Premiere Pro MCP Server

Prepare Transcript Workflow

prepare_transcript_workflow

Destructive

Check UXP transcript readiness and optionally start Speech-to-Text once per confirmed operation; returns accepted, pending, ready, failed, or unknown status with revision.

Instructions

Inspect native UXP transcript readiness before optionally starting Speech-to-Text once per operation. Returns accepted/pending/ready/failed/unknown with revision, never transcript completion from start acceptance. No CEP fallback; Adobe privacy/service preferences apply to explicitly confirmed start.

Input Schema

Name	Required	Description
`language`	No	Optional approved host language.
`operation_id`	Yes	Stable workflow operation ID, reused for inspection only after start.
`wait_seconds`	No	Bounded readiness wait, default0; never repeats native start.
`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 one HTTP session) and held in memory only (200 keys, 1 hour); it does not survive a restart or reconnect. Read-only invocations are never deduplicated.
`project_item_id`	Yes	Exact source project-item ID.
`start_if_missing`	No	Allow one native start after confirmed absence; defaultfalse.
`confirm_destructive`	No	Required true for native start; Adobe services may be used.
`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.
`expected_transcript_revision`	No	Optional prior revision; changes return review_required.

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.

Changed2 schema fields changedv1.25.0Oct 24, 2026

addedInput schema / properties / idempotency_key

Added value: +{
+  "description": "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 one HTTP session) and held in memory only (200 keys, 1 hour); it does not survive a restart or reconnect. Read-only invocations are never deduplicated.",
+  "maxLength": 128,
+  "minLength": 1,
+  "pattern": "^[A-Za-z0-9._:-]+$",
+  "type": "string"
+}

addedOutput schema / properties / idempotency

Added value: +{
+  "additionalProperties": true,
+  "description": "Present when idempotency_key deduplicated this call: replayed is true when the original outcome was returned instead of running again.",
+  "type": "object"
+}

Addedv1.24.0Oct 12, 2026

TDQS

A4.7/5.0

Behavior5/5

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

The annotations already mark this as destructive and non-read-only, and the description adds important behavior: the returned status set, revision, that start acceptance does not mean transcript completion, once-per-operation semantics, no CEP fallback, and Adobe privacy/service implications for confirmed start.

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 compact sentences front-load the purpose, then add return-state and constraint caveats. Every sentence carries operational information, and there is no filler.

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?

For a destructive optional-start workflow with 10 parameters, nested CEP guards, and an output schema, the description supplies the essential caveats an agent needs before calling. The remaining parameter and return details are adequately covered by the rich input schema and output 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?

Schema coverage is 100%, so a baseline of 3 is appropriate, but the description adds cross-parameter context: 'once per operation' relates to operation_id, 'explicitly confirmed start' relates to confirm_destructive, and 'No CEP fallback' relates to the CEP-only expected_cep_target guard.

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 action and scope: inspect native UXP transcript readiness, with an optional one-time Speech-to-Text start. It also names the CEP fallback constraint, giving an agent a concrete way to distinguish this workflow from unrelated sibling tools.

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 clearly frames the use case as inspecting readiness before optionally starting Speech-to-Text, and notes that start requires explicit confirmation and is once per operation. It does not explicitly name alternatives or give a strong when-not-to-use rule beyond the no-CEP-fallback constraint.

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

Deploy Server