Make videos and docs with ChatGPT, Claude, and Gemini — Clueso's MCP. Remote Str
Make videos and docs with ChatGPT, Claude, and Gemini — Clueso's MCP. Remote Streamable HTTP server (io.clueso/video).
active Production-safe Score 95/100 http no auth
At a glance
| Endpoint | https://connect.clueso.io/mcp |
|---|---|
| Source | https://github.com/clueso-ai/clueso-mcp |
| Transport | http |
| Tools | 56 |
| Auth | none |
| First seen | 2026-08-19 19:56:56 |
| Last checked | 2026-11-17 21:59:33 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 323 / 607 ms |
| Last successful check | 2026-11-17 21:59:33 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (56)
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 entryread_animation— Read an HTML animation's page site (index.html, CSS, JS) like a repository. Read-only. • project_id alone → this project's animations, wiedit_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 chduplicate_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 askedget_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 Recordingsget_usage— AI credits and export minutes left for the user in this workspace, and the plan. Call it only when the user asks about credits, limits or exget_embed— Get a project's embeddable video player: `embed_url` (permanent) and `embed_code` (a ready-to-paste <iframe>, the same snippet the editor'screate_folder— Create a folder in the workspace, optionally inside another folder, to organize projects. Returns { folder_id, name, parent_folder_id, alrefind— 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 buttsplit_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 tiedduplicate_clip— Clone one clip — within the same project, or **from another project** — into a target project. - Same project: pass `target_project_id` andadd_clips— Create new clips on a project. One tool, four sources: - kind="blank": empty slide clips you'll populate with add_elements / generate_mediaget_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: parallereorder_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. Youpdate_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 matchesextract_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. "syncupload_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: `animatanalyze_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 videoupdate_article— Update article text content from markdown. Use <SCREENSHOT {id}> placeholders to position screenshots. Screenshots in the markdown are kept.add_article_media— 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 placupdate_article_media— Update an article image/GIF (screenshot), or inspect its current state. - Provide one or more of `zoom_factor`, `crop`, `shapes` to change mcreate_clueprint— Create a new clueprint (reusable video template). A clueprint is a structured file directory with design notes, composition rules, and screeget_clueprint— Fetch clueprint data. Use `include` to control how much you pull back: - include="metadata": just the clueprint's name/description/tags/visiupdate_clueprint— Update a clueprint's metadata and/or file contents in one call. Metadata fields (`name`, `description`, `tags`, `visibility`, `thumbnail_pamanage_brand_kit— Create and change the workspace's brand kits (editors and admins). The same operations as the brand kit page, so a kit made here looks the sset_voice— Set the voiceover voice for every clip in a project, or only for the clips in `clip_ids`. Use this to apply a clueprint's voice (read `voicpronunciation— Read and edit the workspace pronunciation dictionary (Settings → Team → Pronunciation Dictionary). Use it whenever the user asks how a word,translation_glossary— Read and edit the workspace's translation glossary and translation rules (Settings → Translation). Every translation in the workspace followadd_comment— Post a review comment on a project, attributed to "Clueso AI". Use this to leave feedback, suggestions, or notes — either at the project leget_comments— Read the review comments on a project — the other half of `add_comment`, which could post but never read. Comments are how a human reviewerrecord_screen— Records the product on a mock (Code record) as a screen-recording clip in a project. Creates blank placeholder clips, registers job entitiesrun_script— Run a JavaScript program that calls this server's tools: loops, math, values carried between calls, one round trip. Use it whenever code sayget_script_job— Fetch the outcome of a run_script that did not finish inline. Waits for it rather than returning immediately, so one call is usually enough
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 21:59:33 | ✓ | ✓ | 181 ms | 94 | active |
| 2026-11-17 21:44:33 | ✓ | ✓ | 193 ms | 94 | active |
| 2026-11-17 21:29:33 | ✓ | ✓ | 185 ms | 94 | active |
| 2026-11-17 21:14:33 | ✓ | ✓ | 351 ms | 91 | active |
| 2026-11-17 20:59:33 | ✓ | ✓ | 326 ms | 91 | active |
| 2026-11-17 20:44:33 | ✓ | ✓ | 401 ms | 91 | active |
| 2026-11-17 20:29:32 | ✓ | ✓ | 190 ms | 94 | active |
| 2026-11-17 20:14:32 | ✓ | ✓ | 310 ms | 91 | active |
| 2026-11-17 19:59:32 | ✓ | ✓ | 227 ms | 94 | active |
| 2026-11-17 19:44:31 | ✓ | ✓ | 177 ms | 94 | active |
| 2026-11-17 19:29:31 | ✓ | ✓ | 173 ms | 94 | active |
| 2026-11-17 19:14:31 | ✓ | ✓ | 595 ms | 91 | active |
| 2026-11-17 18:59:31 | ✓ | ✓ | 195 ms | 94 | active |
| 2026-11-17 18:44:31 | ✓ | ✓ | 193 ms | 94 | active |
| 2026-11-17 18:29:30 | ✓ | ✓ | 177 ms | 94 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://connect.clueso.io/mcp") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/connect-clueso-io-mcp # JSON