OpenEdit
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENEDIT_HOST | No | Force a specific host. Supported values: premiere, resolve, or standalone. If not set, OpenEdit automatically uses the standalone ffmpeg host when neither editor is open. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
You are editing video with OpenEdit (local, open-source tools; no uploads). Standard workflow:
editor_status — see which editor is connected (Premiere, Resolve, or standalone ffmpeg). Use select_host to change.
transcribe {path} — read the timestamped transcript. Note retakes, rambling, off-topic parts.
plan_cuts {path, removeSilences, removeFillers, removeRetakes, manualCuts} — manualCuts are ranges YOU choose from the transcript (e.g. a flubbed sentence, a tangent).
show_plan {planId} — review the cuts with the user (quote what gets removed, time saved). Adjust and re-plan if asked. Do not apply without the user's OK on non-trivial edits.
apply_cuts {planId} — builds a NEW sequence in the editor (the original is never modified).
make_captions {planId, style} — captions timed to the cut edit (styles: clean, bold-pop, minimal).
auto_zooms {planId} or add_zooms — punch-ins to hide jump cuts / add emphasis.
Optional: place_clips (b-roll, music with duckDb, SFX), render_motion (titles / lower thirds), add_markers.
render {output, reframe?: "9:16" for shorts, loudnorm: true} — in standalone mode this produces the final mp4. All times are seconds. Times for markers, zooms, captions and placements are on the EDITED timeline (after cuts).
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| editor_statusA | Show which video editor OpenEdit is driving (premiere, resolve, or standalone ffmpeg), whether it is connected, and the active project/sequence. Call this first. |
| select_hostA | Choose the editor to drive: "premiere" (needs the OpenEdit panel open in Premiere Pro), "resolve" (DaVinci Resolve running with scripting enabled), "standalone" (no editor; edits are rendered with ffmpeg), or "auto" to re-detect. |
| get_timelineA | List the clips, tracks and markers of the active sequence/timeline in the current editor. |
| probe_mediaA | Get duration, resolution, frame rate and audio/video presence of a media file. |
| transcribeA | Transcribe speech locally with whisper.cpp (word-level timestamps). Returns the transcript as lines prefixed with [mm:ss.s] start times, plus the path of the full word-level JSON. Cached per file+model. If path is omitted, uses the active timeline's source media. |
| find_silencesB | Find silent/dead-air ranges in a file's audio (ffmpeg silencedetect). |
| plan_cutsA | Build a cut plan (which parts of the source to keep) from silences, filler words (um/uh…), retakes (restarted sentences) and your own manualCuts chosen from the transcript. Nothing is changed in the editor yet: returns a planId and a summary to review with the user, then call apply_cuts. |
| show_planB | Show every cut in a plan with what was said in it, plus the kept segments, for review before applying. |
| apply_cutsA | Apply a cut plan in the active editor. Premiere/Resolve: creates a NEW sequence with only the kept ranges (original untouched). Standalone: sets the timeline that render will export. |
| make_captionsA | Create captions from the transcript and add them to the active editor. Pass planId to time captions to the CUT edit (use the same plan you applied), or path for an uncut file. Writes .srt, .vtt and .ass files. Styles: clean (white with outline), bold-pop (big uppercase, active word highlighted), minimal (small boxed). |
| add_markersA | Add sequence markers (edited-timeline seconds), e.g. chapter points, highlights, or notes for the user. |
| add_zoomsA | Add zoom/punch-in effects on the main camera over edited-timeline ranges (for emphasis or to hide jump cuts). |
| auto_zoomsA | Automatic punch-ins for a cut edit: alternates framing between 100% and |
| import_mediaB | Import media files into the editor's project (bin "OpenEdit"). In standalone mode, the first video imported becomes the timeline source. |
| place_clipsB | Place clips on the timeline at edited-timeline times: b-roll/images on upper video tracks (track 2+), music and sound effects on audio tracks. Standalone extras: duration (images), duckDb (lower music under speech by ~N dB), loop, fadeOut. |
| renderA | Export the edited timeline to a file. Standalone: one ffmpeg pass with cuts, zooms, b-roll, music, captions, optional vertical reframe and loudness normalisation. Premiere/Resolve: queues the editor's own export (reframe/burnCaptions/loudnorm are standalone-only). |
| motion_templatesA | List motion-graphics templates (titles, lower thirds, callouts…) and their parameters for render_motion. |
| render_motionC | Render a motion-graphics template to a video file (.mov with alpha by default) and optionally place it on the timeline at |
| render_caption_overlayB | Render animated captions as a transparent video overlay (.mov with alpha) that can be placed over the edit in any editor. Use planId to time it to the cut edit. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| auto_edit | Standard OpenEdit workflow: transcribe, plan cuts, review, apply, captions, zooms, render. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 19 tools
Most tools target a clearly distinct step of the editing pipeline (inspect → transcribe → plan → apply → embellish → render), and descriptions explicitly disambiguate close pairs like add_zooms vs auto_zooms and render vs render_motion. The only mild overlap is around captions (make_captions adds captions in the editor, render_caption_overlay bakes a transparent overlay video), which descriptions mostly resolve but an agent could still pause over.
The dominant pattern is consistent snake_case verb_noun (find_silences, plan_cuts, apply_cuts, add_markers, place_clips, import_media). A few deviations exist — verb-only names (transcribe, render) and noun-only names (editor_status, motion_templates) — but they remain readable and predictable within the set.
19 tools is on the heavy side but each maps to a distinct capability in a genuinely broad workflow (editor selection, analysis, cut planning, captions, zooms, media placement, rendering, motion graphics). Nothing looks redundant enough to be a filler tool, though a couple of render variants push the surface toward the upper bound.
The lifecycle is well covered end-to-end: session/host setup, media probing, transcription, silence/filler analysis, plan review, cut application, captions, markers, zooms, b-roll/music placement, and both editor-queued and standalone rendering. Minor gaps remain: no way to undo/revert an applied cut or remove markers/zooms, and no tool to list or delete previously created plans.