NookCut
OfficialExports EDLs per frame rate, markers, and a build_timeline.lua script so the generated edit can be opened and rebuilt as an editable timeline in DaVinci Resolve.
Generates short-form video and a publish kit for Instagram Reels, including captions, titles, hashtags, and region-aware posting-time suggestions; it does not upload or post.
Generates short-form video and a publish kit for TikTok, including captions, titles, hashtags, and region-aware posting-time suggestions; it does not upload or post.
Generates short-form video and a publish kit for YouTube Shorts, including captions, titles, hashtags, and region-aware posting-time suggestions; it does not upload or post.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
NookCut
Raw recording in, finished short out. It runs fully offline and works with any AI agent.
NookCut turns a long recording (gameplay, a talk, a match, a tutorial) into a short-form video for YouTube Shorts, TikTok and Reels. It finds the moments that matter, cuts them into a story, composes original copyright-free music synced to the cuts, burns in captions, renders vertical/square/wide video, exports an editable DaVinci Resolve timeline (free edition included), and writes a publish kit with titles, hashtags and region-aware posting times.
Offline by design. No cloud services, no API keys, no accounts. Python's standard library and ffmpeg are all it needs. It never uploads or posts anything.
Works with any agent. It's an MCP server, so Claude, ChatGPT, Codex, Gemini CLI, Cursor, VS Code Copilot, local models through an MCP client, and more can drive it. Small local models can make a whole video with a single
auto_editcall.Online is optional. If you allow it, your agent can research trends with its own web search to sharpen hooks and hashtags. Nothing depends on it.
Status: alpha (0.1). It works end to end and is tested on macOS and Linux. Expect rough edges, and please report them.
Contents
Related MCP server: retention
Quick start
pipx install "nookcut[mcp] @ git+https://github.com/nookverse/nookcut.git"
nookcut check # checks ffmpeg and tells you how to fix anything missing
nookcut make ./my-short --source ~/Videos/raw.mp4 --title "Final boss, first clear" --max 45sYou get an .mp4 named after your title in ./my-short/, a publish_kit.md, and a resolve/
folder you can open in DaVinci Resolve. To let an agent do it, see Connect an agent.
Requirements
Python 3.10+
ffmpeg and ffprobe with
libx264,drawtext,minterpolate,gblurandloudnorm. Most builds include them.nookcut checktells you what's missing and how to install it:macOS:
brew install ffmpeg-full, then put it on your PATH (it's keg-only):echo 'export PATH="$(brew --prefix ffmpeg-full)/bin:$PATH"' >> ~/.zprofile. Homebrew's plainffmpegis a minimal build withoutdrawtext, so captions wouldn't work.Windows:
winget install Gyan.FFmpegDebian/Ubuntu:
sudo apt install ffmpeg
A bold font for captions. Impact is found automatically on macOS and Windows; elsewhere, set
NOOKCUT_FONTto any bold.ttf.Optional: a GPU. NookCut encodes on NVIDIA (NVENC), AMD (AMF / VA-API), Intel (Quick Sync / VA-API) or Apple (VideoToolbox) when one works, and falls back to the CPU otherwise.
Platform | Status |
macOS | Supported and tested (CI + daily use) |
Linux | Supported and tested in CI |
Windows | CLI and MCP server should work but aren't tested in CI yet; |
Install
# From GitHub (until the PyPI release)
pipx install "nookcut[mcp] @ git+https://github.com/nookverse/nookcut.git"
# Or run without installing
uvx --from "nookcut[mcp] @ git+https://github.com/nookverse/nookcut.git" nookcut-mcp
# From source
git clone https://github.com/nookverse/nookcut.git && cd nookcut
python3 -m venv .venv && .venv/bin/pip install -e ".[mcp]"The [mcp] extra installs the MCP SDK for the server. The CLI alone needs no third-party packages.
Check it worked with nookcut --version and nookcut check.
Update and uninstall
pipx upgrade nookcut # or: pipx install --force "nookcut[mcp] @ git+https://github.com/nookverse/nookcut.git"
nookcut service restart # only if you use the shared serverTo remove everything NookCut set up:
nookcut service uninstall # if you installed the shared server
claude mcp remove nookcut -s user # or remove "nookcut" from your agent's MCP config
pipx uninstall nookcut
rm -rf ~/.config/nookcut ~/.nookcut ~/.claude/skills/nookcut-editorYour project folders (videos, publish kits) are yours; delete them by hand if you want.
Connect an agent
nookcut setup claude-code # prints the exact command or config for your machine
nookcut setup all # every supported platform
nookcut skill install claude # installs the editing playbook as a skill (also: codex | agents)
nookcut skill export cursor --dir ./my-project # agents-md | gemini | cursor | windsurf | copilot | clineFor example, with Claude Code:
claude mcp add nookcut --scope user -- nookcut-mcpGemini CLI can install it as an extension: gemini extensions install https://github.com/nookverse/nookcut.
See docs/PLATFORMS.md for copy-paste setup for Claude Desktop, Cursor, Windsurf, VS Code, Cline, Codex, Zed, Goose, OpenAI Agents SDK, LangChain, ChatGPT and n8n.
Then ask your agent something like "Make a 45-second vertical short from ~/Videos/raw.mp4. It's my
first clear of the final boss." The server also ships the editing playbook as the nookcut-editor
prompt and the nookcut://skill resource, so agents without a skills system still get it.
Use it from the command line
nookcut make PROJECT --source raw.mp4 --title "..." [--game "..."] [--type gameplay|talking|sports|tutorial|generic]
[--orientation vertical|square|wide] [--max 60] [--region "United States"] [--language en]
[--platforms youtube_shorts,tiktok,instagram_reels] [--music ai|none|file] [--music-file song.mp3]
[--source-audio keep|duck|mute] [--template comeback|victory|highlights] [--name file-name] [--online]
nookcut when India # posting windows in your own time zone
nookcut copy show PROJECT # other caption, title and hashtag options
nookcut watch PROJECT # live progress of any job on that project, even one your agent started
nookcut cancel PROJECT # stop it and free the CPU at onceStep by step: new → analyze → plan → (edit edit.json) → preview → music → render → resolve.
Inputs are forgiving: --orientation 9:16, --max 1:30 and --platforms shorts,reels all work.
Exit codes: 0 ok, 1 error, 2 environment missing, 3 project busy, 130 cancelled.
MCP tools
Tool | What it does |
| Checks ffmpeg, filters, encoders and fonts; shows the install command if anything is missing |
| The whole video in one call: analyze, plan, captions, music, render, Resolve files and publish kit |
| Saves the brief (title, type, length, orientation, region, music, |
| Finds deaths, the win, action peaks and silent audio |
| Builds the edit from a story template with built-in captions |
| Offline caption options per segment, plus titles, description, hashtags and a file name |
| Read or change segments and captions |
| A contact sheet image of every segment for approval |
| Composes the original score (or masters your own track) |
| Renders the final video |
| EDLs and a Lua script that rebuild the edit in DaVinci Resolve |
| Estimated posting windows for a region, in your time zone |
|
|
| Progress (percent, stage, ETA) and instant cancel for long jobs |
Long tools accept wait=false and return a job id, so clients with short tool timeouts still work.
Every result includes a next hint, so even small models know what to call next.
What a project folder contains
my-short/
brief.json what you asked for
analysis.json detected moments
edit.json the edit: segments, speeds, captions (safe to edit by hand)
preview.png contact sheet for approval
music.wav the original score
<name>.mp4 the finished video
resolve/ EDLs per frame rate, markers and build_timeline.lua
publish_kit.md titles, description, hashtags, posting planYour source file is never modified.
Captions in other languages
English captions, titles and hashtags ship built in. For another language, create a pack and translate it:
nookcut copy init bn # writes ~/.nookcut/copy/bn.json, a copy of the English packTranslate the values (keep the keys and {slots}), then set the project's language to bn. Keys
you leave out fall back to English. Packs are plain JSON, so they work offline too.
Configuration
Variable | Default | Purpose |
| auto | Bold |
| auto | Force |
| half your cores, max 4 | Segments rendered in parallel |
|
| ffmpeg priority (0 turns lowering off) |
| unrestricted | Folders the MCP tools may read and write ( |
|
| Where your language packs live |
| none | Bearer token for the HTTP transport |
|
| Server transport settings |
Running it as a shared or remote server
One shared server for every agent session on your computer (optional):
nookcut service install # starts at login (macOS launchd / Linux systemd --user)
nookcut service connect # prints the command that connects Claude Code to it
nookcut service status | restart | uninstallIt listens on 127.0.0.1:8765 only and requires a token stored in ~/.config/nookcut/token
(readable only by you). In this mode a job keeps running if the agent session closes; stop it
with cancel_job or nookcut cancel PROJECT.
Remote (ChatGPT, n8n, web agents):
NOOKCUT_TOKEN=<long-random-string> NOOKCUT_ALLOWED_DIRS=/srv/media nookcut-mcp --transport http --host 0.0.0.0
# or with Docker (ffmpeg and a font included; experimental, the image isn't tested in CI yet)
docker build -t nookcut . && docker run -p 8765:8765 -e NOOKCUT_TOKEN=<long-random-string> -v /srv/media:/media nookcutClients connect to http://host:8765/mcp with Authorization: Bearer <token>. The server refuses
to listen off-localhost without a token. Put it behind HTTPS (a reverse proxy) before exposing it
to the internet.
How it works
Detection, no ML. The video is decoded at 2 fps to 64×36 pixels and measured: brightness, a red vignette at the screen edges, motion and loudness. A fade to black after a red damage vignette is a death; the first long fade after the last death is the win; motion and loudness peaks are highlights. Thresholds live in
analyze.DEFAULTS.Story templates.
comeback: hook → death montage with a counter → "ATTEMPT #N" → best moments → slow-mo finisher → question
victory: a win without deaths
highlights: any video, top moments in order
Each template is fitted to your length limit.
Copy. Captions, titles, descriptions and hashtags come from a built-in library, filled with facts from your brief and the analysis (death count, game name, length) and wrapped to fit the screen.
Music. A score is synthesized from scratch (taiko, pulse or cinematic), with hits on the cuts, then mastered. It uses no samples or existing recordings, so there's no source track to match.
Render. Segments render in parallel on your GPU when possible, then they're joined and mixed with the music. The original audio is ducked under it.
Privacy and security
NookCut makes no network calls. Analysis, music and rendering all happen on your computer.
It never uploads or posts. You get files and a publish kit.
The HTTP server binds to localhost by default, needs a token anywhere else, and can be fenced into specific folders with
NOOKCUT_ALLOWED_DIRS.ffmpeg runs at lower priority and every job can be cancelled instantly.
Report vulnerabilities privately; see SECURITY.md.
FAQ
See docs/FAQ.md. Short answers:
Does it need the internet? No. Every step works offline.
Do I need an API key or subscription? No.
Will the music get copyright claims? It's synthesized from scratch for each video, with no samples, so there's no existing track to match. Automated systems can still misfire now and then; if one does, you can dispute it. If you use your own track, you need the rights to it.
Does it only work for games? No. Detection is best tuned for action games, and other videos use the highlights template.
Contributing
Contributions are welcome. Read CONTRIBUTING.md and the Code of Conduct. Notes for AI coding agents working on this repo are in AGENTS.md. Release notes are in CHANGELOG.md.
License
MIT © 2026 Nookverse
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
The agentic video editor for ChatGPT and Claude. Ask in your chat and it cuts, captions, adds music, titles and motion graphics on a real timeline you can open and adjust.
Clip videos into captioned shorts, add captions, and schedule posts from AI agents.
AI video editor for agents: cut footage, add captions and motion graphics, export editable edits.
Agentic AI video editor: edit a real timeline, generate clips, music and voice, then render.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to autonomously edit videos into publish-ready vertical short-form content, including silence removal, subtitle generation, voiceover synthesis, color grading, and composite pipeline creation.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to autonomously edit raw video footage into publish-ready videos with millisecond-accurate cuts, Whisper transcription, karaoke captions, motion graphics, and high-CTR thumbnails.7 npm6MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to edit talking-head videos locally by transcribing footage, applying validated edit operations like cutting fillers and silences, adding zooms, captions, looks and branding, and checking results with rendered previews. Agents can also read pinned editor feedback notes with annotated frames, resolve them, and export MP4, SRT or OTIO while the user watches changes live.52 npm1MIT
- FlicenseNot gradedqualityAmaintenanceEnables users to turn raw clips into finished, beat-synced montage videos through natural-language chat, including shot selection, music matching, subtitles, transitions, and picture-in-picture. It lets agents analyze footage, plan and review cuts before rendering, and export final edits without a GPU or timeline editor.-