# CutClip.one (remote · cutclip.one)

AI video editor your agent can drive: plan scenes, edit a multi-track timeline, and render MP4s.

- Trust score: 75/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `cutclip.one`: 75/100 (this document), [markdown](https://verifymcp.io/servers/one-cutclip-cutclip/api-mcp.md), [page](https://verifymcp.io/servers/one-cutclip-cutclip/api-mcp)

## Channel facts

- Endpoint: `https://cutclip.one/api/mcp`
- Transports: `streamable-http`
- Auth: `required (not validated)`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 83/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 61/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 10614 tokens (~95/item across 111 items; 111 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 47/100
  - Stability observed for 14 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 73/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 19% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 14 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "project.delete" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 111 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the CutClip.one MCP server?

CutClip.one is a hosted endpoint at https://cutclip.one/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http one-cutclip-cutclip 'https://cutclip.one/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "one-cutclip-cutclip": {
      "url": "https://cutclip.one/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "one-cutclip-cutclip": {
      "type": "http",
      "url": "https://cutclip.one/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.one-cutclip-cutclip]
url = "https://cutclip.one/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "one-cutclip-cutclip": {
      "type": "remote",
      "url": "https://cutclip.one/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add one-cutclip-cutclip --url 'https://cutclip.one/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  one-cutclip-cutclip:
    url: "https://cutclip.one/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "one-cutclip-cutclip": {
      "Transport": "http",
      "Url": "https://cutclip.one/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add one-cutclip-cutclip -t streamable-http -u 'https://cutclip.one/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "one-cutclip-cutclip": {
      "type": "http",
      "url": "https://cutclip.one/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-20 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-14 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-12 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-09 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-08 (score 69, +1)

- [security] Tool “shot.compile_prompt” rewrote its description, which is the text the model reads
- [security] Tool “shot.generate_video” rewrote its description, which is the text the model reads
- [security] Tool “shot.update” rewrote its description, which is the text the model reads
- [functional improvement] Stability: unverified → 0.03
- [cosmetic] “shot.update” added an optional parameter “referenceVideoAssetIds”
- [cosmetic] “shot.update” added an optional parameter “referenceVideoMode”

### 2026-11-07 (score 68, +35)

- [security improvement] Transport: unverified → pass
- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Authorization: Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: fair
- [functional] First check of Destructive annotations: 0
- [functional] First check of Tool coverage: 19
- [functional] First check of Schema quality: pass

## MCP tools (111)

### `project.create` (~46 tokens)

Create a new film project (§11.1)

Input parameters:

- `fps` (integer)
- `height` (integer)
- `name` (string, required)
- `width` (integer)

### `project.list_for_owner` (~22 tokens)

List every project a user owns, most recently updated first

### `project.update` (~46 tokens)

Rename a project or change its description

Input parameters:

- `description` (string)
- `expectedVersion` (integer, required)
- `name` (string)
- `projectId` (string, required)

### `project.delete` (~39 tokens)

Permanently delete a project and everything in it (tracks, scenes, assets, render history). Cannot be undone.

Input parameters:

- `projectId` (string, required)

### `project.get_state` (~37 tokens)

Fetch a project's full current state: project, tracks, scenes, timeline items, placeholders, scenarios

Input parameters:

- `projectId` (string, required)

### `project.get_summary` (~45 tokens)

Fetch a compact project summary (project settings, tracks, scene list) — prefer this over project.get_state for normal conversation context (§16)

Input parameters:

- `projectId` (string, required)

### `project.export` (~48 tokens)

Export a project's full structure (settings, tracks, scenes, timeline, placeholders, transitions, current prompts) as a portable JSON document, suitable for project.import

Input parameters:

- `projectId` (string, required)

### `project.import` (~56 tokens)

Create a brand-new project from a project.export JSON document. Only relinks media whose asset id still exists and is owned by ownerId; anything else comes in unresolved.

Input parameters:

- `data` (object, required)
- `name` (string)

### `track.create` (~52 tokens)

Create a video or audio track on a project (§11.4)

Input parameters:

- `expectedVersion` (integer, required)
- `name` (string, required)
- `projectId` (string, required)
- `type` (string, required)

### `track.update` (~79 tokens)

Rename, mute, lock, or set the volume (0-1) of a track

Input parameters:

- `expectedVersion` (integer, required)
- `locked` (boolean)
- `muted` (boolean)
- `name` (string)
- `projectId` (string, required)
- `trackId` (string, required)
- `volume` (number)

### `track.delete` (~36 tokens)

Delete a track

Input parameters:

- `expectedVersion` (integer, required)
- `projectId` (string, required)
- `trackId` (string, required)

### `track.reorder` (~73 tokens)

Move a track to a new position among the project's tracks — video and audio tracks share one ordering, so a track can move in between tracks of either type

Input parameters:

- `expectedVersion` (integer, required)
- `newOrder` (integer, required)
- `projectId` (string, required)
- `trackId` (string, required)

### `scene.create` (~78 tokens)

Create a storytelling scene on a project — distinct from a timeline clip (§7.2, §11.3)

Input parameters:

- `expectedVersion` (integer, required)
- `narrativePurpose` (string)
- `plannedDurationMs` (integer, required)
- `projectId` (string, required)
- `summary` (string)
- `title` (string, required)

### `scene.update` (~108 tokens)

Update a scene's title, summary, narrative purpose, planned duration, or location (its shots inherit the location unless they override it)

Input parameters:

- `expectedVersion` (integer, required)
- `locationId` (string|null): A location from location.list; null clears it
- `narrativePurpose` (string)
- `plannedDurationMs` (integer)
- `projectId` (string, required)
- `sceneId` (string, required)
- `summary` (string)
- `title` (string)

### `scene.reorder` (~53 tokens)

Move a scene to a new position among the project's scenes

Input parameters:

- `expectedVersion` (integer, required)
- `newOrder` (integer, required)
- `projectId` (string, required)
- `sceneId` (string, required)

### `scene.delete` (~36 tokens)

Delete a scene

Input parameters:

- `expectedVersion` (integer, required)
- `projectId` (string, required)
- `sceneId` (string, required)

### `timeline.add_placeholder` (~96 tokens)

Add a video/audio placeholder clip to a track, ready for a generation prompt (§7.5, §11.5)

Input parameters:

- `durationMs` (integer, required)
- `expectedVersion` (integer, required)
- `kind` (string, required)
- `projectId` (string, required)
- `sceneId` (string)
- `startMs` (integer, required)
- `title` (string, required)
- `trackId` (string, required)

### `timeline.move_item` (~94 tokens)

Move a timeline item to a new start time, and optionally to a different track (must be the same track type — video to video, audio to audio — and the item must not be a transition or have one attached)

Input parameters:

- `expectedVersion` (integer, required)
- `itemId` (string, required)
- `projectId` (string, required)
- `startMs` (integer, required)
- `trackId` (string)

### `timeline.duplicate_item` (~142 tokens)

Duplicate a timeline clip (media or placeholder, not a transition), by default onto the same track immediately after itself, pushing whatever else is later on that track to the right to make room (only fails if the target spot would land inside another clip that starts before it). Pass trackId to duplicate onto a different track of the same type, and/or startMs to place it elsewhere. A duplicated placeholder gets its own independent copy of its prompt (if any).

Input parameters:

- `expectedVersion` (integer, required)
- `itemId` (string, required)
- `projectId` (string, required)
- `startMs` (integer)
- `trackId` (string)

### `timeline.trim_item` (~81 tokens)

Trim a timeline item's start, duration, or source in/out points

Input parameters:

- `durationMs` (integer)
- `expectedVersion` (integer, required)
- `itemId` (string, required)
- `projectId` (string, required)
- `sourceInMs` (integer)
- `sourceOutMs` (integer)
- `startMs` (integer)

### `timeline.set_speed` (~113 tokens)

Change a clip's playback speed (0.2 = 5x slower, 1 = normal, 1.8 = 1.8x faster). Recomputes the clip's timeline duration for the new speed and ripples everything later on the same track to stay contiguous — the source range consumed is unchanged, only how long it takes to play.

Input parameters:

- `expectedVersion` (integer, required)
- `itemId` (string, required)
- `projectId` (string, required)
- `speed` (number, required)

### `timeline.set_volume` (~87 tokens)

Set a clip's own audio gain (0 = silent, 1 = full). Multiplies with its track's volume — both apply together — so a clip can be ducked or muted independent of the rest of its track.

Input parameters:

- `expectedVersion` (integer, required)
- `itemId` (string, required)
- `projectId` (string, required)
- `volume` (number, required)

### `timeline.set_transform` (~286 tokens)

Place a clip on a video track as a layer: its position, size and opacity in the frame. Video tracks stack by order (higher order is drawn on top), and anything outside a scaled-down or transparent clip shows the tracks beneath — so a logo, watermark or picture-in-picture is an image/GIF/video placeholder on a track ABOVE the footage, with e.g. scale 0.15 and x 0.9, y 0.1 for the top-right corner. Images and GIFs loop to fill their clip's whole duration; GIF/PNG transparency is kept. Only the fields you pass change. Defaults (nothing set) are x 0.5, y 0.5, scale 1, opacity 1 — the full frame.

Input parameters:

- `expectedVersion` (integer, required)
- `itemId` (string, required)
- `opacity` (number): 0 invisible, 1 opaque
- `projectId` (string, required)
- `scale` (number): Size relative to filling the frame: 1 full frame, 0.2 a small logo
- `x` (number): Clip center, fraction of frame width: 0 left edge, 0.5 centered, 1 right edge
- `y` (number): Clip center, fraction of frame height: 0 top, 0.5 centered, 1 bottom

### `timeline.split_item` (~53 tokens)

Split a timeline item into two at an absolute timeline position

Input parameters:

- `atMs` (integer, required)
- `expectedVersion` (integer, required)
- `itemId` (string, required)
- `projectId` (string, required)

### `timeline.delete_item` (~45 tokens)

Delete a timeline item (and its placeholder, if any)

Input parameters:

- `expectedVersion` (integer, required)
- `itemId` (string, required)
- `projectId` (string, required)

### `timeline.close_gap` (~68 tokens)

Ripple a timeline item (and everything after it on the same track) earlier to eat the empty space immediately before it. Fails if there is no gap before the item.

Input parameters:

- `expectedVersion` (integer, required)
- `itemId` (string, required)
- `projectId` (string, required)

### `timeline.batch` (~249 tokens)

Apply SEVERAL timeline edits in ONE call — one version check, one result, one undo step, all-or-nothing (if any op fails nothing is applied and the error names the failing op). ALWAYS prefer this over repeated single-edit calls whenever you have two or more timeline edits to make (e.g. trimming five clips, setting speed on several, crossfading a run then closing gaps): it costs one round-trip instead of one per edit. Ops run in order against the live state, so a later op sees the result of an earlier one (e.g. close_gaps, then add_transitions on the now back-to-back clips). Each op is the same as the matching timeline.* tool, minus projectId/expectedVersion/actor: move_item, trim_item, set_speed, set_volume, set_transform, close_gap, close_gaps, add_transition, add_transitions, remove_transition, remove_transitions, update_transition_duration. (Creating, splitting, duplicating and deleting clips are not batchable — use their own tools.) Max 50 ops.

Input parameters:

- `expectedVersion` (integer, required)
- `ops` (array, required)
- `projectId` (string, required)

### `timeline.close_gaps` (~236 tokens)

Close the empty gaps between SEVERAL clips at once (a ripple: each clip after the first is pulled left against its predecessor, and everything later on the track moves with it, so clips after the span keep their spacing). Select the clips with exactly one of itemIds (every gap inside the span from the earliest to the latest of them is closed), trackId (every clip on one track) or all:true (every clip on every track; add trackType to limit to video or audio) — for 'the whole timeline' use all:true, do NOT list ids. The gap before the earliest selected clip is left alone (use timeline.close_gap for that). Crossfade overlaps are preserved. One undo step. Fails if there are no gaps.

Input parameters:

- `all` (boolean): Every clip on every track — narrow with trackType
- `expectedVersion` (integer, required)
- `itemIds` (array): These specific clips
- `projectId` (string, required)
- `trackId` (string): Every clip on this track
- `trackType` (string): With all: only tracks of this type

### `timeline.add_transition` (~252 tokens)

Add a transition (§4.1: crossfade, smooth_blend, fade_from_black, or fade_to_black — a hard cut needs no call at all, it's just the default). crossfade and smooth_blend require fromItemId and toItemId to be two contiguous, back-to-back clips on the same track, and shift toItemId durationMs earlier so the overlap uses only content the clips already have (no source 'handle' footage needed) — this shortens the sequence by durationMs, exactly like a real NLE. smooth_blend is the least noticeable join: the same overlap as crossfade, but eased (cosine) at both ends so the blend has no perceptible start or end; prefer it when the goal is for the viewer not to notice the transition. fade_from_black/fade_to_black only need fromItemId (the clip being faded) and apply within its own bounds.

Input parameters:

- `durationMs` (integer, required)
- `expectedVersion` (integer, required)
- `fromItemId` (string, required)
- `kind` (string, required)
- `projectId` (string, required)
- `toItemId` (string)
- `trackId` (string, required)

### `timeline.add_transitions` (~331 tokens)

Add the SAME transition to several clips in ONE call (and one undo step) — prefer this over repeated timeline.add_transition when joining a run of clips. Select the clips with exactly one of itemIds, trackId (every clip on a track) or all:true (every clip on every track; trackType limits to video/audio) — to crossfade the whole film use all:true with trackType 'video', do NOT list ids or make one call per join. kind crossfade/smooth_blend: adds one between every pair of the selected clips that are neighbours on their track (a chain of N clips gets N-1 transitions; the clips must be back-to-back, close gaps first with timeline.close_gaps). Each incoming clip shifts durationMs earlier, together with any clips chained after it, so the total sequence shortens by durationMs per join. kind fade_from_black / fade_to_black: adds that fade to each selected clip. Pairs/clips that can't take it (already has one, gap, too short) are skipped and reported in `skipped` + warnings; the call only fails if nothing at all could be added.

Input parameters:

- `all` (boolean): Every clip on every track — narrow with trackType
- `durationMs` (integer, required)
- `expectedVersion` (integer, required)
- `itemIds` (array): These specific clips
- `kind` (string, required)
- `projectId` (string, required)
- `trackId` (string): Every clip on this track
- `trackType` (string): With all: only tracks of this type

### `timeline.remove_transitions` (~165 tokens)

Remove transitions from several clips in ONE call (and one undo step): every transition whose clip(s) are all selected (itemIds, trackId or all:true, like timeline.add_transitions) — a crossfade/smooth_blend needs both its clips selected, a fade just its own clip. Crossfaded clips are shifted back to their pre-transition positions. Fails if there is nothing to remove.

Input parameters:

- `all` (boolean): Every clip on every track — narrow with trackType
- `expectedVersion` (integer, required)
- `itemIds` (array): These specific clips
- `projectId` (string, required)
- `trackId` (string): Every clip on this track
- `trackType` (string): With all: only tracks of this type

### `timeline.remove_transition` (~59 tokens)

Remove a transition. For a crossfade or smooth_blend this also shifts the incoming clip back to its pre-transition position.

Input parameters:

- `expectedVersion` (integer, required)
- `projectId` (string, required)
- `transitionItemId` (string, required)

### `timeline.update_transition_duration` (~87 tokens)

Change how long an existing fade, crossfade or smooth_blend lasts, in ms. For a crossfade or smooth_blend this re-shifts the incoming clip to keep it anchored to the outgoing clip's end.

Input parameters:

- `durationMs` (integer, required)
- `expectedVersion` (integer, required)
- `projectId` (string, required)
- `transitionItemId` (string, required)

### `asset.replace_placeholder` (~77 tokens)

Point a placeholder at a real uploaded/generated asset (§11.7, §18.2). Preserves the placeholder and its prompt for provenance; sets its status to 'generated'.

Input parameters:

- `assetId` (string, required)
- `expectedVersion` (integer, required)
- `placeholderId` (string, required)
- `projectId` (string, required)

### `asset.get` (~66 tokens)

Fetch one asset's metadata (type, source, mime type, duration/dimensions if known) plus a downloadUrl for its file: a plain HTTP GET, no auth header needed, valid 24h (call again for a fresh one)

Input parameters:

- `assetId` (string, required)

### `asset.list` (~29 tokens)

List every asset uploaded/generated for a project (§11.7)

Input parameters:

- `projectId` (string, required)

### `scenario.create` (~85 tokens)

Stage a concept + treatment + scene list before materializing it onto the timeline (§9, §11.2). Does not touch tracks/scenes/timeline — call scenario.apply_to_timeline next.

Input parameters:

- `concept` (object, required)
- `expectedVersion` (integer, required)
- `projectId` (string, required)
- `scenes` (array, required)
- `treatment` (string)

### `scenario.get` (~29 tokens)

Fetch a staged scenario's concept, treatment, and scene list

Input parameters:

- `scenarioId` (string, required)

### `scenario.update` (~92 tokens)

Revise a staged scenario's concept, treatment, and/or scene list before applying it — e.g. after the user asks for a pacing or tone change. Only the fields provided are changed.

Input parameters:

- `concept` (object)
- `expectedVersion` (integer, required)
- `projectId` (string, required)
- `scenarioId` (string, required)
- `scenes` (array)
- `treatment` (string)

### `scenario.delete` (~48 tokens)

Delete a staged scenario draft (does not affect anything already applied to the timeline)

Input parameters:

- `expectedVersion` (integer, required)
- `projectId` (string, required)
- `scenarioId` (string, required)

### `scenario.apply_to_timeline` (~159 tokens)

The high-level film-building tool (§34): materializes a staged scenario into real tracks, scenes, placeholders, and timeline items in one atomic, undoable step. Creates a video track with one placeholder per scene; optionally a Music track with one placeholder spanning the whole scenario, an SFX track with a per-scene placeholder wherever a scene has a soundPrompt, and a Voice track wherever a scene has a voicePrompt. When createPromptPlaceholders is true (default), each scene's videoPrompt/soundPrompt/voicePrompt is attached immediately so placeholders start at status prompt_ready.

Input parameters:

- `expectedVersion` (integer, required)
- `options` (object)
- `projectId` (string, required)
- `scenarioId` (string, required)

### `storyline.get` (~60 tokens)

Fetch the Scenario Maker draft storyline for a project: the premise (and how many reference images it has), the scenes the user has accepted so far (path), and the current batch of suggested next scenes (candidates).

Input parameters:

- `projectId` (string, required)

### `storyline.set_premise` (~81 tokens)

Set the Scenario Maker premise (initial scene or short scenario), optionally with up to 3 reference images (base64) that define the look and setting. Resets the accepted path and candidates. Needs a premise or at least one image.

Input parameters:

- `images` (array)
- `premise` (string)
- `projectId` (string, required)

### `storyline.set_candidates` (~60 tokens)

Replace the current batch of suggested next scenes with distinct options you propose, so the user can pick one. Each option should follow from the premise and every scene already in the path.

Input parameters:

- `candidates` (array, required)
- `projectId` (string, required)

### `storyline.pick` (~58 tokens)

Accept one of the current candidates as the next scene in the storyline, optionally with edits. Clears the candidates — suggest new ones afterwards.

Input parameters:

- `candidateId` (string, required)
- `edits` (object)
- `projectId` (string, required)

### `storyline.update_scene` (~42 tokens)

Edit a scene already accepted into the storyline path

Input parameters:

- `edits` (object, required)
- `projectId` (string, required)
- `sceneId` (string, required)

### `storyline.rewind` (~64 tokens)

Rewind the storyline: keep only the first `keep` accepted scenes (0 clears the path) and discard the rest and the current candidates, so a different choice can be made at that point.

Input parameters:

- `keep` (integer, required)
- `projectId` (string, required)

### `storyline.apply` (~116 tokens)

Turn the accepted storyline path into real scenes, placeholders, prompts and timeline items in one undoable step (stages it as a scenario and applies it), then clears the draft path. With draftShots (default true) each scene is first broken into a shot list like shot.draft (metered in credits unless the owner uses their own Anthropic key), so the scenes arrive with shots and one placeholder per shot.

Input parameters:

- `draftShots` (boolean)
- `expectedVersion` (integer, required)
- `projectId` (string, required)

### `prompt.attach` (~162 tokens)

Attach a structured prompt document to a scene slot (visual/sound/music/voice) or a placeholder directly (§8, §11.6)

Input parameters:

- `aspectRatio` (string)
- `camera` (array)
- `createdBy` (string, required)
- `durationSec` (number)
- `environment` (array)
- `expectedVersion` (integer, required)
- `intent` (string)
- `lighting` (array)
- `motion` (array)
- `negativePrompt` (string)
- `projectId` (string, required)
- `providerHints` (object)
- `soundDesign` (array)
- `style` (array)
- `target` (required)
- `text` (string, required)
- `type` (string, required)

### `prompt.update` (~58 tokens)

Revise a prompt — creates a new revision rather than overwriting the old one (§17)

Input parameters:

- `expectedVersion` (integer, required)
- `patch` (object, required)
- `projectId` (string, required)
- `promptId` (string, required)

### `prompt.get` (~23 tokens)

Fetch one prompt document by id

Input parameters:

- `promptId` (string, required)

### `prompt.list_for_scene` (~33 tokens)

List every prompt ever attached to a scene, across all slots and revisions

Input parameters:

- `sceneId` (string, required)

### `prompt.list_revisions` (~44 tokens)

Get the full revision history (oldest first) for a prompt's slot, given any promptId in that lineage (§17)

Input parameters:

- `promptId` (string, required)

### `project.undo` (~28 tokens)

Undo the most recent operation applied to a project (§14)

Input parameters:

- `projectId` (string, required)

### `render.preview` (~153 tokens)

Start a fast, half-resolution preview export of the project's current timeline to MP4 (§11.8). Takes the same aspect/fit as render.final so the framing can be checked cheaply. Costs 1 credit, charged to the project owner; fails with INSUFFICIENT_CREDITS if they can't cover it.

Input parameters:

- `aspect` (string): Shape of the exported video; project (default) keeps the project's own frame. 9:16 / 4:5 for Reels, Shorts and TikTok
- `fit` (string): When the aspect differs from the project's: fill (default) center-crops the picture, fit shows all of it with black bars
- `projectId` (string, required)

### `render.final` (~260 tokens)

Start a full-resolution final export of the project's current timeline to MP4 (§11.8). Costs 5 credits at 1080p (the default), 10 at 2k (2560x1440) or 15 at 4k, charged to the project owner; fails with INSUFFICIENT_CREDITS if they can't cover it. The resolution is the short side for portrait/square shapes (9:16 at 1080p is 1080x1920). Aspect, fit, codec and quality don't change the price.

Input parameters:

- `aspect` (string): Shape of the exported video; project (default) keeps the project's own frame. 9:16 / 4:5 for Reels, Shorts and TikTok
- `codec` (string): h264 (default; plays everywhere) or h265 (HEVC: ~40% smaller files, slower to render)
- `fit` (string): When the aspect differs from the project's: fill (default) center-crops the picture, fit shows all of it with black bars
- `projectId` (string, required)
- `quality` (string): standard (default) or high (less compression, bigger file)
- `resolution` (string)

### `credits.get_balance` (~57 tokens)

Get the credit balance of the project's owner, and what a render costs, in milli-credits (1000 = 1 credit). Check this before starting a render if the balance may be low.

Input parameters:

- `projectId` (string, required)

### `credits.list_history` (~120 tokens)

List the project owner's credit history, newest first: purchases, assistant usage, renders and AI generations, each with its signed amount in milli-credits (1000 = 1 credit; negative = spent), balance after, detail (model, resolution, tokens…) and the project it was for. Also returns net spend per category over the last 30 days. Pass nextCursor back as cursor for older entries.

Input parameters:

- `category` (string)
- `cursor` (string)
- `limit` (integer)
- `projectId` (string, required)

### `render.status` (~26 tokens)

Check the status/progress of a render job

Input parameters:

- `jobId` (string, required)

### `render.get_result` (~60 tokens)

Get a completed render job's result: the output assetId and a downloadUrl for the rendered file — a plain HTTP GET, no auth header needed, valid 24h (call again for a fresh one)

Input parameters:

- `jobId` (string, required)

### `render.list_for_project` (~32 tokens)

List every render job ever started for a project, most recent first

Input parameters:

- `projectId` (string, required)

### `render.delete` (~41 tokens)

Remove a render job from the project's export list. If it finished, its output file is deleted too. Cannot be undone.

Input parameters:

- `jobId` (string, required)

### `asset.upload` (~82 tokens)

Upload a video, audio or image file into a project's media library. Send the file bytes as base64 (max 50 MB; larger files must be uploaded in the browser). Returns the new assetId.

Input parameters:

- `contentBase64` (string, required)
- `filename` (string, required)
- `mimeType` (string, required)
- `projectId` (string, required)

### `asset.capture_frame` (~86 tokens)

Grab one frame of a video asset (e.g. a take) as a new PNG image asset. timeMs is the position in the video itself, not on the timeline. Save the result with shot.add_still, location.add_reference or character.add_reference.

Input parameters:

- `assetId` (string, required)
- `projectId` (string, required)
- `timeMs` (number, required)

### `prompt.draft` (~94 tokens)

Draft three alternative generation prompts for a scene's asset (metered in credits unless the owner uses their own Anthropic key). Returns the variants; attach one to a scene with prompt.attach.

Input parameters:

- `assetType` (string, required)
- `currentText` (string)
- `guidance` (string, required)
- `projectId` (string, required)
- `sceneSummary` (string)
- `sceneTitle` (string)

### `shot.draft` (~99 tokens)

Draft a shot list for one scene — shot sizes, angles, movement, lens, f-stop, focus — from the scene, the film look and the cast (metered in credits unless the owner uses their own Anthropic key). Returns drafts only; create the ones you want with shot.create.

Input parameters:

- `count` (integer)
- `guidance` (string)
- `projectId` (string, required)
- `sceneId` (string, required)

### `storyline.suggest` (~75 tokens)

Suggest next scenes for the project's storyline from its premise (metered in credits unless the owner uses their own Anthropic key). Requires storyline.set_premise first. The suggestions become candidates; choose one with storyline.pick.

Input parameters:

- `count` (integer)
- `guidance` (string)
- `projectId` (string, required)

### `film.get_look` (~37 tokens)

Get the project's film look (style, grade, film stock, camera body, default models)

Input parameters:

- `projectId` (string, required)

### `film.update_look` (~84 tokens)

Set the project's film look (§36). Fields merge into the current look unless replace is true. Set this first: every shot prompt inherits it.

Input parameters:

- `expectedVersion` (integer, required)
- `look` (object, required): Project-wide look applied to every shot prompt. An empty string clears a field.
- `projectId` (string, required)
- `replace` (boolean)

### `generation.list_models` (~35 tokens)

List the generation models (image and video) with their capabilities and prices in milli-credits (1000 = 1 credit).

### `character.list` (~31 tokens)

List the project's cast with each character's reference images (the character map)

Input parameters:

- `projectId` (string, required)

### `character.get` (~24 tokens)

Get one character and its reference images

Input parameters:

- `characterId` (string, required)

### `character.create` (~142 tokens)

Add a recurring character to the cast. Describe appearance precisely — it drives the generated reference sheet.

Input parameters:

- `appearance` (string): Face, hair, build, age — identity details that must not drift
- `description` (string)
- `expectedVersion` (integer, required)
- `name` (string, required)
- `notes` (string)
- `projectId` (string, required)
- `role` (string)
- `voiceId` (string|null): ElevenLabs voice this character speaks with (voice.list); null clears it
- `voiceName` (string|null): The voice's display name, as voice.list gives it
- `wardrobe` (string)

### `character.update` (~141 tokens)

Update a character's name, description or voice

Input parameters:

- `appearance` (string): Face, hair, build, age — identity details that must not drift
- `characterId` (string, required)
- `description` (string)
- `expectedVersion` (integer, required)
- `name` (string)
- `notes` (string)
- `projectId` (string, required)
- `role` (string)
- `voiceId` (string|null): ElevenLabs voice this character speaks with (voice.list); null clears it
- `voiceName` (string|null): The voice's display name, as voice.list gives it
- `wardrobe` (string)

### `character.set_primary` (~56 tokens)

Choose which reference image anchors the character's identity in generated views and shots

Input parameters:

- `characterId` (string, required)
- `expectedVersion` (integer, required)
- `projectId` (string, required)
- `referenceId` (string, required)

### `character.delete` (~45 tokens)

Remove a character (and its reference sheet) from the cast

Input parameters:

- `characterId` (string, required)
- `expectedVersion` (integer, required)
- `projectId` (string, required)

### `character.add_reference` (~97 tokens)

Attach an image asset (e.g. an uploaded photo via asset.upload) to a character as one view of its character map. The first reference becomes the identity anchor.

Input parameters:

- `assetId` (string, required)
- `characterId` (string, required)
- `expectedVersion` (integer, required)
- `label` (string)
- `makePrimary` (boolean)
- `projectId` (string, required)
- `view` (string, required)

### `character.remove_reference` (~43 tokens)

Remove one reference image from a character's map

Input parameters:

- `expectedVersion` (integer, required)
- `projectId` (string, required)
- `referenceId` (string, required)

### `character.generate_sheet` (~141 tokens)

Generate the character map (front, ¾ left/right, profile, back, full body, close-up) with an image model, keeping one identity. With no reference yet, a front portrait is generated first from the description. Costs credits per image (see generation.list_models), charged to the project owner. Runs in the background — poll generation.list. Views the character already has are skipped unless listed in views.

Input parameters:

- `characterId` (string, required)
- `imageModel` (string)
- `label` (string): Free-text pose/expression for a custom or expression view
- `projectId` (string, required)
- `views` (array)

### `character.generate_view` (~75 tokens)

Generate (or regenerate) one view of a character's map, e.g. an expression. Costs credits, charged to the project owner.

Input parameters:

- `characterId` (string, required)
- `imageModel` (string)
- `label` (string)
- `projectId` (string, required)
- `view` (string, required)

### `location.list` (~28 tokens)

List the project's location library with each location's reference plates

Input parameters:

- `projectId` (string, required)

### `location.get` (~24 tokens)

Get one location and its reference plates

Input parameters:

- `locationId` (string, required)

### `location.create` (~100 tokens)

Add a recurring location (setting) to the library. Describe it precisely — it drives the generated plates. Assign it to scenes with scene.update locationId; shots inherit it.

Input parameters:

- `description` (string): Architecture, layout, materials, props, weather — what must look the same in every shot set here
- `expectedVersion` (integer, required)
- `name` (string, required)
- `notes` (string)
- `projectId` (string, required)

### `location.update` (~81 tokens)

Update a location's name or description

Input parameters:

- `description` (string): Architecture, layout, materials, props, weather — what must look the same in every shot set here
- `expectedVersion` (integer, required)
- `locationId` (string, required)
- `name` (string)
- `notes` (string)
- `projectId` (string, required)

### `location.delete` (~55 tokens)

Remove a location (and its plates) from the library. Scenes and shots set there fall back to text only.

Input parameters:

- `expectedVersion` (integer, required)
- `locationId` (string, required)
- `projectId` (string, required)

### `location.add_reference` (~88 tokens)

Attach an image asset (e.g. an uploaded photo via asset.upload) to a location as one of its reference plates (wide, reverse, detail or custom)

Input parameters:

- `assetId` (string, required)
- `expectedVersion` (integer, required)
- `label` (string)
- `locationId` (string, required)
- `projectId` (string, required)
- `view` (string, required)

### `location.remove_reference` (~42 tokens)

Remove one reference plate from a location

Input parameters:

- `expectedVersion` (integer, required)
- `locationReferenceId` (string, required)
- `projectId` (string, required)

### `location.generate_plates` (~128 tokens)

Generate a location's reference plates (wide, reverse angle, detail) with an image model, keeping one place. With no plate yet, the first is drawn from the description. Costs credits per image (see generation.list_models), charged to the project owner. Runs in the background — poll generation.list. Views the location already has are skipped unless listed in views.

Input parameters:

- `imageModel` (string)
- `label` (string): Free-text angle for a custom view
- `locationId` (string, required)
- `projectId` (string, required)
- `views` (array)

### `shot.list` (~41 tokens)

List shots (with camera settings) for one scene, or for the whole project

Input parameters:

- `projectId` (string, required)
- `sceneId` (string)

### `shot.get` (~20 tokens)

Get one shot

Input parameters:

- `shotId` (string, required)

### `shot.create` (~403 tokens)

Add a shot to a scene with camera direction (§38). Each shot gets its own video clip on the timeline; the scene's length becomes the sum of its shots and later clips ripple. The first shot of a scene takes over the scene's existing video placeholder.

Input parameters:

- `action` (string): What happens during the shot (used for video)
- `aspectRatio`: This shot's frame shape (null = the film look's, else the project's). Stills use it; the video take follows its start frame
- `camera` (object): Physical camera settings. Unset fields are left to the model.
- `cameraAngle`
- `cameraMovement`
- `characterIds` (array): Cast members in frame — their reference images keep them consistent
- `composition` (string): e.g. "rule of thirds, subject frame left, negative space right"
- `description` (string): What the frame shows
- `dialogue` (string): Spoken line(s); prefix with the speaker's name ("ANNA: …") so shot.lipsync knows who says it
- `expectedVersion` (integer, required)
- `generateAudio` (boolean): Ask the video model for native audio (costs more)
- `lighting` (object)
- `locationId` (string|null): Override the scene's location for this shot (null = where the scene is)
- `order` (integer): Position within the scene (default: last)
- `plannedDurationMs` (integer)
- `projectId` (string, required)
- `sceneId` (string, required)
- `seed`
- `shotSize`
- `speakerCharacterId` (string|null): Who speaks the dialogue (null = the character it names, else the first cast member with a voice)
- `videoModel` (string|null)
- `videoResolution`: Video output resolution (null = the model's default; only some models offer a choice, and higher costs more)

### `shot.update` (~544 tokens)

Change a shot's story, cast, framing, camera rig, lighting, reference videos or duration (a duration change ripples later clips)

Input parameters:

- `action` (string): What happens during the shot (used for video)
- `aspectRatio`: This shot's frame shape (null = the film look's, else the project's). Stills use it; the video take follows its start frame
- `camera` (object): Physical camera settings. Unset fields are left to the model.
- `cameraAngle`
- `cameraMovement`
- `characterIds` (array): Cast members in frame — their reference images keep them consistent
- `composition` (string): e.g. "rule of thirds, subject frame left, negative space right"
- `description` (string): What the frame shows
- `dialogue` (string): Spoken line(s); prefix with the speaker's name ("ANNA: …") so shot.lipsync knows who says it
- `endFrameAssetId` (string|null)
- `expectedVersion` (integer, required)
- `generateAudio` (boolean): Ask the video model for native audio (costs more)
- `lighting` (object)
- `locationId` (string|null): Override the scene's location for this shot (null = where the scene is)
- `plannedDurationMs` (integer)
- `projectId` (string, required)
- `referenceVideoAssetIds` (array): Video assets (uploads or earlier takes) whose motion and camera the shot follows; replaces the list ([] clears it). Only reference_to_video models use them — generation.list_models shows each model's…
- `referenceVideoMode` (string): follow (default): make a new clip copying the reference's motion and camera. edit: change the first reference clip itself and keep the rest — write the change in the description (e.g. "Replace the ma…
- `seed`
- `shotId` (string, required)
- `shotSize`
- `speakerCharacterId` (string|null): Who speaks the dialogue (null = the character it names, else the first cast member with a voice)
- `startFrameAssetId` (string|null)
- `videoModel` (string|null)
- `videoResolution`: Video output resolution (null = the model's default; only some models offer a choice, and higher costs more)

### `shot.delete` (~58 tokens)

Delete a shot; later clips close up. Deleting a scene's last shot keeps its clip as the scene's picture slot.

Input parameters:

- `expectedVersion` (integer, required)
- `projectId` (string, required)
- `shotId` (string, required)

### `shot.reorder` (~64 tokens)

Move a shot to a new position within its scene (its clips are re-laid out in the new order)

Input parameters:

- `expectedVersion` (integer, required)
- `newOrder` (integer, required)
- `projectId` (string, required)
- `shotId` (string, required)

### `shot.compile_prompt` (~90 tokens)

Preview exactly what would be sent to the generation model for a shot — compiled prompt, reference images and videos, duration and cost. ignoredReferenceVideos counts the shot's reference videos the model won't receive; referenceVideoMode is follow or edit; problem says why shot.generate_video would refuse. Free.

Input parameters:

- `model` (string)
- `shotId` (string, required)
- `target` (string, required)

### `shot.generate_keyframe` (~93 tokens)

Generate keyframe image variants for a shot from its camera direction, cast references and location plates. The first variant becomes the start frame if the shot has none. Costs credits per image, charged to the project owner. Runs in the background — poll generation.list.

Input parameters:

- `model` (string)
- `numImages` (integer)
- `projectId` (string, required)
- `shotId` (string, required)

### `shot.select_keyframe` (~69 tokens)

Use an image asset (usually a keyframe variant) as the shot's start or end frame

Input parameters:

- `assetId` (string, required)
- `expectedVersion` (integer, required)
- `projectId` (string, required)
- `shotId` (string, required)
- `which` (string)

### `shot.generate_video` (~155 tokens)

Generate a video take for a shot using its camera movement, action and cast. An image_to_video model animates the start frame (shot.generate_keyframe first); a reference_to_video model needs no start frame and follows the shot's reference videos (shot.update referenceVideoAssetIds), using the keyframe as its opening image when there is one. With referenceVideoMode edit it changes the first clip itself instead (e.g. replaces a person with a cast character). Costs credits per second, charged to the project owner. The first take fills the shot's timeline clip; later takes wait for shot.select_take.

Input parameters:

- `model` (string)
- `projectId` (string, required)
- `shotId` (string, required)

### `shot.select_take` (~56 tokens)

Put a generated take (video asset) on the shot's timeline clip

Input parameters:

- `assetId` (string, required)
- `expectedVersion` (integer, required)
- `projectId` (string, required)
- `shotId` (string, required)

### `shot.add_still` (~105 tokens)

Add an existing image asset (e.g. a frame from asset.capture_frame, or an upload) to a shot's stills, free of charge. asStartFrame makes it the frame the video animates from; a shot without a start frame always gets it.

Input parameters:

- `asStartFrame` (boolean)
- `assetId` (string, required)
- `expectedVersion` (integer, required)
- `projectId` (string, required)
- `shotId` (string, required)

### `shot.remove_keyframe` (~79 tokens)

Remove a generated still (keyframe asset) from a shot. If it was the shot's start or end frame, that frame is cleared. Undoable; credits are not refunded.

Input parameters:

- `assetId` (string, required)
- `expectedVersion` (integer, required)
- `projectId` (string, required)
- `shotId` (string, required)

### `music.compile_prompt` (~168 tokens)

Preview what music.generate would send to Lyria for a placeholder — prompt, length, model and cost. Free.

Input parameters:

- `instrumental` (boolean)
- `lyrics` (string): Words to sing, with optional [Verse]/[Chorus] tags. Ignored when instrumental
- `model` (string): lyria-3-clip (30 s) or lyria-3.5 (full song); defaults by the clip's length
- `placeholderId` (string, required): A music or ambience placeholder on an audio track (timeline.add_placeholder; scenario.apply_to_timeline makes a "Score" one)
- `projectId` (string, required)
- `prompt` (string): Genre, mood, instruments, tempo. Defaults to the clip's prompt, then the scene's music prompt

### `music.generate` (~205 tokens)

Generate a music track with Google Lyria (the model behind Flow Music) for a music/ambience placeholder, sized to the clip. Costs credits per track, charged to the project owner. Runs in the background — poll generation.list with placeholderId. The finished track fills the clip (undoable).

Input parameters:

- `instrumental` (boolean)
- `lyrics` (string): Words to sing, with optional [Verse]/[Chorus] tags. Ignored when instrumental
- `model` (string): lyria-3-clip (30 s) or lyria-3.5 (full song); defaults by the clip's length
- `placeholderId` (string, required): A music or ambience placeholder on an audio track (timeline.add_placeholder; scenario.apply_to_timeline makes a "Score" one)
- `projectId` (string, required)
- `prompt` (string): Genre, mood, instruments, tempo. Defaults to the clip's prompt, then the scene's music prompt

### `voice.list` (~37 tokens)

List the ElevenLabs voices characters and voice clips can speak with (id, name, labels like gender/accent, a preview URL). Free.

### `voice.compile` (~158 tokens)

Preview what voice.generate would speak for a voice placeholder — text, voice, model and cost. Free.

Input parameters:

- `characterId` (string): Speak in this character's voice
- `model` (string): eleven-multilingual-v2 (default), eleven-v3 (most expressive) or eleven-flash-v2.5 (cheapest)
- `placeholderId` (string, required): A voice placeholder on an audio track (timeline.add_placeholder with kind voice)
- `projectId` (string, required)
- `text` (string): The words to speak. Defaults to the clip's prompt, then the scene's voice prompt
- `voiceId` (string): ElevenLabs voice (voice.list). Defaults to characterId's voice, then a narrator voice

### `voice.generate` (~193 tokens)

Speak a line with ElevenLabs for a voice placeholder (narration, off-screen dialogue — no lip-sync). Costs credits per character, charged to the project owner. Runs in the background — poll generation.list with placeholderId. The finished audio fills the clip (undoable).

Input parameters:

- `characterId` (string): Speak in this character's voice
- `model` (string): eleven-multilingual-v2 (default), eleven-v3 (most expressive) or eleven-flash-v2.5 (cheapest)
- `placeholderId` (string, required): A voice placeholder on an audio track (timeline.add_placeholder with kind voice)
- `projectId` (string, required)
- `text` (string): The words to speak. Defaults to the clip's prompt, then the scene's voice prompt
- `voiceId` (string): ElevenLabs voice (voice.list). Defaults to characterId's voice, then a narrator voice

### `shot.lipsync` (~295 tokens)

Give a shot's take spoken dialogue with matching lips: ElevenLabs speaks the line in the speaker's voice (character.update voiceId), then a lip-sync model reworks the take's mouth to it. Works with any video model; best on close and medium shots with one visible face. The result is a new take with the line as its sound; it replaces the source take in the clip if that's still there (undoable). Costs credits (speech per character + lip-sync per second). Poll generation.list with shotId.

Input parameters:

- `dryRun` (boolean): Only preview the speaker, voice, line and cost; nothing is charged
- `model` (string): sync-lipsync-2 (default), sync-lipsync-2-pro (sharper, costlier) or kling-lipsync (2-10 s takes only, cheapest)
- `projectId` (string, required)
- `shotId` (string, required)
- `speechModel` (string): eleven-multilingual-v2 (default), eleven-v3 or eleven-flash-v2.5
- `takeAssetId` (string): The take to rework (a video from generation.list). Defaults to the take in the shot's clip
- `text` (string): The words to speak. Defaults to the shot's dialogue without its speaker label
- `voiceId` (string): Override the speaker's voice (voice.list)

### `shot.revoice` (~219 tokens)

Re-voice a take that has native speech (made with generateAudio on a model like Seedance 2.5, Kling O3 or Wan 3): ElevenLabs' voice changer converts the speech to the speaker's voice and keeps its timing, so the lips still match. One voice for the whole track — for single-speaker shots; ambience in the take may change. The result is a new take (replaces the source in the clip if it's there; undoable). Costs credits per minute of audio. Poll generation.list with shotId.

Input parameters:

- `dryRun` (boolean): Only preview the speaker, voice, line and cost; nothing is charged
- `model` (string): eleven-sts-v2 (default)
- `projectId` (string, required)
- `shotId` (string, required)
- `takeAssetId` (string): The take to rework (a video from generation.list). Defaults to the take in the shot's clip
- `voiceId` (string): Override the speaker's voice (voice.list)

### `generation.list` (~106 tokens)

List generation jobs (character views, location plates, keyframes, takes, lip-synced/re-voiced takes, music, voice lines) for a project, newest first, optionally for one shot, character, location or music/voice placeholder. outputAssetIds are the results.

Input parameters:

- `characterId` (string)
- `locationId` (string)
- `placeholderId` (string)
- `projectId` (string, required)
- `shotId` (string)

### `generation.status` (~28 tokens)

Get one generation job's status, progress and outputs

Input parameters:

- `generationJobId` (string, required)

### `generation.cancel` (~34 tokens)

Cancel a queued or running generation. A job that hasn't reached the provider is refunded.

Input parameters:

- `generationJobId` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/one-cutclip-cutclip/api-mcp#diagnostics

## Score history

- 2026-11-21: 75
- 2026-11-20: 75
- 2026-11-19: 74
- 2026-11-18: 74
- 2026-11-17: 73
- 2026-11-16: 73
- 2026-11-15: 72
- 2026-11-14: 72
- 2026-11-13: 71
- 2026-11-12: 71
- 2026-11-11: 70
- 2026-11-10: 70
- 2026-11-09: 70
- 2026-11-08: 69
- 2026-11-07: 68
- 2026-11-06: 33

## Common questions

### What is the CutClip.one MCP server?

CutClip.one is an MCP server listed in the public MCP registry as one.cutclip/cutclip. AI video editor your agent can drive: plan scenes, edit a multi-track timeline, and render MP4s. This page covers its hosted endpoint (https://cutclip.one/api/mcp).

### Is the CutClip.one MCP server safe to use?

CutClip.one scores 75 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the CutClip.one MCP server expose?

CutClip.one exposes 111 tools: project.create, project.list_for_owner, project.update, project.delete, project.get_state, and 106 more. Their descriptions and schemas cost roughly 10,614 tokens of context every time the server is loaded.

### Does the CutClip.one MCP server require authentication?

Yes. CutClip.one asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the CutClip.one MCP server still maintained?

CutClip.one is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the CutClip.one MCP server?

VerifyMCP ran 13 checks on CutClip.one, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://cutclip.one/api/mcp
- Authorisation metadata: https://cutclip.one/.well-known/oauth-protected-resource/api/mcp
- Repository: https://github.com/leovegas/cutclip-mcp
- Website: https://www.cutclip.one/
- Changelog RSS feed: https://verifymcp.io/servers/one-cutclip-cutclip/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/one-cutclip-cutclip/api-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/one-cutclip-cutclip/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/one-cutclip-cutclip/api-mcp
