Categories › Productivity & Office › Notes, docs & knowledge bases
Make videos and docs with your AI agent — describe what you need, every output stays editable.
Remote server: your requests and data go to connect.clueso.io. Claude Code: claude mcp add --transport http clueso https://connect.clueso.io/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
get_design_guide — 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 read_animation — Read an HTML animation's page site (index.html, CSS, JS) like a repository. Read-only. • project_id alone → this project's animations, with edit_animation — Change an HTML animation's site: ONE revision, linted, checked and probed. A passing save with project_id moves that project's uses; a failicreate_project — Create a new blank Clueso project. Returns the projectId and initialClipId — the project starts with one blank clip already at index 0 (defaupdate_project — Update a project's metadata: rename, change description, move to a different folder, or change aspect ratio. Only fields you provide are chaduplicate_project — Clone an entire project — every clip, voiceover, asset, and metadata field — into a fresh project. The copy has its own S3 namespace, so chaexport_project — Export the project as a video. Exports spend the workspace's export minutes (the user's paid allowance), so only export when the user asked get_export — Read a project's video export: its status and, once done, its link. Call it when the user asks for the link or the status, not to wait on anget_media_job — Fetch the outcome of a media job (an article GIF, a frame grab) that did not finish inline: the tool that started it returned { job_id, statget_recording_activity — Status of this workspace's auto-recordings, and how many recording generations this billing cycle has used. The same view as the Recordings get_embed — Get a project's embeddable video player: `embed_url` (permanent) and `embed_code` (a ready-to-paste <iframe>, the same snippet the editor's create_folder — Create a folder in the workspace, optionally inside another folder, to organize projects. Returns { folder_id, name, parent_folder_id, alreafind — Find any resource by `type`; filter by `query` (name substring unless noted) or exact `id`. Returns {type, count, items: [{id, name, type, .switch_workspace — Switch the active workspace. The choice sticks for this client until you change it again — including across reconnects — so every later callget_project — Get a summary of a project: canvas dimensions, per-clip summary (ids, indices, durations, element counts, voiceover_volume), and `audio_tracget_clip — Read one clip: elements (canvas px), voiceover (text, voice, duration, voiceover_volume), background, transition (null if none). Three indepupdate_clips — Update clips in ONE call (always batch): background, transition, duration, title, hidden, position, voiceover_volume, video_styling (video cremove_clip — Remove a clip from the project by index. Cannot remove the last remaining clip. Interactive links to the removed clip are cleared: any buttosplit_clip — Split a video clip into two clips at the given timestamp. The left clip keeps the original clip ID; the right clip gets a new ID and is insecaptions — 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 duplicate_clip — Clone one clip — within the same project, or **from another project** — into a target project. - Same project: pass `target_project_id` and add_clips — Create new clips on a project. One tool, four sources: - kind="blank": empty slide clips you'll populate with add_elements / generate_media.get_element_schema — Return the schema for an element type's type_data, as TypeScript declarations. Call this before add_elements / update_elements when you don'add_elements — 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 shapupdate_elements — Update elements across one or more clips in ONE call (always batch). Items apply in order; partial success ok. clip_index not needed (elemenremove_elements — Remove many elements across one or more clips in a single tool call. One entry per element ({clip_index, element_id}). Concurrency: parallelreorder_elements — Reorder the elements inside a clip. List position IS the z-index — later entries in `ordered_element_ids` render on top of earlier ones. Youupdate_groups — Transform, keyframe, rename, nest or lock GROUPS. A group moves, scales, rotates and fades as ONE unit without touching children's stored poremove_from_project — Remove an element, a group or an audio track from a project. - target="element": removes an element (requires element_id, or element_ids foradd_audio — 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 backgupdate_audio — Mutate fields on an existing music/SFX track by id. Read existing tracks via `get_project.audio_tracks` — the per-entry shape there matches extract_audio — 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 auvoiceover_batch — Set voiceover text and/or generate speech for many clips in ONE call. Per entry: "set_text" (clip_index + text), "generate_speech" (async TTauto_sync — Run the agentic auto-sync pipeline on a clip with a source recording: detects natural sync points (UI changes, narrated steps) and inserts sadd_sync_point — Insert one sync marker on a clip's transcript. Use this when: - The user is explicit about WHERE the camera should pause / cut (e.g. "sync tupload_file — Upload files to Clueso. Pick a mode by client and where the file lives: - `files` (ChatGPT only): the user's attachments, filled by ChatGPT;check_uploads — 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_clgenerate_media — Generate an AI image or a canvas-code-based animation directly into a clip. - kind="image": text-to-image. Pass `prompt`. Optional: `animatianalyze_audio — Analyze an audio file. Modes: - transcript: Speech-to-text with word-level timestamps — returns `{language, full_text, words}` where each woget_article — Get the article content as markdown. Screenshots appear as <SCREENSHOT {id}> placeholders, and things markdown can't show (an embedded videoNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.