premiere-pro-mcp

Overview Schema Source Related Servers Discussions Admin

Plan Active Speaker Reframe

plan_active_speaker_reframe

Read-onlyIdempotent

Plans active-speaker vertical reframes or static stacked/split layouts from word timings and speaker regions, returning framings, switches, keyframes, and apply routes without changing Premiere.

Instructions

Plan an active-speaker vertical reframe (Motion Scale/Position keyframes that follow whoever is talking) or a static stacked/split layout from a word timeline and static speaker regions. Returns framings, switches, keyframes, and apply routes. Local-only; never changes Premiere.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "word_timeline": "<word_timeline>",
      "source_frame": "<source_frame>",
      "speaker_regions": "<speaker_regions>"
    },
    "name": "plan_active_speaker_reframe"
  }
}

Input Schema

Name	Required	Description
`layout`	No	auto (default) picks active_speaker for 3+ speakers or a region wider than 0.6, stacked for exactly 2 speakers.
`headroom`	No	Fraction of the crop height reserved above the region top; defaults to 0.12.
`frame_rate`	No	Sequence frame rate used to snap times to frames; defaults to 30.
`ease_frames`	No	Frames to ease each switch with bezier keyframes; 0 (default) emits hold keyframes (hard cuts).
`source_frame`	Yes	Source clip frame size in pixels, e.g. 1920x1080 or 3840x2160.
`target_frame`	No	Target sequence frame size in pixels; defaults to 1080x1920.
`word_timeline`	Yes	Caller-supplied word-timed transcript for one Premiere source item. Words must be ordered by start time and bound to the transcript revision returned by get_clip_transcript_uxp. Different labeled speakers may overlap; same-speaker words may not, even when another speaker is between them.
`speaker_regions`	Yes	Normalized (0..1) face/body rectangle of every speaker that appears, measured in the source frame.
`min_hold_seconds`	No	Never switch faster than this; shorter turns are absorbed. Defaults to 1.5.
`expected_cep_target`	No	Optional reviewed CEP sequence/clip identity and exact tick ranges. Checked before every generated command; UXP refuses this CEP-only guard.
`switch_lead_seconds`	No	Switch this long before the speaker starts; defaults to 0.15.
`expected_project_path`	No	Optional absolute saved-project path. Every generated CEP command refuses before its body when the active project differs or is unsaved. UXP commands refuse this CEP-only guard; local-only tools do not inspect Premiere. Omit to keep existing behavior.
`base_video_track_index`	No	Video track holding the source clip in the target sequence; defaults to 0.

Output 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.
`receipt`	No	Versioned common mutation receipt; success never implies rendered verification.
`idempotency`	No	Present when idempotency_key deduplicated this call: replayed is true when the original outcome was returned instead of running again.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.30.0Nov 14, 2026

TDQS

A3.8/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so safety is largely covered. The description usefully reinforces 'Local-only; never changes Premiere' and reveals that the output includes apply routes, but adds nothing about validation failures, timeline/revision checks, or determinism guarantees.

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?

Three tight sentences: purpose and modes first, outputs second, side-effect guarantee last. Nothing is repeated and there is no filler.

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 an output schema present the description needn't explain return values, and it correctly focuses on scope, inputs, and non-mutation. Given 13 parameters and the transcript-revision binding constraint, a sentence pointing at prerequisites (transcript revision from get_clip_transcript_uxp) would close the remaining gap.

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 coverage is 100%, so every parameter, including layout's auto-selection rule and the speaker_regions normalization, is already documented. The description only restates the two headline inputs (word timeline, speaker regions) and the layout dichotomy, adding little beyond the schema.

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

Purpose4/5

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

States a specific verb and resource ('Plan an active-speaker vertical reframe ... or a static stacked/split layout') and sketches the concrete output (Motion Scale/Position keyframes, stacked/split layout). It does not name the near neighbours it competes with (auto_reframe_sequence, plan_speaker_checkerboard, compute_mask_fit_motion), so sibling differentiation is left implicit.

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?

Gives clear preconditions for use (from a word timeline plus static speaker regions) and clarifies that this is a planning-only call whose output feeds an apply route. No explicit when-not-use or named alternatives, so it stops short of a 5.

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

Deploy Server