Umless MCP server
Commit Nov 10, 2026Cuts filler words, stutters, retakes, and dead air from talking-head videos and audio recordings using AI.
Also known as thoufeekx/umless
- Stars
- 1
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 10, 2026
- License
- MIT
What is Umless MCP?
Umless cuts filler words, stutters, retakes, and dead air from talking-head videos and audio recordings using AI.
Summary generated from the project's README
About Umless MCP server
Editing talking-head videos by removing filler words, stutters, and dead air is what Umless enables for content creators and developers. This open-source command-line tool automates the tedious process of trimming ums, uhs, and repeated phrases from audio and video recordings. It uses ffmpeg to handle media processing and can be run locally using whisper.cpp for transcription or via OpenRouter to access more advanced language models for detecting retakes and false starts.
Developers can integrate these capabilities into AI workflows using the MCP server, which provides two specific tools: analyze_video for inspecting cuts and Um Scores without rendering, and clean_video for generating the final edited file. Setting up the server requires an OpenRouter API key and ffmpeg on your system path. While the cloud-connected path offers precise retake detection and tighter cuts, the local mode allows for free, private processing where audio never leaves your machine.
What you can do with it
- 1Analyze video qualityAsk an AI agent to provide a transcript and an Um Score for a video file to see how much filler needs removing.
- 2Automate video editingInstruct a client to remove all stutters and dead air from a raw recording to create a polished version.
- 3Remove speech errorsRequest the removal of retakes and false starts from a demo recording using an LLM-powered workflow.
Written from the project's README. Every use case is checked against a quote from it.
Configuration
OPENROUTER_API_KEYUMLESS_WHISPER_BIN
Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablethoufeekx/umless is public and reachablegithub.com/thoufeekx/umless ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-10github.com/thoufeekx/umless ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubUmless
Record once, post today. Umless is an open-source command-line tool that cuts ums, stutters, retakes and dead air out of talking-head video and demo recordings. On our test take it turned 39.4 s into 17.5 s: 9 ums, 6 stutters and one "let me say that again" removed, with no clicks at the cuts.
Quick start · Use it from AI agents (MCP) · How it works · Hosted version · Report a bad cut
If Umless saves you an editing session, a ⭐ helps other people find it.
Quick start
You need Node 20+, ffmpeg on your PATH and an OpenRouter key. A 3-minute video costs about $0.02 in API calls. No key? See Run fully local.
export OPENROUTER_API_KEY=...
npx -y github:thoufeekx/umless my-video.mp4 # writes my-video.umless.mp4
npx -y github:thoufeekx/umless my-video.mp4 --score # Um Score only, no render
The first run builds the CLI from GitHub, so it takes a minute; later runs are cached. (npx umless without the github: prefix will work once the package is on npm.) From a clone:
git clone https://github.com/thoufeekx/umless && cd umless && npm install
npx tsx cli/umless.ts my-video.mp4
The terminal prints an Um Score (ums per minute, stutters and retakes, seconds of dead air), your transcript with every cut word struck through, and the before/after length. Audio files work too and come out as .m4a.
Run fully local (no API key)
Without OPENROUTER_API_KEY (or with UMLESS_STT=local), Umless transcribes on your machine with whisper.cpp. It's free and the audio never leaves your computer. Set it up once:
bash scripts/setup-local-whisper.sh # clones + builds whisper.cpp in ~/whisper.cpp, downloads ggml-base.en (148 MB) to ~/.cache/umless
export UMLESS_WHISPER_BIN=~/whisper.cpp/build/bin/whisper-cli
npx tsx cli/umless.ts my-video.mp4
The script needs git, a C/C++ compiler, cmake and curl. On macOS, brew install whisper-cpp also gives you whisper-cli. Other settings: UMLESS_WHISPER_MODEL (default ~/.cache/umless/ggml-base.en.bin) and UMLESS_WHISPER_THREADS (default 4).
What's different from the cloud path:
- No retake detection. Spotting "sorry, let me say that again" needs a language model, so it only runs with an OpenRouter key. Ums, stutters/repeats and dead air are still cut.
- Fewer ums caught and looser cuts. On our 39 s test take, local
base.enfound 8 of the 9 ums the cloud transcript found, and its word timings are less precise, so less dead air is removed: the take came out at 26.4 s locally vs 17.5 s with the cloud path (which also removes the retake).
What it cuts
- Filler words: um, uh, er and similar. The transcriber keeps every "um" (many speech-to-text models silently drop them).
- Stutters and repeated phrases: "the the", "so so so".
- Retakes and false starts: say a sentence twice and it keeps the last clean one.
- Dead air: long pauses shrink to a natural 0.25 s.
- Clean cuts: every boundary snaps to the quietest 10 ms nearby, with 15 ms fades, so you don't hear clicks.
On real footage
The 39 s test take above is scripted. Here are two unscripted clips from Wikimedia Commons, run through the same CLI with no hand edits:
| Clip | Before | After | What it cut |
|---|---|---|---|
| NASA astronaut Greg Chamitoff, "The Smell of Space" (public domain) | 1:30 | 1:09 (−23%) | 1 restart, 1 false start, 1 repeat, 17.7 s of dead air |
| Mick Harvey, interviewed by Andrew McMillen (CC BY 3.0) | 1:30 | 0:54 (−40%) | 2 restarts, 1 repeat, 32.2 s of dead air |
On these clips the transcriber returned very few "um" tokens, so the savings come from restarts, repeats and pauses. Sources: Chamitoff clip (NASA Johnson; no endorsement implied), Harvey clip (Andrew McMillen, CC BY 3.0, trimmed to 90 s and cut by Umless).
Use it from AI agents: MCP server and Claude skill
umless mcp starts an MCP server on stdio with two tools:
| Tool | What it does | Returns |
|---|---|---|
analyze_video(path, retakes?) |
Transcribes and finds every cut, no render | cuts[] (start, end, type: filler / repeat / retake / silence, text, reason), keep[] segments, Um Score, counts, before/after duration |
clean_video(path, out?, options?) |
Renders the cleaned file (options: retakes, studio_sound) |
output path, before/after duration, seconds saved, counts, the full cut list |
The server needs ffmpeg on the PATH and your OPENROUTER_API_KEY in its environment. Files are read from and written to the machine the server runs on.
Claude Code
claude mcp add umless -e OPENROUTER_API_KEY=$OPENROUTER_API_KEY -- npx -y github:thoufeekx/umless mcp
Or install the plugin, which adds the MCP server and the umless skill (so "remove the ums from demo.mp4" just works):
/plugin marketplace add thoufeekx/umless
/plugin install umless@umless
Claude Desktop (claude_desktop_config.json) and Cursor (~/.cursor/mcp.json or .cursor/mcp.json) use the same block:
{
"mcpServers": {
"umless": {
"command": "npx",
"args": ["-y", "github:thoufeekx/umless", "mcp"],
"env": { "OPENROUTER_API_KEY": "sk-or-..." }
}
}
}
Skill only (Claude Code, uses the CLI if the MCP server is not connected):
mkdir -p ~/.claude/skills/umless && curl -fsSL https://raw.githubusercontent.com/thoufeekx/umless/main/skills/umless/SKILL.md -o ~/.claude/skills/umless/SKILL.md
To check the server end to end on your machine: node scripts/mcp-e2e.mjs testdata/demo_raw.mp4 (calls both tools over stdio).
How it works
ffmpegpulls the audio track.- ElevenLabs Scribe v2 (through OpenRouter) transcribes it word by word with timings. A second, cheap pass (Parakeet) finds the ums Scribe skipped, and each one is cut only where the audio shows a sound between two words.
- Rules mark fillers and repeats, and an LLM (
gpt-5-miniby default) marks retakes and false starts. ffmpegrenders the kept segments into a new file.
Change the models with UMLESS_STT_MODEL, UMLESS_FILLER_MODEL (off disables the second pass) and UMLESS_LLM_MODEL. The pipeline is in lib/pipeline.ts, the CLI in cli/umless.ts, the cut-list layer in lib/cutlist.ts and the MCP server in mcp/server.ts.
To try it before using your own footage, run it on testdata/demo_raw.mp4, a 39 s take with 9 ums, 6 stutters and a retake.
Why open source
Most filler-word removers are closed. You can't see why a word was cut, and you pay per minute forever. With Umless you can read every rule, change the thresholds and run it in your own scripts and pipelines.
Don't want a terminal?
- Umless hosted: upload in the browser, plus Studio Sound and re-voicing a clean script in your own voice. Join the waitlist.
- Done-for-you: send raw recordings and get finished edits back. Your first cleanup is free.
Roadmap
npx umlesson npm (today:npx github:thoufeekx/umless)- Timeline export (FCPXML / EDL) so you can finish in Premiere, Resolve, Final Cut or Kdenlive
- A
--jsoncut list on the CLI (the MCP server already returns one)
Want one of these sooner? Open an issue or send a PR.
Contributing
Issues and PRs are welcome. If Umless cut something it shouldn't have, open an issue with the command you ran and the struck-through transcript it printed. Development and deploy notes for the hosted app are in docs/DEVELOPMENT.md.
License
MIT © 2026 ThoufeekX Labs
Umless MCP questions
What does Umless cut from videos?
It removes filler words (ums, uhs), stutters, repeated phrases, retakes, false starts, and long pauses.
Can I run Umless without an API key?
Yes, you can run it fully locally using whisper.cpp, though you will lose retake detection and get less precise cuts.
What tools are required to use the CLI?
You need Node 20+, ffmpeg on your PATH, and an OpenRouter API key for full functionality.
How does it handle audio transitions?
It uses clean cuts by snapping boundaries to the quietest 10 ms nearby with 15 ms fades to prevent clicks.