ChatCut MCP
Use ChatCut when an agent needs to create or manage ChatCut video projects, import and inspect media, edit timelines and transcripts, add or style captions, create motion graphics, generate video, music, sound effects, or voiceovers, and export finished media. Choose ChatCut for editable project-based video workflows that combine AI generation with precise timeline work; use narrower generators or local media tools when no persistent ChatCut project is needed. A connected ChatCut account is required, and the agent must ask before spending ChatCut credits, starting cloud renders, deleting projects, assets, or timelines, or uploading private media.
Use ChatCut MCP with AI agents
Aident Loadout lets Claude Code, Codex, Cursor, and other supported agents call ChatCut MCP. Choose from 54 supported Actions. Review each execution in Audit.
Connect ChatCut MCP once through Aident Vault. Your agent can use the supported Actions without receiving the underlying credential.
Category
MediaPricing and payment
- Pricing
- Free in Loadout. Provider charges may apply when using a personally connected account.
- Unified payment
- Not currently supported. Connect a provider account when required.
Included Actions
- Apply ScriptApply the edits already authored as `timeline.md` to the canonical timeline. This is the commit step for Script edits: it diffs the file against the live state and commits atomically (any single-row error rolls back the whole apply). After a successful apply, `timeline.md` is re…
- Ask Followup QuestionsAsk the user follow-up questions in an interactive ChatCut card inside the MCP host chat. Use this when connector users should answer structured questions by clicking, choosing visual cards, auditioning voice cards, or filling text, instead of receiving raw `<widget>` HTML. Supp…
- Browse AssetsBrowse lightweight source-asset cards in the current project's media pool. Returns identity, duration in milliseconds, dimensions, folder, processing lifecycle, source access, concise transcript/generation/audio facts, and query match snippets. Query terms are whitespace-separat…
- Browse LibraryBrowse the ChatCut Library with one unified discovery tool. This tool is for ChatCut Library content only, not the user's project assets/media pool and not timelines. Categories match the Library tabs: motion-graphics, luts, zoom, effects, audio-effects, sound-effects, transitio…
- Clean ScriptMechanical first-pass cleanup for talking-head transcripts already on the timeline: fixed filler-token removal plus batch silence pause compression / restoration. For cleanup tasks, run this before semantic Script editing when fixed fillers or long pauses are present. Both capab…
- Convert Motion Graphic To VideoConvert a motion graphic into a real, transparent video asset (vp8/WebM alpha). Step 1 of the MG→video convert flow: kicks a cloud render of the MG at its native length and returns a durable renderId. Then: 1. Call track_export with the renderId until status is "complete" and re…
- Create Motion Graphic From CodeCreate a new Motion Graphic asset from inline React/JSX code supplied in this tool call. Use this for direct-authored Motion Graphics from inline JSX where the visual mechanism is chosen for the edit: emphasis, orientation, proof, sequence, contrast, transition, recurring identi…
- Create ProjectCreate a new empty ChatCut project for the current external MCP user. Use this when an external MCP client needs a fresh project before importing or editing media. This uses ChatCut's official Zero project.createWithTrack mutator, creates one active timeline and one video track,…
- Delete ProjectSoft-delete a ChatCut project the signed-in user owns — the same delete the editor dashboard performs. The project disappears from the dashboard and list_projects and its edits are blocked, but its data is retained: restore_project(projectId) undoes this. Requires an explicit pr…
- Detach AudioDetach a video clip's sound into a standalone audio item on an audio track (like "Detach Audio" in desktop NLEs). # When to use The user wants a video clip's picture and sound as two independently editable timeline items: offset the sound (J/L cuts), keep audio while replacing t…
- Duplicate ProjectDuplicate an existing ChatCut project into a new project owned by the signed-in user — the same full copy the editor dashboard's Duplicate action makes (all timelines, tracks, items, captions including word-level edits, speakers, transcripts, and asset references; chat history a…
- Edit AssetUpdate or delete a library asset. - update: change asset-level fields. Code update transport depends on the current agent surface. For other fields use json (e.g. filename, sourceLut). type is optional for update and inferred from assetId. - Motion-graphic properties schema uses…
- Edit CaptionsManage captions/subtitles through an SRT-like, time-ordered Card model. To inspect caption text content, use the `read_captions` tool; legacy projects may persist a one-time derived-caption reconciliation before returning the read. # When to read first - Card-targeted actions (`…
- Edit ItemItem-level timeline operations across types: `video` (incl. B-roll cutaways), `audio`, `image`, `gif`, `svg`, `motion-graphic`, `effect`, `transition`. Existing legacy `solid` items may be deleted, but edit_item does not create, duplicate, or update solids; use opaque Motion Gra…
- Edit ProjectUpdate project-level settings or speakers. Actions: - update: change project name/description. - speaker-create / speaker-update / speaker-delete: manage the speaker list used by transcripts. Canvas size, aspect ratio, and fps are per-timeline state — change them with manage_tim…
- Edit TrackManage tracks. Actions: list | create | update | delete | tighten. # Roles & ducking Auto-ducking comes from per-track roles — aim for ONE role per track, on the track that actually contains the relevant clips (talking-head speech often lives on the main video track's embedded a…
- Export Motion Graphic ProresExport one or more motion graphics as transparent ProRes 4444 .mov renders. Use this for the manual-equivalent "Export motion graphic" workflow and before NLE XML export when the XML should reference rendered motion-graphic media. The tool starts a cloud render and returns a dur…
- Find TranscriptFind the **timestamp** of a spoken phrase — a time-coordinate lookup, not a transcript reader or editing tool. # What this tool is for Locating WHEN something is said, so you can anchor non-transcript objects (B-roll, motion graphics, markers, brand overlays) at that moment. Ret…
- Get Editor UrlReturn the targeted ChatCut project's editor URL for the host's browser/card UI. Use this after create_project or target_project, or pass projectId from list_projects/the editor URL when continuing an existing project. If no project is known yet, call list_projects, target_proje…
- Import MediaCreate a short local-helper import session for direct ChatCut media imports from bytes held by the external MCP client. For local files, call this once with action="create_session", then run the plugin helper with at most four files. For more files, create a fresh session for ea…
- Inspect AssetInspect exactly one source asset. Every call returns source metadata; audio/video metadata may include transcript state and, when ASR is available, a preview of up to 60 characters plus segmentCount, but does not include transcript rows by default. Request a uniform coarse video…
- Inspect ItemReturn complete readable detail for exactly one item already placed on a timeline. Use item ids or prefixes from preview_timeline. The result includes identity, timeline and track, timeline/source ranges, asset reference, playback state, geometry, crop/fit/position/scale/rotatio…
- Isolate VoiceApply or clear AI voice isolation (DeepFilterNet3 speech enhancement) on a video or audio item with spoken human voice. This is not generic denoise — it is speech-only enhancement. IMPORTANT — only for clips that contain spoken human voice: DeepFilterNet3 is a speech-enhancement…
- List ProjectsList the ChatCut projects this signed-in user owns or can access (id, name, thumbnail, editor URL), newest first. This is a discovery-only call: it does not bind the external MCP session or retarget the live editor/browser surface. Call target_project with the chosen projectId b…
- Manage Design StyleManage the user's library of Design Styles. A design style is the ONLY representation of brand identity in this product — the currently applied design style IS the project's design style. There is no separate "project-only" brand. Actions split into two namespaces by storage: #…
- Manage MarkersManage note markers on a timeline. Current contract: marker-note-v2. A marker is a point-or-range comment anchored to timeline frames — for example "fix audio dip here" or "this cut is too tight". Each marker has a frame position, optional duration, and one user-visible field: n…
- Manage Media PoolOrganize the media pool library using user-managed folders. Use this for Finder/NLE-style organization only: list folders, create bins, rename bins, move assets into bins, or rename how assets appear in the media pool. It does not edit the timeline and it does not change source…
- Manage SkillManage reusable ChatCut workflow skills. This tool manages the user's saved Workflow Skills ONLY. ChatCut's built-in capability playbooks (talking-head-guide, motion-graphic-gen, video-gen, ...) are a separate system and will never show up here; their absence from this list does…
- Manage TemplateManage editor templates for the current project. Actions: - get: inspect one template by templateId. - list_assets: list every asset under a template, grouped by type. Use this before deciding apply vs generation. - apply: copy the whole template timeline/content into the curren…
- +25 Actions
Provider sources
Related AI agent Apps
- FalUse Fal when an agent needs to discover, compare, and run active Fal models for image, video, audio, music, speech, transcription, 3D, and media understanding. List models before selecting a non-default endpoint to inspect its current price and inputs. Choose fal_personal for unrestricted BYOK access or fal_account_management for private account operations. Supported calls use Aident platform credentials; ask before paid or high-cost generation.
- Fal ToolsGenerate and edit images and videos with Fal AI models.
- Ably ToolsAbly is a real-time messaging platform helping developers build live features, including chat and data synchronization, with global scalability and robust reliability for modern applications
- Abstract ToolsAbstract API provides a suite of APIs for developers to automate various tasks, including data validation, enrichment, and more.