premiere-pro-mcp

Overview Schema Source Related Servers Discussions Admin

Create Caption Track

create_caption_track

Import a reviewed caption artifact into the active Premiere sequence or generate a local lecture-caption timing and review plan without changing the artifact.

Instructions

Import an already reviewed caption artifact into the active sequence, or create a local lecture-caption timing and review workflow plan. Import rejects unsupported formats before host dispatch and reports structural success only when valid count readback shows exactly one new caption track. Unreadable or unexpected results preserve committed_unverified diagnostics; inspect before retrying. Captions import with Premiere's default style; styling, per-word colour, and Upgrade Caption to Graphic stay manual (get_caption_style_guidance). The planning action never contacts Premiere or changes an artifact. Caption tracks render in export_sequence by default; CEP cannot remove or hide them. Import results include observed undoSteps (null when unavailable) and reversal guidance for guarded experimental QE multiple_undo or caption mute through a capable UXP panel.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "create_caption_track"
  }
}

Input Schema

Name	Required	Description	Default
`action`	No	Use import (the default) to create a Premiere caption track, or plan_lecture_workflow for a read-only SRT/VTT timing and review plan.	import
`item_id`	No	For action import, the node ID or name of the imported caption project item (for example, an SRT file). Omit for plan_lecture_workflow.
`start_seconds`	No	For action import, offset in seconds from the start of the sequence (default: 0).
`caption_format`	No	For action import, Premiere caption format: subtitle (default), 608, 708, teletext, ebu, op42, or op47.
`artifact_format`	No	For plan_lecture_workflow, the syntax of caption_content. VTT content must include its WEBVTT header.
`caption_content`	No	For plan_lecture_workflow, the caller-owned SRT or VTT content to parse locally. The returned plan contains no caption text and does not write this artifact.
`idempotency_key`	No	Optional client-chosen key (1-128 chars of A-Z a-z 0-9 . _ : -) for this intended edit. Pass a fresh key per edit and reuse it only when retrying that same edit, for example after a client-side timeout. A repeat with the same tool, key and arguments is not run again: while the first call is running it fails with IDEMPOTENCY_IN_PROGRESS (poll get_last_operations); after it finished it returns the original outcome marked replayed. A definite failure with nothing applied (receipt outcome not_applied) may be retried with the same key. Reusing a key with different arguments fails with IDEMPOTENCY_KEY_REUSED. Scoped to this MCP session (the stdio server process, or the HTTP server process when Streamable HTTP is stateless per request) and held in memory only (200 keys, 1 hour); it does not survive a restart or reconnect. Read-only invocations are never deduplicated.
`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.
`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.
`observed_offset_seconds`	No	For plan_lecture_workflow, an editor-observed constant offset in seconds. Positive means captions currently appear later than intended; the preview proposes the inverse shift when safe.
`target_duration_seconds`	No	For plan_lecture_workflow, optional intended sequence duration. A mismatch requires review unless proportional scaling is explicitly authorized.
`timing_tolerance_seconds`	No	For plan_lecture_workflow, tolerance used to classify an offset or duration mismatch (default: 0.25 seconds).
`allow_proportional_scaling`	No	For plan_lecture_workflow, explicitly permit a bounded timing-scale preview when the artifact end does not match target_duration_seconds. This still never rewrites a caption artifact.

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

A4.4/5.0

Behavior5/5

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

Beyond the annotations, the description discloses important behavior: unsupported formats are rejected before host dispatch, success requires exactly one new caption track in readback, and unexpected results preserve committed_unverified diagnostics that should be inspected before retrying. It also explains default styling, export rendering behavior, undoSteps reporting, and reversal guidance, giving the agent substantial operational context.

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?

The description is front-loaded with the core purpose and the two operating modes, then follows with behavioral caveats. It is dense and uses some jargon such as committed_unverified diagnostics, but most sentences carry actionable information for this complex tool.

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?

Given the 13-parameter schema, nested expected_cep_target object, annotations, and an output schema, the description is complete enough for an agent to call the tool correctly. It covers action semantics, failure handling, styling boundaries, and export implications without needing to restate return values already documented by the output schema.

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?

The input schema has 100% description coverage, so parameter meaning is already well documented by the structured schema itself. The description adds useful context about the two actions and default caption styling, but it does not materially elaborate the individual parameters or their constraints beyond what the schema already provides.

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 states a specific verb and resource in both modes: importing an already reviewed caption artifact into the active sequence, or planning a local lecture-caption timing and review workflow. It clearly distinguishes the import action from the planning action and signals the boundary with sibling get_caption_style_guidance.

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?

It gives clear context for choosing import versus plan_lecture_workflow and explicitly routes styling, per-word colour, and Upgrade Caption to Graphic work to get_caption_style_guidance. It lacks explicit exclusions against sibling tools such as build_caption_artifact or retime_caption_file, though 'already reviewed' implies the artifact should be built elsewhere.

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

Deploy Server