Premiere Pro MCP Server

Apply Extended Edit Plan

apply_extended_edit_plan

Destructive

Executes a reviewed compound CEP edit plan once using typed guarded commands, stopping on the first failed or unverified receipt and reporting completed and unknown steps without retry or rollback.

Instructions

Consume a reviewed compound CEP token once and invoke only its existing typed tools with same-command project/sequence/clip/effect guards. Stops at first failed or unverified receipt, reports completed and unknown steps, and never retries or rolls back partial work. Rendering and audible synchronization remain separate evidence.

Input Schema

Name	Required	Description
`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.
`confirmation_token`	Yes	Single-use token from preview_extended_edit_plan.
`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.

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

A3.8/5.0

Behavior4/5

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

Beyond the destructiveHint=true annotation, the description adds substantive behavioral detail: it stops at the first failed or unverified receipt, reports completed and unknown steps, never retries, and never rolls back partial work. That last point is exactly the information an agent needs before invoking a destructive, non-idempotent operation. It does not cover idempotency_key semantics or return payload shape in prose, and the dense phrasing ('unverified receipt') obscures some of the value.

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?

Three sentences, front-loaded with the core action, with no filler. It is tightly packed to the point of density, but every sentence adds a distinct behavioral fact (execution model, failure semantics, evidence boundary).

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, nested-guard tool with an output schema and full annotation coverage, the description supplies what structured fields cannot: partial-application behavior on failure, absence of rollback, and the boundary that rendering and audible synchronization are verified separately. Nothing essential to a correct invocation is missing.

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 rich nested descriptions for the guard object and the idempotency key, so the schema carries nearly the full burden. The description adds only the notion that the token is single-use and reviewed, not per-parameter meaning. Baseline 3 applies.

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?

The description states a specific verb and resource: consume a reviewed compound CEP token once and invoke its existing typed tools under project/sequence/clip/effect guards. It is clearly an executor of a previously reviewed plan, which distinguishes it implicitly from preview_extended_edit_plan. It does not name the sibling explicitly, and jargon like 'compound CEP token' and 'typed tools' requires prior context.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: the word 'reviewed' and 'Consume ... once' signal that a preview step must precede this call, and the schema's confirmation_token field points to preview_extended_edit_plan. There is no explicit statement of when to choose this over apply_edit_plan or other apply_* siblings, and no when-not guidance.

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

Deploy Server