Back to Browse

Demusic MCP Server

Developer ToolsModerate5.6MCP RegistryLocal
Free

Server data from the Official MCP Registry

Remove background music AI video models bake into clips; keep dialogue and SFX.

About

Remove background music AI video models bake into clips; keep dialogue and SFX.

Security Report

5.6
Moderate5.6Moderate Risk

demusic is a local CLI and MCP server that detects and removes background music from video clips using ffmpeg, Demucs, and an AudioSet ONNX classifier, with no evidence of exfiltration or backdoors. Its permissions (file read/write for media, network_http only for the one-time model download and optional fal.ai separation with a user-supplied key, process_spawn for ffmpeg/demucs) match its purpose. Minor concerns include an unpinned-by-hash model download over HTTP mirrors, the unvalidated output path in remove_music, and a mandatory attribution metadata tag that is not user-disableable. Supply chain analysis found 5 known vulnerabilities in dependencies (0 critical, 1 high severity). Package verification found 1 issue.

12 files analyzed · 11 issues found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

File System Read

Reads files on your machine. Normal for tools that analyze or process local data.

File System Write

Writes or modifies files on your machine. Check that this is expected for the tool.

process_spawn

Check that this permission is expected for this type of plugin.

HTTP Network Access

Connects to external APIs or services over the internet.

env_vars

Check that this permission is expected for this type of plugin.

What You'll Need

Set these up before or after installing:

demucs (local, needs demusic[demucs]) | fal (needs FAL_KEY) - default demucsOptional

Environment variable: DEMUSIC_SEPARATOR

Optional: your fal.ai key when DEMUSIC_SEPARATOR=falRequired

Environment variable: FAL_KEY

Path to ffmpeg (default: ffmpeg on PATH)Optional

Environment variable: DEMUSIC_FFMPEG

How to Install

Add this to your MCP configuration file:

{
  "mcpServers": {
    "demusic": {
      "command": "uvx",
      "args": [
        "demusic==0.1.0"
      ],
      "env": {
        "FAL_KEY": "your-fal-key-here",
        "DEMUSIC_FFMPEG": "your-demusic-ffmpeg-here",
        "DEMUSIC_SEPARATOR": "your-demusic-separator-here"
      }
    }
  }
}

Some servers take additional arguments. See the repository for details.

Documentation

View on GitHub

From the project's GitHub README.

demusic

tests License: Apache-2.0 MCP server

demusic removes the background music that AI video models (Seedance, Kling, Veo, Hailuo, Wan, ...) bake into generated clips, and keeps the dialogue, sound effects and ambience. It finds where the music is and only replaces the audio there, so the rest of the clip is untouched. Local, free, CLI + MCP server.

Read in Chinese · How detection works

Why

Native-audio video models often add a music bed nobody asked for: a few seconds of score at the start of a shot, a pad under the dialogue. Cut ten such clips together and you get ten pieces of music fighting each other, and you can't lay your own score over it.

The usual fix - run a vocal remover and keep only the vocals - throws away footsteps, doors, rain and room tone along with the music, and it is wrong on every clip that had no music to begin with. demusic is what we run on every clip of our AI dramas at Dawnwood:

  1. Separate the audio into stems (Demucs htdemucs_6s, locally or on your fal key).
  2. Is it loud enough to be a bed? The melodic stems must be audible (> -50 dBFS).
  3. Is it actually music? An AudioSet classifier must hear music on the accompaniment for 2+ seconds. Engine hum, gunfire and room tone pass step 2 but fail this one.
  4. Strip only those spans: there the audio becomes dialogue + percussion/impacts, with a 0.25 s crossfade; everywhere else the original audio stays. The picture is stream-copied (no re-encode).

It is deliberately conservative. On 164 clips with no music it wrongly flagged 2; on 87 clips a person had flagged by ear it found 33. The misses are very quiet beds - lower --threshold or use --mode force when you know a clip has music. Calibration details.

Install

Requires Python >= 3.10 and ffmpeg on PATH.

pip install "demusic[demucs]"     # local separation (pulls in PyTorch; CPU is fine)
# or, no torch, separation on fal.ai with your own key:
pip install "demusic[fal]" && export FAL_KEY=...

The music classifier (~90 MB ONNX, BSD-3) downloads once to ~/.cache/demusic.

Quickstart

# where is the music?
demusic check shot_012.mp4
# shot_012.mp4: MUSIC  spans 0-2.8s  melodic -42.1 dBFS  p=0.34

# write shot_012.demusic.mp4 with the music removed
demusic strip shot_012.mp4

# a whole folder; clean copies of every file (unchanged ones copied) into clean/
demusic strip renders/*.mp4 --out-dir clean/
optionmeaning
--separator demucs|fal|DIRlocal Demucs (default), fal.ai with FAL_KEY, or a folder of stems you already separated (vocals.wav, drums.wav, bass/guitar/piano/other.wav or music.wav)
--mode spans|whole|forcereplace only where music was heard (default) / the whole track if any music was heard / always, without detection
--threshold 0.3classifier music probability; 0.2 finds quieter beds at a higher false-positive rate
--loud-floor -50melodic-stem loudness gate (dBFS)
-o FILE / --out-dir DIRoutput path for one file / for a batch
--jsonone JSON object on stdout (files[] with music, spans, melodic_dbfs, strength, action, output)

Exit codes: 0 ok (for check: no music), 1 check found music, 2 usage, 3 failure. demusic check in CI or a render pipeline = fail the build when a clip has a music bed.

Speed: separation is roughly real time on a laptop CPU (a 10 s clip ~10-20 s), much faster on a GPU. Detection itself is a few hundred ms.

Python

from demusic.core import process
r = process("shot.mp4", "shot.clean.mp4")          # strip
r = process("shot.mp4", strip=False)                # check only
print(r["music"], r["spans"])

AI agents (MCP)

claude mcp add demusic -- demusic mcp            # Claude Code
# or any MCP client: command "uvx", args ["--from", "demusic[demucs]", "demusic", "mcp"]

Tools: check_music (read-only) and remove_music (writes a new file, never overwrites the input). Set DEMUSIC_SEPARATOR=fal in the server env to use fal. There is also a Claude skill and AGENTS.md.

Limits

  • Music that is meant to be in the scene (a band on screen, a radio) is removed too when it is detected. Skip those clips.
  • Inside a stripped span, non-percussive effects (a running tap, wind) go with the music; Demucs has no separate SFX stem. Outside the spans nothing changes.
  • Sung vocals land in the vocals stem and are kept.

Credit

Apache-2.0. demusic writes cleaned with demusic by Dawnwood into each output file's comment tag. If it saves you time, please keep that and mention "demusic by Dawnwood" - a request, not a condition (see NOTICE).

Made by Dawnwood, an AI drama studio. More tools we use in production: dramapack (short-drama delivery packs and QC) · all our open source.

Reviews

No reviews yet

Be the first to review this server!