site placed nowhere here: alone on the clip)\n  {filmstrip: true}                   → whole clip as 12 frames + a timeline of cues, actions, element starts/ends\n  {save: true}                        → also returns presigned_url\n  select: [] + render: {}             → the PNG alone (default for one animation)\nA render of one animation also returns { warnings } (glow cut at its box, text off its frame, frames near the limits).\n\nElements: id, element_type, name, x, y, width, height, start_time, end_time, rotation + type data (textdata/shapedata/imagedata/videodata/zoomdata/…) + `keyframes` in add_elements' wire shape (round-trips into update_elements). An HTML animation (codedata.version 2) carries `html_mograph`: status + the parameters, actions and cues its page declares (the vocabulary for update_elements param_tracks/actions/cues, e.g. update_elements({updates:[{element_id, type_data:{cues:[{op:'set', key, wordIndex, offset}]}}]})); files via read_animation. An older canvas animation carries `animation`; it plays and exports as is.\n","inputSchema":{"type":"object","properties":{"project_id":{"type":"string","description":"The project ID"},"clip_index":{"type":"integer","minimum":0,"maximum":9007199254740991,"description":"Zero-based clip index"},"render":{"description":"Render a PNG (present = render; `{}` = t=0). Checking work: several mid-clip `timestamps`, not t=0: text and images have ~0.4s entry animations so a correct edit looks empty at t=0 while shapes show. Or `animations: false`.","type":"object","properties":{"timestamps":{"description":"Clip seconds (default 0). Several → one labelled grid (~¼ the tokens); prefer several when checking. A cell is ⅓ width: small print → one number. Max 15; deduped, sorted.","anyOf":[{"type":"number","minimum":0},{"minItems":1,"maxItems":15,"type":"array","items":{"type":"number","minimum":0}}]},"layout":{"description":"Several timestamps: 'sheet' (default, one image) | 'separate' (full-size, ~4x tokens; only when a cell is too small).","type":"string","enum":["sheet","separate"]},"save":{"description":"Also upload the image and return presigned_url (→ update_clueprint files=[{path, source_url}]). One image: not with layout:'separate'.","type":"boolean"},"max_width":{"description":"Returned image width: default 960 (frame), 1280 (whole grid). ~(w×h)/750 tokens; raise only for small print. One animation: the resolution drawn before the crop (sheet cells stay ≤360px; closer → layout:'separate' or a clip frame).","type":"integer","minimum":320,"maximum":1568},"animations":{"description":"Default true (the frame as the video shows it). false: every element settled at its final position and opacity: check COMPOSITION without mid-flight elements looking misplaced.","type":"boolean"},"preview":{"description":"Token from edit_animation(dry_run: true): the unsaved page drawn and cropped like element_id (its element, else one using that site, else the page alone on this clip). Nothing saved.","type":"string","minLength":1},"element_id":{"description":"Only this element over the background, cropped to its box, one small sheet (an HTML animation is drawn from its page, own values and timeline). No timestamps → four moments.","type":"string","minLength":1},"filmstrip":{"anyOf":[{"type":"boolean","const":true},{"type":"object","properties":{"from":{"description":"Window start, element-local seconds, or clip seconds for a whole clip (default 0).","type":"number","minimum":0},"to":{"description":"Window end, element-local seconds, or clip seconds for a whole clip (default the end).","type":"number","exclusiveMinimum":0},"around":{"description":"Center the window on a cue ('cue:land') or an action clip ('action:hop', by name or id) instead of from/to. On a whole clip, a cue several animations share is 'cue:land@<element name>'.","type":"string","pattern":"^(cue|action):.+"},"span":{"description":"With around: the window's length in seconds (default 2 around a cue; the clip plus 0.5 around an action).","type":"number","exclusiveMinimum":0},"frames":{"description":"How many frames across the window, first and last included (default 12, max 16).","type":"integer","minimum":2,"maximum":16},"fps":{"description":"Frames per second instead of a count, e.g. 8 over 2 s is 17, capped at 16.","type":"number","exclusiveMinimum":0,"maximum":60},"seam":{"description":"get_clip of a whole clip only: the cut from this clip into the next, as the player shows it: this clip's last second, its transition, and the next clip's first second, in this clip's seconds; takes frames, no window. Every cut of the film at once: get_project({render: {seams: true}}).","type":"boolean","const":true}},"additionalProperties":false}],"description":"Motion in ONE image: evenly spaced labelled frames (default 12 over the whole animation) with a timeline of cues (lines) and action clips (bars): judge pacing, easing, beats on cues. true, or {from, to} / {around, span}, with frames or fps. Replaces timestamps. get_clip without element_id/preview: the whole clip in clip seconds, ticks for each element's start/end. HTML animations are drawn from their pages, the next clip's across a seam included."},"video":{"description":"For people: a low-res MP4 of the same window (filmstrip's, else first 10 s) as video_url (1 h link). You can't watch it: judge from the filmstrip.","type":"boolean"},"test":{"type":"object","properties":{"parameter_values":{"description":"Values to try, over the element's own (an image or video value: a URL or upload).","type":"object","propertyNames":{"type":"string"},"additionalProperties":{}},"param_tracks":{"description":"Keyframes to try for animatable parameters: {key: [{t, value, interpolation?}]}.","type":"object","propertyNames":{"type":"string"},"additionalProperties":{"minItems":1,"type":"array","items":{"type":"object","properties":{"t":{"type":"number","minimum":0,"description":"Element-local (page) seconds."},"value":{},"interpolation":{"type":"string"}},"required":["t","value"],"additionalProperties":{}}}},"actions":{"description":"Action clips to try instead of the element's: [{name, start, duration?, args?}].","type":"array","items":{"type":"object","properties":{"name":{"type":"string","minLength":1},"start":{"type":"number","minimum":0},"duration":{"type":"number","exclusiveMinimum":0},"args":{"type":"object","propertyNames":{"type":"string"},"additionalProperties":{}}},"required":["name","start"],"additionalProperties":false}},"cues":{"description":"Cue times to try: {key: seconds}.","type":"object","propertyNames":{"type":"string"},"additionalProperties":{"type":"number","minimum":0}}},"additionalProperties":false,"description":"Try other settings on the one animation rendered (element_id or preview), nothing saved; element-local (page) seconds. Check a value or cue before setting it with update_elements."}},"additionalProperties":false},"select":{"description":"JSON to return. Omit = everything; [] = no JSON and requires render (e.g. render:{} for the PNG alone). Without render, name the sections you need, e.g. ['voiceover_words'] or ['elements.name']. Sections (each returns its own key): 'elements' (whole rows); 'voiceover_words' ({word, start, end, punctuated_word}, SECONDS; null without transcription); 'groups' (id, name, parent_id, bounds_px, anchor_px, keyframes; ids for update_groups); 'busy' ([{entity_path, job_type}] still writing: EMPTY = voiceover/AI image landed; non-empty = don't write those yet). 'elements.<key>' keeps just those keys (id always): name, element_type, x, y, width, height, start_time, end_time, rotation, keyframes, textdata, shapedata, imagedata, videodata, zoomdata, codedata, clickaction, questiondata, resultsdata, formdata, avatardata, parent_id, dropShadows, animation; mixed with 'elements' → whole rows. y_top (centre-aligned text only) = the TOP edge; send it back as y with y_anchor:'top'. E.g. ['elements.x','elements.y','elements.width','elements.height'] geometry; ['elements.name','elements.start_time','elements.end_time'] timing; ['elements.textdata','voiceover_words'] copy vs VO.","type":"array","items":{"type":"string","enum":["elements","voiceover_words","groups","busy","geometry","elements.name","elements.element_type","elements.x","elements.y","elements.width","elements.height","elements.start_time","elements.end_time","elements.rotation","elements.keyframes","elements.textdata","elements.shapedata","elements.imagedata","elements.videodata","elements.zoomdata","elements.codedata","elements.clickaction","elements.questiondata","elements.resultsdata","elements.formdata","elements.avatardata","elements.parent_id","elements.dropShadows","elements.animation"]}},"element_ids":{"description":"Which element rows to return ([] = none). Writes already echo resolved layout, so re-reads are often unnecessary.","type":"array","items":{"type":"string"}}},"required":["project_id","clip_index"],"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":{"title":"Get clip details","readOnlyHint":true,"destructiveHint":false,"openWorldHint":false},"definitionHash":"153fd3226242420595ac64638c697e7bcd112b34568fc4516b856717c7b1d181","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-18T11:47:04.042Z","metadataTrust":"untrusted"},{"serverName":"io.clueso/video","endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","name":"get_clueprint","title":"Get clueprint","description":"Fetch clueprint data. Use `include` to control how much you pull back:\n- include=\"metadata\": just the clueprint's name/description/tags/visibility/thumbnail.\n- include=\"tree\": metadata + the full file tree (path, mime_type, and size per entry). Call this first when exploring an unfamiliar clueprint.\n- include=\"files\": the contents of the files listed in `file_paths` (no metadata — call include='tree' first if you also need metadata). Text inline, binary as presigned GET URLs.\n- include=\"all\": metadata + the file tree + the contents of every file in the clueprint (use sparingly on large clueprints).\n\nEvery read is logged for the workspace's recents. Pass use=true ONCE, when you start building a project from it: that counts the use (the clueprint's use count, apply analytics); add project_id when the project already exists.\n\nBuilding from it: Brand kit vs clueprint: the brand kit sets WHO (logos, palette roles, fonts, icons, company facts, brand guidelines); the clueprint sets THE FORMAT (structure and layouts, pacing, motion, transitions, script and voiceover style, music, caption style and animation unless the kit has its own caption style, effects). With both, the kit wins on identity and the clueprint on format; the user's explicit ask beats both. Re-skin the clueprint's literal colors, fonts and logos to the project's kit roles (pick the logo variant by scene background). A community clueprint or another workspace's is always re-skinned, never shipping another company's logo; only this workspace's own clueprint with brand_locked: true keeps its colors, fonts and logos. The reply's `brand` says whether this clueprint is brand_locked for this workspace; pass clueprint_id with project_id to get_design_guide for the kit to re-skin with.","inputSchema":{"type":"object","properties":{"clueprint_id":{"type":"string","description":"ID of the clueprint."},"include":{"default":"tree","description":"What to return: 'metadata' | 'tree' | 'files' | 'all'. Defaults to 'tree'.","type":"string","enum":["metadata","tree","files","all"]},"file_paths":{"description":"include='files' only: relative paths to read (e.g. ['design/colors.md', 'rules/voice.md']). Ignored for other modes.","type":"array","items":{"type":"string","minLength":1}},"use":{"description":"true: you are building a project from this clueprint; counts the use. Once per build.","type":"boolean"},"project_id":{"description":"use=true only: the project being built from it, when it exists.","type":"string"}},"required":["clueprint_id"],"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":{"title":"Get clueprint","readOnlyHint":true,"destructiveHint":false,"openWorldHint":false},"definitionHash":"ee8d2dd41176b5135f3a63fdec980ec2ef0273b722e7afe8466d129ba5d139b7","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-18T11:47:04.042Z","metadataTrust":"untrusted"},{"serverName":"io.clueso/video","endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","name":"get_design_guide","title":"Get design guide","description":"Clueso's design guide, the HTML animation pages guide and the Director's skills. Ask for everything you need in ONE call. Each select entry is a section path or plain words; words search all three and return the best few, each labelled with the path that selects it exactly.\n\n  get_design_guide({select: ['gist', 'styles.kinetic-type', 'motion.*', 'stagger from the centre']})\n\nPaths: 'gist' (the design gist and its contents; also what no arguments returns); design sections ('motion.camera', 'x.*' with its children, '*' for all); 'animation' (the pages guide's core), 'animation.gist', 'animation.<path>' ('animation.craft.seams', 'animation.examples.hero'); 'skills', 'skills.<name>'; the run_script stdlib: 'stdlib' (overview and modules), 'stdlib.anim', 'stdlib.native.tween', 'stdlib:<words>'. One header per entry; anything past the size budget is listed by path for your next call.\ntopic: 'pages' returns the whole guide for writing and editing HTML animation pages (read_animation / edit_animation); with select, only those sections. topic: 'skills' lists the Director's skills, the motion, design and animation craft notes on its computer; pass skill (and path) to read one.\n\nBrand: pass project_id (or brand_kit_id) and the reply starts with a short 'brand' section: the brand kit's palette by role, each font role's exact font_setting, its logos (id, kind, for_background, aspect, url) and its guidelines. Follow it by default. 'brand.<section>' returns one section in full as JSON with its edit link: overview, company (product knowledge), palette, logos, fonts, reference_images, guidelines, icons, captions, voices; 'brand.*' for all. Use an item by reference: a logo → add_elements element_type 'image' with src = that logo's url (match for_background to what is behind it; never recolor); a color role → its hex (palette.accent); a font role → its font_setting. List kits with find(type='brand_kits'); set a project's kit with update_project brand_kit_id. Building from a clueprint: pass its clueprint_id too, and the brand section says which of the two decides what (the kit: identity; the clueprint: format).","inputSchema":{"type":"object","properties":{"topic":{"description":"'design' (default): the house style, shaped by select. 'pages': authoring HTML animation pages. 'skills': the computer's skills, for inspiration.","type":"string","enum":["design","pages","skills"]},"select":{"description":"Everything to return, in one list: section paths and plain words, mixed. 'brand' and 'brand.<section>' read the brand kit.","minItems":1,"maxItems":40,"type":"array","items":{"type":"string","minLength":1,"maxLength":120}},"skill":{"description":"topic 'skills': a skill's name from the list; returns its SKILL.md and its files.","type":"string"},"path":{"description":"topic 'skills' with skill: a file inside it, e.g. 'references/x.md'.","type":"string"},"project_id":{"description":"The project you are designing: adds its brand kit (the project's own, else the workspace default) as the 'brand' section.","type":"string"},"brand_kit_id":{"description":"Read this brand kit (an id from find(type='brand_kits'), or 'default') instead of the project's: for a project on another kit, or a co-branded scene.","type":"string"},"clueprint_id":{"description":"The clueprint this project is built from: the brand section then says what it decides (format) and what the kit decides (identity), and whether it is brand_locked.","type":"string"}},"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":{"title":"Get design guide","readOnlyHint":true,"destructiveHint":false,"openWorldHint":false},"definitionHash":"2bec714a673b8207e5697b187c956c3e225b51de7c86e1bf4afe3c605393a750","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-18T11:47:04.042Z","metadataTrust":"untrusted"},{"serverName":"io.clueso/video","endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","name":"get_element_schema","title":"Get element schema","description":"Return the schema for an element type's type_data, as TypeScript declarations. Call this before add_elements / update_elements when you don't already know the field shape for the element_type you're placing.\n\nBy default it is compact: every field with its type and a one-line note, plus the keyframable list. Ask about specific properties with `fields: ['background_setting']` or `query: 'pill background'` — those come back with their full notes, default and an example; `detail: 'full'` returns everything, including the keyframe rules. Inside run_script it is a function like any tool: get_element_schema({element_type: 'text', query: 'line height'}) looks a property up mid-script.\n\nFields are listed in camelCase, the names get_clip returns. Where the tool descriptions write one in snake_case (font_setting, animation_setting), the field says so — `(= font_setting)` on fontSetting — and either spelling is accepted.\n\nPass element_type='group' for the GROUP surface instead — what a group is, how its pivot works, and the nine properties it can animate.","inputSchema":{"type":"object","properties":{"element_type":{"type":"string","enum":["text","callout","rectangle","arrow","blur","spotlight","zoom","image","video","animation","question","results","form","avatar","draw","group"],"description":"One of: text, callout, rectangle, arrow, blur, spotlight, zoom, image, video, animation, question, results, form, avatar, draw, group"},"mode":{"default":"add","description":"'add' returns required + optional fields; 'update' returns all-optional.","type":"string","enum":["add","update"]},"fields":{"description":"Return only these fields, with their full notes, default and an example — text is 15KB whole, ~300 bytes for two.","type":"array","items":{"type":"string"}},"query":{"description":"Words describing the property you want ('pill background', 'corner radius', 'line height'): returns the best-matching fields (up to 5) as `fields` would.","type":"string","minLength":2,"maxLength":80},"detail":{"description":"'compact' (default): names, types and one-line notes. 'full': every field's full notes, nested docs and the keyframe rules.","type":"string","enum":["compact","full"]},"format":{"description":"Defaults to 'declarations' — TypeScript-style, which is the better READ. Inside run_script it defaults to 'json' instead, because a script indexes into the structure and the declaration text would arrive newline-escaped. Set it explicitly to override either default.","type":"string","enum":["declarations","json"]}},"required":["element_type"],"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":{"title":"Get element schema","readOnlyHint":true,"destructiveHint":false,"openWorldHint":false},"definitionHash":"ef3c8703f7f04d5de8a784ecc540d1d6772faca780df72af86b249dde2fe30a8","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-18T11:47:04.042Z","metadataTrust":"untrusted"},{"serverName":"io.clueso/video","endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","name":"get_embed","title":"Get embed URL","description":"Get a project's embeddable video player: `embed_url` (permanent) and `embed_code` (a ready-to-paste <iframe>, the same snippet the editor's Share → Embed copies). Use it to put a Clueso video in a website, help center or LMS lesson.\n\nReturns { project_id, published, embed_url?, embed_code?, latest_publish? }.\n  • published=false — the project has never been published as an embed. Call export_project(project_id, destination=\"embed\"), tell the user it has started and stop; get_export(export_id) returns the embed_url once it is done and the user asks.\n  • published=true — the URL is live. After editing the project, re-publish with export_project(destination=\"embed\"): the video behind the SAME URL is replaced, so every page embedding it updates without changing the embed code.\n  • latest_publish — the most recent embed publish { export_id, status, progress, requested_at, finished_at }. While it is queued/inprogress, embed_url still serves the previous version.","inputSchema":{"type":"object","properties":{"project_id":{"type":"string","description":"The project ID whose embed to read"}},"required":["project_id"],"$schema":"https://json-schema.org/draft/2020-12/schema"},"annotations":{"title":"Get embed URL","readOnlyHint":true,"destructiveHint":false,"openWorldHint":false},"definitionHash":"8b795a969a92a6c09b9920a792a173991dd4826e7c856a40702db055d505a424","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-18T11:47:04.042Z","metadataTrust":"untrusted"}],"endpoints":[{"endpointFingerprint":"f5cfeb0016b0640f7028937249a89f9059663531ae09544a1d88bed8633cbef8","protocol":"streamable-http","status":"indexed","toolCount":50,"observedAt":"2026-11-18T11:47:04.042Z"}],"authentication":"unknown"},"connectionConfigurations":{"status":"ready","authentication":"not embedded","clients":{"Claude Desktop":{"mcpServers":{"io.clueso/video":{"url":"https://connect.clueso.io/mcp"}}},"Cursor":{"mcpServers":{"io.clueso/video":{"url":"https://connect.clueso.io/mcp"}}},"VS Code":{"servers":{"io.clueso/video":{"type":"http","url":"https://connect.clueso.io/mcp"}}}}},"resourceType":"mcp-server","callable":true,"runtime":{"callable":true,"protocols":["mcp"]},"interfaces":[{"protocol":"mcp","transport":"streamable-http","url":"https://connect.clueso.io/mcp"}],"profile":{"apiVersion":"1","schemaVersion":"1","id":"mcp-server:io.clueso%2Fvideo","resourceType":"mcp-server","canonicalUrl":"https://www.agentsjunction.com/api/v1/servers/io.clueso%2Fvideo","name":"io.clueso/video","description":"Make videos and docs with your AI agent — describe what you need, every output stays editable.","interfaces":[{"protocol":"mcp","transport":"streamable-http","url":"https://connect.clueso.io/mcp"}],"capabilities":[],"identity":{"source":"official-registry","websiteUrl":"https://help.clueso.io/mcp-setup","repositoryUrl":"https://github.com/clueso-ai/clueso-mcp","version":"1.0.2"},"verification":{"state":"official","confidence":100},"operations":{"resourceType":"mcp-server","name":"io.clueso/video","status":"online","lastCheckedAt":"2026-11-20T09:16:04.647Z","lastSuccessfulCheck":"2026-11-20T09:16:04.647Z","latencyMs":240,"consecutiveFailures":0,"isStale":false,"checks":{"endpointReachable":true,"protocolValid":true,"agentCardValid":null,"mcpHandshakeValid":true},"lastSeen":null,"lastSuccessfulInteraction":null,"lastHealthCheck":"2026-11-20T09:16:04.647Z","source":{"type":"health-check","url":null},"observedAt":"2026-11-20T09:16:04.647Z"},"security":null,"timestamps":{"createdAt":"2026-08-19T12:26:06.099Z","updatedAt":"2026-08-19T12:26:06.099Z","observedAt":"2026-11-20T09:16:04.647Z"},"compatibility":{"serverVersion":"1.0.2","protocolVersions":[{"protocol":"mcp","version":null}]}}}}