Premiere Pro MCP Server

Build Caption Artifact

build_caption_artifact

Generate SRT or VTT caption files from word timings with balanced groups, karaoke timestamps, and speaker markup. Works locally without altering Premiere.

Instructions

Build a CapCut/Submagic-style SRT or VTT caption artifact from a caller-supplied word timeline: balanced word groups, sentence-aware breaks, min/max cue durations, optional karaoke word timestamps (VTT), emphasis and speaker markup. Local-only; returns the artifact inline or writes it inside an approved workspace and never changes Premiere.

Input Schema

TableJSON Schema

Name	Required	Description
`format`	Yes	Artifact format. SRT uses HH:MM:SS,mmm; VTT starts with WEBVTT and uses HH:MM:SS.mmm.
`karaoke`	No	VTT only: emit per-word <HH:MM:SS.mmm> timestamps inside each cue for word-highlight styles. Errors for SRT.
`max_lines`	No	Maximum lines of plain caption text per cue (default 1); markup does not add lines.
`uppercase`	No	Render caption text in upper case.
`output_path`	No	Optional absolute file path to write the artifact to. Requires approved_workspace_path; the file must not already exist. When omitted the artifact text is returned inline (up to 512 KiB).
`style_preset`	No	Style descriptor to return with the artifact (default clean). Documentation only; not encoded in SRT/VTT.
`strip_fillers`	No	Tokens removed from the caption text (case-insensitive, punctuation ignored).
`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.
`words_per_cue`	No	Target words per cue (default 4); sentences are split into balanced groups of at most this many words.
`emphasis_words`	No	Words wrapped in <b> (SRT) or <c.emphasis> (VTT).
`speaker_prefix`	No	Prefix cues with the speaker label when present: 'Speaker: ' in SRT, <v Speaker> in VTT.
`max_cue_seconds`	No	Maximum cue duration (default 5).
`min_cue_seconds`	No	Minimum cue duration (default 0.5); short cues are extended but never past the next cue start.
`merge_gap_seconds`	No	Extend a cue to the next cue start when the gap is smaller than this (default 0.3) so captions do not flicker.
`max_chars_per_line`	No	Maximum characters per line of plain caption text (default 32); words are never split. Wrapping counts unescaped words only, so VTT escaping, karaoke timestamps, emphasis tags, and speaker prefixes can make the rendered line longer.
`approved_workspace_path`	No	Absolute existing directory that must contain output_path (checked via realpath of the parent directory). Required with output_path.

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."

Changed1 schema field changedv1.16.0Sep 16, 2026

changedInput schema / properties / word_timeline / description

Previous value: -"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."New value: +"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."

Addedv1.14.9Sep 8, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the sparse annotations, the description discloses that the tool is local-only, never touches Premiere, returns inline (up to 512 KiB) or writes into an approved workspace, and errors on karaoke+SRT. These are exactly the behavioral facts an agent needs and none are contradicted by the readOnlyHint=false / destructiveHint=false annotations.

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

Conciseness4/5

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

Roughly two dense sentences for a 16-parameter tool, with the core purpose front-loaded and the safety/output clause second. Efficient, though the first sentence packs a long clause list that is more enumeration than prose.

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

Completeness5/5

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 correctly does not explain return values, and it covers the write path, workspace constraint, format semantics and non-interference with Premiere. Nothing essential for correct invocation is missing.

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?

Schema coverage is 100%, so the schema already carries per-parameter detail and the baseline is 3. The description nonetheless summarizes the parameter set coherently ('balanced word groups, sentence-aware breaks, min/max cue durations, optional karaoke word timestamps, emphasis and speaker markup'), giving an agent a mental model of the knobs before opening 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 and resource ('Build a CapCut/Submagic-style SRT or VTT caption artifact') and scopes it to a caller-supplied word timeline. The 'Local-only ... never changes Premiere' clause implicitly distinguishes it from the sibling create_caption_track, which mutates the timeline.

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?

Usage is clear from context: build a standalone caption file rather than apply captions to the timeline, and 'karaoke ... Errors for SRT' tells the agent a format/option constraint up front. It never names create_caption_track or another sibling explicitly, so the alternative routing is left to inference.

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

Deploy Server