Beat Cutter v1.0.0

Video & audio beat-cutter 2 actions MCP

Cut a folder or zip of video clips into a hard-cut, beat-synced montage. Set a BPM (or detect one from an optional music track) and it assembles a video of a target length from randomly chosen clip segments, muxing in the music if given. Images inside a zip are skipped automatically.

Open in Omniscient Back to apps

The omniscient:// link needs a protocol handler on your machine, which is not built yet. Until then it does nothing — use the commands below.

Actions

Jump to: generatedetect_bpm

Generate montage

generate

Cut a source zip/folder of video clips into a beat-synced montage of a target length.

Inputs

Name	Type	Required / default	Values and notes
`source`	path	required
`audio`	path	optional, default `""`
`bpm`	float	optional, default `120.0`
`beats_per_cut`	enum	optional, default `4`	`124816`
`align_to_beats`	bool	optional, default `false`
`duration`	float	optional, default `60.0`
`resolution`	enum	optional, default `vertical`	`verticalhorizontalsquareauto`
`fps`	int	optional, default `30`
`shuffle`	bool	optional, default `true`
`avoid_repeat`	bool	optional, default `true`
`seed`	int	optional
`keep_intermediate`	bool	optional, default `false`
`work_dir`	path	optional, default `""`
`out`	path	optional, default `""`

Outputs

Name	Type	Notes
`file`	path
`cuts`	int
`bpm_used`	float

Detect BPM from audio

detect_bpm

Estimate the tempo and beat timing of a music track using a built-in onset/autocorrelation detector (numpy only, no extra model download).

Inputs

Name	Type	Required / default	Values and notes
`audio`	path	required

Outputs

Name	Type	Notes
`bpm`	float
`beat_count`	int

Use it

Generate montage

Command line

shell

python app.py --action generate --params '{"source": "D:/path/to/source"}'

Run from the app’s own folder. Single quotes work in bash and PowerShell; in cmd.exe use double quotes and escape the inner ones.

MCP tool

mcp

run_action("beat-cutter", "generate", {"source": "D:/path/to/source"})

Workflow node

json

{
  "id": "n0",
  "app": "beat-cutter",
  "action": "generate",
  "params": {
    "source": "D:/path/to/source"
  },
  "inputs": {}
}

Detect BPM from audio

Command line

shell

python app.py --action detect_bpm --params '{"audio": "D:/path/to/audio"}'

Run from the app’s own folder. Single quotes work in bash and PowerShell; in cmd.exe use double quotes and escape the inner ones.

MCP tool

mcp

run_action("beat-cutter", "detect_bpm", {"audio": "D:/path/to/audio"})

Workflow node

json

{
  "id": "n0",
  "app": "beat-cutter",
  "action": "detect_bpm",
  "params": {
    "audio": "D:/path/to/audio"
  },
  "inputs": {}
}

Example prompts

Things you can say to Claude, Cursor or Codex once the MCP server is registered.

cut clips.zip into a 60 second 128bpm vertical montage
detect the bpm of track.mp3
make a beat-synced reel from D:/pexels_export at 90bpm, 2 beats per cut