Premiere Pro MCP Server

Plan Beat Montage

plan_beat_montage

Read-onlyIdempotent

Convert beat detection timings into a shot plan: cut every N beats, assign available clips, and output add-to-timeline batches with trim ranges and cut markers—without altering the Premiere project.

Instructions

Plan a beat-synced montage: carve a detect_beats grid into shots every N beats (merging short and splitting long spans), assign clips in order, and emit add_to_timeline_batch chunks, trim ranges, and cut markers. Local-only and deterministic; never changes Premiere.

Input Schema

TableJSON Schema

Name	Required	Description
`clips`	Yes	Source clips available for the montage, in the caller's preferred order.
`order`	No	Clip assignment order; defaults to as_given. round_robin interleaves priority groups.
`frame_rate`	No	Sequence frame rate used to snap shot boundaries; defaults to 30.
`allow_reuse`	No	When true, cycle through clips again once they run out (continuing from where each stopped); otherwise the montage stops.
`beat_seconds`	Yes	Strictly ascending beat times in sequence seconds, such as beatTimesSeconds from detect_beats.
`max_shot_seconds`	No	Longer spans split at intermediate beats; defaults to 6.
`min_shot_seconds`	No	Shorter spans merge with the next beats; defaults to 0.4.
`start_beat_index`	No	Index of the first beat to cut on; defaults to 0.
`audio_track_index`	No	Target audio track for linked audio; defaults to 0.
`cut_every_n_beats`	No	Beats per shot; defaults to 2.
`video_track_index`	No	Target video track for every placement; defaults to 0.
`total_duration_seconds`	No	Optional cap on montage length measured from the first cut.

Output Schema

TableJSON Schema

Name	Required	Description
`ok`	Yes	Whether the tool completed successfully.
`data`	No	Tool-specific result data when ok is true.
`tool`	Yes	The registered MCP tool name.
`error`	No	Failure detail when ok is false.

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.14.9Sep 8, 2026

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark the tool as read-only, idempotent, and non-destructive; the description adds value by stating 'Local-only and deterministic' and 'never changes Premiere', reinforcing the safety profile and clarifying determinism for planning output. It contributes context beyond the structured annotations without contradicting them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is one dense sentence with no filler; the core purpose is front-loaded, and each clause adds a distinct piece of behavior (grid carving, clip assignment, output artifacts, non-mutation). It earns its length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-parameter, planning-only tool with a full input schema and an output schema, the description covers the algorithm, output, and safety, and the schema covers parameter details. It could add an explicit dependency note on detect_beats or a pointer to add_to_timeline_batch, but these are already implied and partially documented in the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema description coverage, the schema already defines each parameter, so the description only needs to add algorithmic meaning. It does this by explaining the shot carving rule ('every N beats', 'merging short and splitting long spans') and the assignment order concept, which maps to cut_every_n_beats, min_shot_seconds/max_shot_seconds, and order.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description leads with a specific verb and resource ('Plan a beat-synced montage') and then details the exact behavior: carving a detect_beats grid into shots, assigning clips, and emitting add_to_timeline_batch chunks, trim ranges, and cut markers. This clearly distinguishes it from related planning tools and from detect_beats/add_to_timeline_batch.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description makes the planning-only, no-mutation role explicit via 'never changes Premiere', which routes an agent away from apply-style tools. It also references detect_beats as the source of the beat grid, implying it should follow beat detection and precede timeline application, though it does not explicitly name the apply alternative or state when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server