Fcpxml MCP Server

Find ultra-short clips (flash frames) that are likely errors, with severity categorization

Find unintentional gaps in the timeline

Detect REAL silence by analyzing each clip's source audio with ffmpeg silencedetect, mapped into timeline time. Unlike detect_silence_candidates (XML-only heuristics), this reads the actual media files referenced by the timeline. Requires ffmpeg; clips whose media is missing or unreadable are reported, not failed.

Detect potential silence/dead air using timeline heuristics (gaps, ultra-short clips, name patterns, duration anomalies)

Compare two FCPXML files and report differences in clips, markers, transitions, and format

Text-based editing: cut timeline content by what was SAID. mode=remove cuts every occurrence of the given phrases (with ripple); mode=keep_only keeps only the matched phrases and cuts everything else in each matched clip (clips with no matches are left untouched). Uses each media file's _transcript.json (auto-transcribes if missing). Non-destructive: writes a _transcript_edit copy.

Export timeline data to CSV format

Generate EDL (Edit Decision List) from timeline

Export timeline as FCP7 XML (XMEML) for Premiere Pro, DaVinci Resolve, and Avid compatibility

Export timeline as DaVinci Resolve compatible FCPXML (simplified v1.9)

Export clip list grouped by role for audio mixing stem planning

Automatically fill gaps in the timeline by extending adjacent clips

List all clips matching a specific audio or video role

Find clips longer than threshold

Find clips shorter than threshold (flash frame detection)

Automatically fix detected flash frames by extending neighbors or deleting

Flatten a compound clip back into individual clips in the spine

Create documentary-style A/B roll edits alternating between main content and cutaways

Create rapid-fire montages with pacing curves (accelerating, decelerating, pyramid)

Import beat markers from external audio analysis (JSON format)

Import SRT or VTT subtitles as chapter markers on the timeline

Import timestamped transcript (YouTube chapter format) as markers. Supports '0:00 Title' and 'HH:MM:SS Title' formats

Insert a library clip onto the timeline at a specific position

List all clips with timecodes, durations, and metadata

List compound clips (ref-clips) and their nested content

List all connected clips (B-roll, titles, audio) with their lanes and parent clips

List all available FCP transition effects with slugs and UUIDs

LIVE: enumerate the running Final Cut Pro's open libraries, events, and projects via Apple's read-only scripting dictionary. Refuses to launch FCP unless allow_launch is true. macOS-only.

Extract all keywords/tags from project

List all available clips in the library (source media, not yet on timeline)

Extract markers (chapter, todo, standard) with timestamps

List all FCPXML projects in directory

List all audio/video roles used in the timeline with clip counts

List available timeline templates with slot definitions

LIVE: send an FCPXML file into the running Final Cut Pro with zero clicks (official Open Document Apple event), then VERIFY the import actually landed. macOS-only; first use triggers an Automation permission prompt. Pass library_location ending in .fcpbundle to target a library (a path that does not exist yet is created by FCP). Omit it and the target is inferred only when exactly one library is open; with several open, or none, the call refuses and names them rather than guessing. Verification polls FCP until the document's project names appear in the target, so the call can block up to verif…

Batch trim clips to a maximum duration for fast-paced montages

Create new FCPXML with different resolution/aspect ratio (9:16 for TikTok, 1:1 for Instagram, etc.)

Bulk-rewrite media source paths (asset/media-rep src URLs) to relink moved or renamed media folders without opening FCP. Prefix-based: find='/Volumes/OldDrive/Media' replace='/Volumes/NewDrive/Media'. Use dry_run to preview.

Cut filler words (um, uh, erm...) out of the timeline with ripple, using word-level transcripts of the real source audio. Conservative default filler list — words like 'like' and 'so' are only cut if you pass them explicitly. Uses each media file's _transcript.json (auto-transcribes if missing). Non-destructive: writes a _defillered copy.

Detect REAL silence in each clip's source audio (ffmpeg) and CUT it out of the timeline with ripple. Clips are split around silence; the silent middles are removed and everything after shifts earlier. Non-destructive: writes a _silence_removed copy. Preview with detect_media_silence first.

Remove or mark detected silence candidates from timeline

Move clips to a new position in the timeline

Align cuts to nearest beat markers for music-synced edits. Works on spine cuts and on connected clips lane by lane (a music video keeps its whole edit on lanes). Moving a connected clip does not ripple the clips after it; a move that would collide with a neighbour in the same lane is skipped and reported.

Split a clip at specified timecodes

Transcribe each clip's source media locally with word-level timestamps (faster-whisper). Writes a _transcript.json next to each media file (reused by edit_by_transcript / remove_filler_words so media is only transcribed once) and optionally an SRT for captions. Requires the optional [transcribe] extra; degrades to an install hint without it.

The whole shoot on one page: every clip's transcript packed into one document — a header per source, one line per utterance, broken on silence or a speaker change, audio events inline. Built for planning an edit from what was said. Uses each media file's _transcript.json / the index (auto-transcribes if missing). Truncated at 60KB; write=true saves the full pack as <project>_pack.md beside the FCPXML.

Trim a clip's in-point and/or out-point

Comprehensive timeline health check for flash frames, gaps, duplicates, and issues