fcpxml-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENAI_BASE_URL | No | Route LLM calls through any OpenAI-compatible proxy (LiteLLM, OpenRouter, Ollama, vLLM) | |
| FCP_PROJECTS_DIR | No | Root directory for FCPXML file discovery via list_projects | ~/Movies |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| inspectB | Read a timeline or project without changing it. Use this first to understand what you are working with. Actions: list_projects, analyze_timeline, analyze_pacing, list_clips, list_markers, list_roles, list_keywords, list_effects, list_templates, list_library_clips, list_compound_clips, list_connected_clips, filter_by_role, list_keyframes, list_speed_points. |
| diagnoseA | Find problems in a timeline: gaps, flash frames, duplicates, dead air, and beat structure. Read-only. Run before editing. Actions: validate_timeline, detect_gaps, detect_duplicates, detect_flash_frames, detect_silence_candidates, detect_media_silence, detect_beats, find_short_cuts, find_long_clips, diff_timelines. |
| editB | Change clips on the timeline: insert, delete, trim, split, reorder, retime, remove silence, and attach audio, B-roll or transitions. Writes a new file. Actions: insert_clip, delete_clips, trim_clip, split_clip, reorder_clips, change_speed, rapid_trim, add_transition, add_audio, add_connected_clip, assign_role, fill_gaps, fix_flash_frames, remove_silence_candidates, remove_media_silence, set_keyframes, delete_keyframes, batch_keyframes, set_animation_curve, set_speed_curve, reset_speed. |
| markB | Add or import markers and chapters, including from SRT/VTT subtitles, transcripts, and beat analysis. Actions: add_marker, batch_add_markers, import_srt_markers, import_transcript_markers, import_beat_markers, snap_to_beats. |
| generateB | Build new timeline structure from source clips: rough cuts, montages, A/B roll, templates and compound clips. Actions: auto_rough_cut, generate_ab_roll, generate_montage, apply_template, create_compound_clip, flatten_compound_clip, import_edl_json. |
| transcriptB | Transcribe source media locally and edit the timeline by what was SAID rather than by timecode. Also removes filler words. Actions: transcribe_media, edit_by_transcript, remove_filler_words, transcript_pack. |
| deliverA | Get the edit out: export to other NLEs, CSV, EDL and stems, reformat, relink media, or push straight into a running Final Cut Pro. Exports and push refuse a cut with no rendered preview of its current state (pass confirm_unreviewed=true to ship anyway). Actions: export_csv, export_edl, export_fcp7_xml, export_resolve_xml, export_role_stems, reformat_timeline, relink_media, push_to_fcp, list_fcp_libraries. |
| previewB | See the edit without opening Final Cut Pro. Render a proxy video of the timeline, a contact sheet of every cut, a single frame, or a filmstrip-plus-waveform check read from the SOURCE MEDIA rather than from the XML. Run preview_check to confirm a fix actually landed. Actions: preview_render, preview_sheet, preview_frame, preview_check, preview_timeline. |
| watchA | Close the round-trip. Watch the Final Cut Pro export folder, detect the XML the moment it lands, and diff it against the last one seen. Pair with deliver.push_to_fcp for a full loop: push in, edit, Cmd-E, watch_pull. Actions: watch_start, watch_status, watch_stop, watch_pull. |
| indexA | The analysis cache under ~/.fcp-mcp/index.db. index_status shows what is cached and how old it is; index_build warms it for every source in a timeline (args: filepath, with_transcript); index_clear drops it. Every other tool works with the index off (FCP_MCP_INDEX=off) — this only makes the second question fast. Actions: index_status, index_build, index_clear. |
| scenesA | 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. |
| organizeA | Bulk library logging and the ledger. organize_auto proposes keywords per clip from cached captions and the transcript (apply=true writes them). Select clips with clip_name (glob), keyword and/or role, then organize_keywords (keywords, mode add|remove|replace), organize_rate (rating favorite|rejected|clear) or organize_roles (audio_role, video_role); each writes a _organized copy. history lists every recorded operation for the file's folder (limit); undo (n) moves the outputs of the last n writes into the journal's undone/ folder — it never deletes and refuses when a file changed since it was written. Actions: organize_auto, organize_keywords, organize_rate, organize_roles, history, undo. |
| findA | Natural-language shot search. find_shots (filepath, query, limit=10, visual=false, clip_name?) ranks moments by what was said (transcript), what was logged (names, keywords, notes, markers, audio events) and, when a local vision model is installed, what the frames look like — the first line of every result names which tiers answered and why one could not. find_index (captions=true, backend) warms scenes and captions and reports which clips have no transcript (it never transcribes or goes online). find_to_timeline (min_source_separation=1, output_path?) assembles the hits into a _found selects reel and reports its diversity score. Actions: find_index, find_shots, find_to_timeline. |
| viewA | See the cut inline. view_timeline(filepath, thumbnails=true, words=true) returns the timeline — lanes, clips, markers, gaps, cached transcript words and filmstrip thumbnails — as an exact rational-time JSON payload that hosts with MCP Apps render as an interactive timeline (clip details, range selection, inspect / find-similar / marker / delete buttons that call the other tools). view_clip(filepath, clip_name) is the inspect button. Read-only; edits go through edit and mark. Actions: view_timeline, view_clip. |
| genA | Generative fill, quote-then-confirm. gen_quote(provider, seconds, prompt, model?) prices a job from a dated table (fal: kling-2.5, wan-2.5; gemini: veo-3.1; runway/luma are honest stubs) and returns a quote id. gen_fill_gap(filepath, prompt, gap_index|at), gen_broll(filepath, clip_name, prompt, seconds=5, at?) and gen_extend_clip(filepath, clip_name, seconds=5) REFUSE without quote_id + confirm=true, a matching job, a key in the environment (FAL_KEY / GEMINI_API_KEY) and a price under FCP_MCP_GEN_MAX_USD (default 5). The result is probed with ffprobe for its real fps and length, saved under generated/ next to the project, attached as a connected clip with role |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| qc-check | Run a full quality control check on your timeline — flash frames, gaps, duplicates, and health score |
| youtube-chapters | Extract chapter markers formatted for YouTube descriptions |
| rough-cut | Guided rough cut generation — choose keywords, pacing, and duration |
| timeline-summary | Quick overview of a timeline — stats, pacing, and potential issues |
| cleanup | Find and fix common timeline issues — flash frames, gaps, and duplicates |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| FCP timeline app | Interactive timeline rendered by MCP Apps hosts from the view tool's results |
TDQS
Scored across 15 tools
The 15 tools are grouped into clearly labeled high-level purposes (inspect, diagnose, edit, mark, generate, etc.), but each tool bundles many overlapping sub-actions under vague verbs. The flat tool names 'inspect' and 'diagnose' overlap heavily (both read-only analysis), and 'generate' vs 'gen' (generative fill) are confusingly adjacent, as are 'scenes' vs 'index' vs 'find' which all touch indexing/scene detection.
Names are consistent in style (all lowercase single-word verb/noun groupings) but inconsistent in convention — some are plain verbs (inspect, edit, mark), some are nouns (transcript, scenes), and one is an abbreviation (gen) that nearly duplicates generate. The sub-action names inside descriptions are snake_case but the top-level tool names are not, mixing conventions.
15 tools is at the upper edge of reasonable, but this is a mega-server where only 15 names actually hide well over a hundred sub-actions, making the surface feel deceptively compact while functionally enormous. Each named tool is a mini-server rather than a task, which strains the 'one tool = one clear action' model.
The surface is remarkably complete for a Final Cut Pro XML workflow — inspection, diagnostics, editing, marking, generation, transcription, delivery, preview, watching, indexing, scene detection, organization, search, viewing, and generative fill are all covered. Lifecycle coverage from read through edit, export, round-trip and search is thorough with few obvious gaps.