Kolbo.AI

Soft-delete up to 1000 media items in one call. Items go to trash (30-day recovery). Owner only — items not owned by the user are silently skipped (count returned in response). Use this for "clean up all my old [type]" or "delete the failed generations from yesterday".

Move up to 1000 media items to a different project in a single call. Caller must own ALL items AND have access to the target project — if any item isn't owned by the caller, the entire operation is rejected (atomic).

Move MANY sessions into one project in a single call — the tool to use when reorganizing a user's library ("file all my Acme work into the Acme project", "clean up the API Generations bucket"). Each session carries ALL of its generations and media with it. Prefer this over looping `move_session`: one call handles up to 100 sessions, while `move_session` is rate limited per call. Sessions of mixed types (chat + image + video) can go in the SAME call. Each session moves independently, so one that cannot move — a generation still running, a Creative Director session, or one you lack edit access to — does NOT block the rest; check `failed[]` in the result and report those to the user. Resolve session ids with `list_sessions` and the target project id with `list_projects` first.

PERMANENTLY delete up to 1000 media items. NOT REVERSIBLE — removes from MongoDB, S3, folders, and source generation records. Owner only. ALWAYS confirm with the user before calling; this is the bulk equivalent of `permanently_delete_media`.

Restore up to 1000 trashed media items at once. Owner only. Returns the count restored and how many ids weren't in trash (already active or not owned).

Cancel a running generation and release/refund its credits. Works for every generation type the SDK tracks (image, image edit, video, image-to-video, video-to-video, elements, first/last frame, lipsync, music, speech, sound, 3D, motion graphic, global image/video edit, creative director). Use when the user says "stop", "cancel that", "never mind" while something is still running, or to clear a stuck generation. Returns how many credits came back. A generation that already finished or failed cannot be cancelled — you get a 409 with its current status, which is not an error worth retrying. For Shorts Creator jobs use shorts_cancel instead.

Fetch messages in a chat conversation. Returns role, content, model, and any media URLs attached to each message.

List the user's chat conversations across ALL projects, most-recent first. Returns session_id, name, project_id, and activity timestamps. Pass `project_id` to narrow to one project (resolve names via `list_projects`).

Send a chat message to Kolbo AI. Starts a new conversation (omit session_id) or continues an existing one. Returns the assistant response when complete. Supports image/video/audio analysis via media_urls — pass public URLs and the model auto-routes to a vision-capable model (e.g. Gemini) when media is detected. Supports web search and deep think modes. LOCAL FILE (on the user's machine, or attached to this chat)? NEVER reply that you cannot upload files — Kolbo uploads it for you. Call `media_upload_widget` so the user picks the file (claude.ai web/mobile), or `create_upload_ticket` and POST the file yourself if you can run shell/HTTP commands; either way you get an https:// URL to pass here. Ignore any "absolute local path" wording in the args below — this server cannot read the caller's disk, so a path will fail.

Check your remaining Kolbo credit balance.

Clone a custom TTS voice from an audio sample (the user's voice or any voice they own the rights to). Costs credits (provider-dependent) — confirm with the user before firing. Providers: "elevenlabs" (recommended, 2s–180s sample) or "deepdub" (2s–300s). After cloning, the voice appears in `list_voices` and can be used with generate_speech. Free plan caps at 3 custom voices. LOCAL FILE (on the user's machine, or attached to this chat)? NEVER reply that you cannot upload files — Kolbo uploads it for you. Call `media_upload_widget` so the user picks the file (claude.ai web/mobile), or `create_upload_ticket` and POST the file yourself if you can run shell/HTTP commands; either way you get an https:// URL to pass here. Ignore any "absolute local path" wording in the args below — this server cannot read the caller's disk, so a path will fail.

Create a reusable custom chat agent (a named persona for the chat tool). The `description` IS the agent's system instruction — write it as the persona + behavior you want ("You are a senior creative director. Turn any brief into a structured shot list…"). Use when the user wants a persistent, reusable assistant ("make me a creative-director agent", "set up a support-triage bot"). For a ONE-OFF persona on a single conversation, pass `system_prompt` to chat_send_message instead — no need to create an agent. Plan limits apply (server rejects when the custom-agent cap is reached).

Save a new Color DNA palette from manual colors or from analyze_color_palette output. IMPORTANT: activating a palette is STICKY and ACCOUNT-WIDE — once active, it strict-grades EVERY generation (generate_image, generate_image_edit, generate_video, generate_video_from_image) automatically until deactivated, not just the next one. Always tell the user this before activating, and mention deactivate_color_palette / skip_color_palette (per-call opt-out) as the way out. Pass is_active: false to save without activating.

Create an AI Doc (Magic Pad document) in the user's Kolbo workspace. YOU author the document: write complete, well-structured HTML content (plans, briefs, scripts, research summaries, meeting notes…) and save it here so the user can read and edit it in the Kolbo app. Docs are project-scoped — when the user is working in a named project, resolve it with `list_projects` and pass `project_id`. Returns the doc id; use `share_doc` afterwards if the user wants a public link.

Create a new media folder for the user. Folders are user-scoped (span all projects) and useful for grouping related assets. Returns the new folder id — pass it as `folder_id` to `list_media`, `add_media_to_folder`, etc.

Create a moodboard from 1–15 image URLs. The server analyzes the images and synthesizes a reusable master style prompt — then pass the returned moodboard id as `moodboard_id` on generation tools to apply the style. Use Kolbo URLs (generated images or `upload_media` output) or any public image URL. Typical flow: generate/upload reference images → create_moodboard → generate with moodboard_id. LOCAL FILE (on the user's machine, or attached to this chat)? NEVER reply that you cannot upload files — Kolbo uploads it for you. Call `media_upload_widget` so the user picks the file (claude.ai web/mobile), or `create_upload_ticket` and POST the file yourself if you can run shell/HTTP commands; either way you get an https:// URL to pass here. Ignore any "absolute local path" wording in the args below — this server cannot read the caller's disk, so a path will fail.

Create a new Kolbo project. Use when the user starts a new body of work ("new project for film X", "set up a workspace for the campaign"). After creating, pass the returned id as `project_id` on EVERY subsequent generation/upload/doc call for that work. Plan limits apply (server rejects when the plan's project cap is reached).

Create a Kolbo Review asset with v1 media attached. Upload first via `upload_media`, `create_upload_ticket`, or `media_upload_widget`, then pass the returned `media_id`. Requires `project_id` when the user named a project.

Create a review collection folder inside a project.

Add a text comment on a review asset. Optional video timecodes: time_start / time_end (seconds).

Create a guest review link for an asset or collection. Returns share_url for clients (no Kolbo account needed).

Get a short-lived ticket for uploading LOCAL files straight into the user's Kolbo media library, with NO upload card and no user interaction. You are reached over a REMOTE connector: this server cannot read the caller's disk, so `upload_media` with a local path will always fail here — do not try it. If you can run shell commands or issue HTTP requests yourself, this tool is the right path. If you cannot (claude.ai web/mobile), ignore this tool and call `media_upload_widget` so the user picks the file. Why it exists: when the server cannot read the caller's disk, the only other ways in are making the user click an upload card (`media_upload_widget`) or inlining the file as base64 via `upload_media` — base64 is slow and burns context in proportion to file size, so do not use it for anything but a tiny file. Returns `upload_url` + `token`; POST each file as multipart field `file` with header `Authorization: Bearer <token>` and read the CDN URL from `media.url` in the response. One POST per file; the ticket is reusable until it expires. The endpoint is RATE LIMITED (the exact cap and window come back in the ticket's `rate_limit` field — currently 40 uploads/minute): pace a batch bigger than that rather than firing every file at once, and on HTTP 429 honour the `Retry-After` header / `retry_after_seconds` body field instead of guessing a backoff. Then pass those URLs to any generation tool (transcribe_audio, generate_image_edit, generate_video_from_image, generate_lipsync, visual DNA, …).

Create a Visual DNA profile from reference media. Each item in images/video/audio can be a public URL or an absolute local file path. Max 4 images, 1 video, 1 audio. Files capped at 25MB each. For EVERY DNA type, a reference sheet dramatically improves consistency (character turnaround / product details / location angles / style board) — offer to generate one with `generate_character_sheet` (matching `sheet_type`) first, then pass its URL as `character_sheet_url` here (see that tool). LOCAL FILE (on the user's machine, or attached to this chat)? NEVER reply that you cannot upload files — Kolbo uploads it for you. Call `media_upload_widget` so the user picks the file (claude.ai web/mobile), or `create_upload_ticket` and POST the file yourself if you can run shell/HTTP commands; either way you get an https:// URL to pass here. Ignore any "absolute local path" wording in the args below — this server cannot read the caller's disk, so a path will fail.

Create a Visual DNA folder for organizing characters (e.g. "Main Cast", "Villains", "Film X Characters"). Folder names are unique per user (409 on duplicates). Then use `move_visual_dna_to_folder` to file DNAs into it.

Clear whichever Color DNA palette is currently active for the account. Generations stop being auto color-graded until another palette is activated.

Delete a custom chat agent you own. Global preset agents cannot be deleted. This removes the agent config only — it does not touch any conversations that used it.

Permanently delete a Color DNA palette. Owner only. If it was the active palette, generations stop being color-graded.

Delete an AI Doc (soft delete — recoverable from the app's trash flow). Owner only. Confirm with the user before deleting anything they did not just create in this conversation.

Soft-delete a media item — moves it to the user's trash where it can be restored for 30 days. Owner only. Idempotent. Use this for "delete this image / video / song" — NOT for `permanently_delete_media`, which is irreversible.

Delete a folder (soft delete — items inside are detached but NOT deleted from the user's media library). Owner only. ALWAYS ask the user to confirm before calling this — folder deletion is not surfaced in any "undo" flow.

Permanently delete a moodboard (owner only; system presets cannot be deleted). The underlying image files stay in storage — only the board is removed. Confirm with the user before deleting boards they did not just create.

Remove one source from a project's knowledge base by its file_key (from list_project_context).

Soft-delete a review asset and its underlying review media.

Soft-delete a review collection (assets become uncollected).

Delete a review comment (own comment, or any comment if you have full project access).

Delete a Visual DNA profile by ID. Only the owner can delete.

Delete a Visual DNA folder. The DNAs inside are NOT deleted — they move back to the root level (response includes items_moved_to_root). Safe to call without confirmation for empty folders; mention the contents-move when the folder has items.

Delete one of the user's custom cloned voices (owner only, soft delete). Preset/platform voices cannot be deleted. Confirm with the user first.

Apply a targeted AI edit to an existing image. Covers mechanical enhancements (upscale, remove background, skin retouching) AND creative operations (expand/outpaint, reframe, inpaint, erase, face swap, background replace, camera angle, multi-shot grid, split/upscale). ⚠️ To EXPAND an image / add space / widen it to a new aspect ratio while keeping the existing artwork intact, use operation="zoom_out" — NOT "reframe" (reframe re-generates the whole picture). ⚠️ For open-ended PROMPT-DRIVEN content edits — "make it night", restyling, adding/removing objects — use `generate_image_edit` instead; it runs on stronger dedicated editing models and produces better results. LOCAL FILE (on the user's machine, or attached to this chat)? NEVER reply that you cannot upload files — Kolbo uploads it for you. Call `media_upload_widget` so the user picks the file (claude.ai web/mobile), or `create_upload_ticket` and POST the file yourself if you can run shell/HTTP commands; either way you get an https:// URL to pass here. Ignore any "absolute local path" wording in the args below — this server cannot read the caller's disk, so a path will fail.

Edit your own review comment text and/or timecodes.