# CutLuma video editor (remote · cutluma.com)

Free online video editor: search tools, guides and templates, video sizes, pricing, editor links.

- Trust score: 70/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

> **Recent critical change**: Authorization (2026-10-14). See the changelog below before you install this server.

## Components

- remote · `cutluma.com`: 70/100 (this document), [markdown](https://verifymcp.io/servers/com-cutluma-video-editor/cutluma.md), [page](https://verifymcp.io/servers/com-cutluma-video-editor/cutluma)

## Channel facts

- Endpoint: `https://cutluma.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- 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 2026-10-23.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (edit_project).
  - 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**: 80/100
  - 99% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 8505 tokens (~57/item across 147 items; 25 tools + 122 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 43/100
  - Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 87/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 60% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 25 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 27 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 CutLuma video editor MCP server?

CutLuma video editor is a hosted endpoint at https://cutluma.com/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 com-cutluma-video-editor 'https://cutluma.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-cutluma-video-editor": {
      "url": "https://cutluma.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-cutluma-video-editor": {
      "type": "http",
      "url": "https://cutluma.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-cutluma-video-editor]
url = "https://cutluma.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-cutluma-video-editor": {
      "type": "remote",
      "url": "https://cutluma.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-cutluma-video-editor --url 'https://cutluma.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-cutluma-video-editor:
    url: "https://cutluma.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-cutluma-video-editor": {
      "Transport": "http",
      "Url": "https://cutluma.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-cutluma-video-editor -t streamable-http -u 'https://cutluma.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-cutluma-video-editor": {
      "type": "http",
      "url": "https://cutluma.com/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.

### 2026-10-22 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-20 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-18 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-15 (score 67, +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.

### 2026-10-14 (score 66, −6)

- [critical regression] Authorization: partial → fail
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] New tool “edit_project”, which the server declares destructive
- [security] Tool “list_free_tools” rewrote its description, which is the text the model reads
- [security] Tool “make_editor_link” rewrote its description, which is the text the model reads
- [security] Tool “search_cutluma” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 50 → 57
- [functional improvement] Tool coverage: 47% → 60%
- [functional] New resource “ai-agent-video-editor”
- [functional] New resource “audio-loudness-normalizer”
- [functional] New resource “blur-video-background”
- [functional] New resource “change-color-in-video”
- [functional] New resource “color-grading-online”
- [functional] New resource “color-pop-video”
- [functional] New resource “freeze-frame-intro”
- [functional] New resource “how-much-does-youtube-pay”
- [functional] New resource “how-to-become-a-ugc-creator”
- [functional] New resource “how-to-create-and-sell-an-online-course”
- [functional] New resource “how-to-make-money-with-video”
- [functional] New resource “how-to-monetize-a-video-podcast”
- [functional] New resource “how-to-start-a-clipping-business”
- [functional] New resource “how-to-start-a-faceless-youtube-channel”
- [functional] New resource “how-to-start-a-freelance-video-editing-business”
- [functional] New resource “how-to-start-a-social-media-video-agency”
- [functional] New resource “knowledge-base-software”
- [functional] New resource “linkedin-video-for-b2b-leads”
- [functional] New resource “magnify-video”
- [functional] New resource “motion-tracking”
- [functional] New resource “multicam-video-editor”
- [functional] New resource “multilingual-video-business”
- [functional] New resource “polish-video-narration”
- [functional] New resource “product-video-ads-for-online-stores”
- [functional] New resource “real-estate-video-business”
- [functional] New resource “screen-recording-to-guide”
- [functional] New resource “short-video-monetization-tiktok-reels-shorts”
- [functional] New resource “sop-generator”
- [functional] New resource “text-behind-video”
- [functional] New resource “video-affiliate-marketing”
- [functional] New resource “video-content-repurposing-system”
- [functional] Server version: 1.0.0 → 1.1.0
- [functional] New tool “connect_editor”
- [functional] New tool “create_project”
- [functional] New tool “export_video”
- [functional] New tool “get_job”
- [functional] New tool “get_media_levels”
- [functional] New tool “get_media_transcript”
- [functional] New tool “get_project”
- [functional] New tool “get_transcript”
- [functional] New tool “list_edit_ops”
- [functional] New tool “list_media”
- [functional] New tool “list_projects”
- [functional] New tool “video_business_playbooks”
- [functional] New tool “view_contact_sheet”
- [functional] New tool “view_frame”
- [functional] New tool “view_media”
- [functional] New tool “view_media_frame”
- [cosmetic] “search_cutluma” reworded the description of “kind”

### 2026-10-13 (score 72, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “find_templates” rewrote its description, which is the text the model reads
- [security] Tool “list_free_tools” rewrote its description, which is the text the model reads
- [security] Tool “make_editor_link” rewrote its description, which is the text the model reads
- [security] Tool “search_cutluma” rewrote its description, which is the text the model reads
- [functional regression] Resource “ai-video-editor-with-prompts” was removed
- [functional regression] Resource “ai-video-upscaler” was removed
- [functional regression] Resource “extend-video-with-ai” was removed
- [functional regression] Resource “remove-object-from-video” was removed
- [functional] New resource “how-to-edit-videos-on-a-chromebook”
- [functional] New resource “how-to-make-a-linkedin-video”
- [functional] New resource “how-to-make-a-wedding-invitation-video”
- [functional] New resource “how-to-make-an-ai-video-from-text”
- [functional] New resource “how-to-speed-up-a-video-online”
- [functional] New resource “how-to-translate-a-video”
- [functional] New resource “how-to-use-green-screen-online”

### 2026-10-12 (score 72, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “find_templates” rewrote its description, which is the text the model reads
- [security] Tool “list_free_tools” rewrote its description, which is the text the model reads
- [security] Tool “make_editor_link” rewrote its description, which is the text the model reads
- [security] Tool “search_cutluma” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 4226 → 4826
- [functional improvement] Stability: unverified → 0.07
- [functional] New resource “ai-video-editor-with-prompts”
- [functional] New resource “ai-video-generator”
- [functional] New resource “ai-video-upscaler”
- [functional] New resource “extend-video-with-ai”
- [functional] New resource “how-to-make-ai-b-roll”
- [functional] New resource “image-to-video”
- [functional] New resource “remove-object-from-video”
- [functional] New resource “translate-video”
- [functional] New resource “youtube-to-shorts”

### 2026-10-10 (score 71)

First indexed and scored.

## MCP tools (25)

### `search_cutluma` (~167 tokens)

Search CutLuma

Search CutLuma's free online video tools, "video editor for <platform>" pages, how-to guides (video sizes, subtitles, screen recording, shorts…), the video business playbooks (how to earn from video: clipping, YouTube, UGC, courses, podcasts…) and 5030 animated video templates. Returns matching pages with links, a Markdown URL for the full text and, where it applies, a link that opens the editor with that tool or template ready.

Input parameters:

- `kind` (string): "guide" covers the how-to guides and the video business playbooks
- `limit` (integer)
- `query` (string, required): What the user wants to do or find, e.g. "add Arabic subtitles", "TikTok size", "sale template"

### `get_page` (~81 tokens)

Read a page as Markdown

Read any CutLuma content page as Markdown: "/" (overview, plans, features), "/tools", "/tools/<slug>", "/video-editor", "/video-editor/<slug>", "/guides", "/guides/<slug>", "/templates", "/templates/<id>".

Input parameters:

- `path` (string, required): Path such as /guides/social-media-video-sizes

### `list_free_tools` (~61 tokens)

List the free tools

All 68 single-purpose tools (captions, screen recorder, resize, trim, remove silence, add music, green screen, GIF maker…) with what each does, whether it is free or part of the paid plans, and the link that opens it.

### `find_templates` (~372 tokens)

Find video templates

Find animated video templates by keyword, format (9:16 for TikTok/Reels/Shorts, 1:1, 4:5, 16:9 for YouTube), category (Trending formats, Social posts, Hooks & intros, Lists & tips, Tutorials & courses, Stats & data, Quotes & stories, Sales & business, Real estate, Construction, Medical & health, Product & launch, Creators, Food & drink, Fitness & wellness, Fashion & beauty, Travel, Music & nightlife, Events, Holidays, Education & school, Kids & family, Gaming & esports, Tech & SaaS, Finance & money, Cars & automotive, Sports, Pets & animals, Home & interior, Hotels & hospitality, Nonprofit & causes, Local services, News & media, Weddings & love, Corporate & HR, Memes & humor, Faith & spirituality, Science & nature, Art & photography, Books & writing, Film & entertainment, Government & public info, 中文 · Chinese, हिन्दी · Hindi, Español · Spanish, عربي · Arabic, Français · French, বাংলা · Bengali, Português · Portuguese, Русский · Russian, Bahasa Indonesia · Indonesian, اردو · Urdu, Deutsch · German, 日本語 · Japanese, Türkçe · Turkish, 한국어 · Korean) or language (en, zh, hi, es, ar, fr, bn, pt, ru, id, ur, de, ja, tr, ko). Each result has an "open" link that loads it in the editor.

Input parameters:

- `arabic` (boolean): true: Arabic right-to-left templates only
- `category` (string)
- `format` (string)
- `language` (string): only templates written in this language
- `limit` (integer)
- `query` (string)

### `video_size_guide` (~70 tokens)

Video sizes per platform

Recommended aspect ratio and pixel size for YouTube, Shorts, TikTok, Instagram Reels/Stories/feed, Facebook, LinkedIn and X, with safe-zone advice for vertical video.

Input parameters:

- `platform` (string): Optional filter, e.g. "tiktok", "instagram reels", "youtube"

### `video_business_playbooks` (~174 tokens)

Video business playbooks

CutLuma's series of researched guides on earning money with video (start here, service business, channel business, platform income, platform payouts, retainer service, local service, digital product, commission income, audience business, localization service, ad creative, operating system, lead generation). Without arguments: every part with its business model, key facts and takeaways. With "topic": the parts that match (e.g. "clipping", "YouTube pay", "UGC", "real estate", "course", "affiliate", "podcast", "translate"). Each part cites its sources; read the full text with get_page. Figures are published ranges and worked examples, not promises of income.

Input parameters:

- `topic` (string): Optional: what the user wants to earn from or which model they ask about

### `make_editor_link` (~205 tokens)

Build an editor link

A link the user can open to start right away in the CutLuma editor with a tool or template ready. tool is one of: captions, record, resize, silence, shorts, product, testimonials, trim, text, music, montage, camera, voice, speed, tts, translate, greenscreen, cutout, prompter, stock, textvideo, magicdesign, aiimage, bgremove, magicedit, visualizer, charts, industry, effects, translatedesign, localize, transcript, dub, publish, present, open, subtitles, textbehind, tracking, subjectfx, colorchange, freezeintro, guide, hub, narration, agent, grade, mixer, multicam. language is a two-letter code for captions (e.g. "ar", "es"). With neither, a blank project opens.

Input parameters:

- `language` (string)
- `template` (string): Template id from find_templates
- `tool` (string)

### `get_pricing` (~40 tokens)

Plans and prices

Current CutLuma plans with price, billing interval, limits and what each includes. The editor is free; AI features are part of the paid plans.

### `get_shared_video` (~56 tokens)

Look up a shared video

Details of a video shared with a CutLuma link (cutluma.com/watch?v=…): title, kind, size, length, direct file, embed and thumbnail URLs.

Input parameters:

- `url` (string, required): The share link

### `list_projects` (~44 tokens)

List my video projects

The signed-in user's CutLuma projects, newest first, with ids, sizes and durations. Needs the user's sign-in or an agent key.

Input parameters:

- `limit` (integer)

### `create_project` (~100 tokens)

Create a video project

Start an empty project. format: 16:9 (YouTube), 9:16 (TikTok, Reels, Shorts), 1:1, 4:5 or 21:9; or give width and height. Returns the id and the link the user opens so you can edit it.

Input parameters:

- `format` (string)
- `height` (integer)
- `name` (string)
- `width` (integer)

### `get_project` (~65 tokens)

Read a project’s timeline

Tracks (top to bottom) and every clip with id, kind, start and duration in seconds, as last saved. Use before editing. full=true also lists caption clips.

Input parameters:

- `full` (boolean)
- `project` (string, required): Project id from list_projects or create_project

### `list_media` (~53 tokens)

List my media library

Videos, images and sounds the user has uploaded or recorded: id, name, kind, duration. Put one on the timeline with the addMedia op.

Input parameters:

- `kind` (string)
- `limit` (integer)

### `get_transcript` (~82 tokens)

Read what is said in a project

The spoken words of the project’s clips placed on the timeline (start/end in seconds), when the clips have been transcribed. If this is empty, get_media_transcript transcribes a file (also one that is not on the timeline yet), or run the addCaptions op.

Input parameters:

- `project` (string, required): Project id from list_projects or create_project

### `connect_editor` (~52 tokens)

Check the editor connection

Whether an editor tab is listening for this project. If not, returns the link the user must open. Editing, frames and export need it.

Input parameters:

- `project` (string, required): Project id from list_projects or create_project

### `list_edit_ops` (~65 tokens)

List every edit command

The full catalogue of ops the open editor can run (name, arguments, meaning): text, captions, trims, colour grading, sound, effects, AI tools… Call once per session before edit_project.

Input parameters:

- `project` (string, required): Project id from list_projects or create_project

### `edit_project` (~115 tokens)

Edit the project

Run one or more ops from list_edit_ops in order, as one undo step. Returns what changed (or why an op failed) and the new timeline. Times are seconds; clip ids come from get_project. Ops that only measure (loudness, scopes) return their data here too.

Input parameters:

- `actions` (array, required)
- `confirm` (boolean): Set true to run ops that normally wait for a person’s click (delete everything, share).
- `project` (string, required): Project id from list_projects or create_project

### `view_frame` (~143 tokens)

Look at a frame

The composited picture at a time, as a JPEG, so you can check framing, text, colour and layout. Moves the playhead there. With clip, that one clip alone (its crop, grade and effects, nothing in front of it or behind it) — also the way to see a multicam angle that is not on air.

Input parameters:

- `clip` (string): A clip id from get_project (or part of its name): show that clip alone
- `project` (string, required): Project id from list_projects or create_project
- `time` (number, required): Seconds from the start
- `width` (integer): Picture width in pixels (default 640)

### `view_contact_sheet` (~145 tokens)

Look at the whole video at once

A grid of frames across the project (or between from and to), each stamped with its time. The quickest way to review an edit. Give times to see exact moments instead (both sides of every cut, say); give clip to see one clip alone across its length.

Input parameters:

- `clip` (string): A clip id from get_project (or part of its name): show that clip alone
- `count` (integer)
- `from` (number)
- `project` (string, required): Project id from list_projects or create_project
- `times` (array): Exact times in seconds to show, instead of from / to / count
- `to` (number)

### `view_media` (~160 tokens)

Look at a file before using it

A contact sheet of a video in the media library (or the picture itself, for an image): frames across the file, each stamped with its time in the file, without putting it on the timeline. Use it to find the part worth using in a long recording: look at the whole file, then closer with from / to, then view_media_frame for one moment. Runs in the open editor.

Input parameters:

- `count` (integer)
- `from` (number): Seconds into the file
- `media` (string, required): Media id from list_media, or the file name
- `project` (string, required): Project id from list_projects or create_project
- `times` (array): Exact times in the file to show
- `to` (number)

### `view_media_frame` (~101 tokens)

Look at one frame of a file

One frame of a library video at a time in the file (or a library image), as a JPEG: the file itself, with no crop, grade or titles.

Input parameters:

- `media` (string, required): Media id from list_media, or the file name
- `project` (string, required): Project id from list_projects or create_project
- `time` (number): Seconds into the file
- `width` (integer): Picture width in pixels (default 640)

### `get_media_transcript` (~241 tokens)

Read what is said in a file

The words said in a library video or sound file, in lines with their times in the file (seconds), whether or not it is on the timeline. COST: a stretch that was not heard before is transcribed now with the user’s AI time (paid plans): one AI minute per minute of sound, silence is free. What was heard is kept, so asking again, or captioning the file once it is on the timeline, costs nothing more — the result says how many AI seconds this call used and which stretches are known. Give from / to to listen to part of a long file (get_media_levels shows where there is sound, for free). A long stretch answers with a job id: poll get_job.

Input parameters:

- `from` (number): Seconds into the file (default: its start)
- `language` (string): Spoken language code such as en, ar, es (default: detect)
- `media` (string, required): Media id from list_media, or the file name
- `project` (string, required): Project id from list_projects or create_project
- `to` (number): Seconds into the file (default: its end)

### `get_media_levels` (~160 tokens)

Hear a file as numbers

Loudness over time of a library video or sound file: RMS in dBFS per step (−100 = silence), the quiet stretches (pauses, dead air) and the loudest moments (a clap, laughter, applause), all in seconds of the file. Finds where the talking is without transcribing. Free. A long file takes a while the first time: it may answer with a job id (poll get_job).

Input parameters:

- `from` (number)
- `media` (string, required): Media id from list_media, or the file name
- `project` (string, required): Project id from list_projects or create_project
- `step` (number): Seconds per reading (default: about 300 readings)
- `to` (number)

### `export_video` (~120 tokens)

Export the finished video

Render the project to MP4 in the user’s editor, save it to their library and return a share link. Takes about as long as the video, so this returns a job id at once: poll get_job. The plan’s limits apply (Free: 1080p with a watermark).

Input parameters:

- `fps` (integer)
- `project` (string, required): Project id from list_projects or create_project
- `quality` (string)
- `resolution` (integer)
- `share` (boolean): Also make a public watch link (default true)

### `get_job` (~38 tokens)

Check a running job

Status (queued, running, done, failed) and result of an export or any call that answered "running".

Input parameters:

- `job` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-cutluma-video-editor/cutluma#diagnostics

## Score history

- 2026-10-23: 70
- 2026-10-22: 70
- 2026-10-21: 69
- 2026-10-20: 69
- 2026-10-19: 68
- 2026-10-18: 68
- 2026-10-17: 67
- 2026-10-16: 67
- 2026-10-15: 67
- 2026-10-14: 66
- 2026-10-13: 72
- 2026-10-12: 72
- 2026-10-10: 71

## Common questions

### What is the CutLuma video editor MCP server?

CutLuma video editor is an MCP server listed in the public MCP registry as com.cutluma/video-editor. Free online video editor: search tools, guides and templates, video sizes, pricing, editor links. This page covers its hosted endpoint (https://cutluma.com/mcp).

### Is the CutLuma video editor MCP server safe to use?

CutLuma video editor scores 70 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 CutLuma video editor MCP server expose?

CutLuma video editor exposes 25 tools: search_cutluma, get_page, list_free_tools, find_templates, video_size_guide, and 20 more. Their descriptions and schemas cost roughly 2,910 tokens of context every time the server is loaded.

### Does the CutLuma video editor MCP server require authentication?

No. We connected to CutLuma video editor without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the CutLuma video editor MCP server still maintained?

CutLuma video editor is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://cutluma.com/mcp
- Website: https://cutluma.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-cutluma-video-editor/cutluma.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-cutluma-video-editor/cutluma.json
- HTML version of this page: https://verifymcp.io/servers/com-cutluma-video-editor/cutluma