Premiere Pro MCP Server

Plan Beat Montage

plan_beat_montage

Read-onlyIdempotent

Plan beat-synced montages: carve a beat grid into shots, assign clips in order, and output timeline batch commands, trim ranges, and cut markers without altering Premiere.

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; on failure, diagnostic detail when the tool provides it.
`tool`	Yes	The registered MCP tool name.
`error`	No	Failure detail when ok is false.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.18.6Sep 30, 2026

changedOutput schema / properties / data / description

Previous value: -"Tool-specific result data when ok is true."New value: +"Tool-specific result data when ok is true; on failure, diagnostic detail when the tool provides it."

Addedv1.14.9Sep 8, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description still adds value by declaring 'Local-only and deterministic' and describing the shape of what it produces (chunks, trim ranges, cut markers), which the annotations do not convey. It stops short of noting any limits on the beat grid or reuse behavior.

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?

Two clauses, no filler, with the core operation front-loaded before the emission and safety details. Every sentence earns its place.

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?

With 12 parameters, full schema coverage, an output schema, and annotations all present, the description gives an agent enough to call it correctly: inputs come from detect_beats, output feeds add_to_timeline_batch, nothing is mutated. It could be stronger by noting determinism guarantees or ordering defaults, but no critical gap remains.

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

Parameters3/5

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

Schema description coverage is 100% with per-field defaults, so the schema carries the parameter burden. The description maps behavior to parameters at a high level ('every N beats', 'merging short and splitting long spans', 'assign clips in order'), which helps conceptually but adds no syntax or format detail beyond the schema.

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?

States a specific verb ('Plan') and resource ('beat-synced montage'), then enumerates the exact operations: carving a detect_beats grid, assigning clips, and emitting add_to_timeline_batch chunks, trim ranges, and cut markers. It names the sibling tools it consumes and feeds, so an agent can distinguish it from detect_beats or add_to_timeline_batch without opening any schema.

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?

Implicitly routes the agent: it consumes 'a detect_beats grid' and emits 'add_to_timeline_batch chunks', telling the caller where this sits in the pipeline. It lacks an explicit when-not or a stated prerequisite on when to prefer this over manual timeline assembly, but the workflow context is clear.

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

Deploy Server