scenes
Detect shot boundaries across timeline sources, then write markers at each cut or split clips at those points. Use it to review Final Cut Pro projects and apply detected cuts as editable markers or splits.
Instructions
Shot boundaries. detect_scenes reads every source in a timeline and reports cuts in timeline time (args: filepath, clip_name?, backend auto|content|adaptive|ffmpeg, threshold?, min_scene_len=0.5); scenes_to_markers writes a marker at each cut; scenes_split cuts the clips there. PySceneDetect via the scenes extra, ffmpeg without it — the result names which one answered. Actions: detect_scenes, scenes_to_markers, scenes_split.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"action": "<action>"
},
"name": "scenes"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| args | No | Arguments for the chosen action, e.g. {"filepath": "/path/to/project.fcpxml"}. Any action that takes a filepath also accepts expected_sha256: the call refuses if the file no longer hashes to it (every write result and analyze_timeline report the current sha256). | |
| action | Yes | Which operation to run. |