Premiere Pro MCP Server

Undo

undo

Reverse recent Premiere project actions via QE, checking stack position before each step. Requires expected stack index; marker boundaries may refuse requests.

Instructions

EXPERIMENTAL (undocumented QE DOM: qe.project.undo / undoStackIndex). Undo the most recent Premiere project action(s) through QE, checked step by step against Premiere's undo-stack position (stackVerified; the timeline itself is not read back). Undo history is project-wide. Only actions Premiere records are undoable: QE edits such as razor, insert, lift and extract report undoSteps (and undoStackIndex) in their results; pass that undoSteps as count to reverse exactly that call. A marker receipt with undoTracked:false recorded no undo step: calling Undo for it would reverse an earlier action. Only CEP tool results carry undoSteps; UXP tools and workflows that send several commands are not counted. Always pass expected_undo_stack_index to check the stack position, but matching position alone does not prove which action is on top. Observed marker boundaries refuse the entire request before any step unless acknowledge_untracked_markers:true explicitly permits prior non-marker actions. The barrier persists through server/helper reloads while the CEP engine remains alive; it cannot account for marker writes before observation, after an engine reset, or through UXP, the manual UI, or other clients. Matching the QE index verifies stack position only.

Input Schema

TableJSON Schema

Name	Required	Description
`count`	No	Number of times to undo (default: 1)
`expected_undo_stack_index`	Yes	Required safety guard: the undoStackIndex a tool result reported right after the call you want to reverse. The step is refused, with nothing changed, when Premiere's undo-stack position differs from it. The guard compares the position only; matching position cannot prove which action is on top.
`acknowledge_untracked_markers`	No	Explicitly acknowledge that QE steps reverse or restore prior non-marker actions, because marker reversal is not verified. Default false; marker boundaries refuse the entire request before any step.

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.

Changed3 schema fields changedv1.19.0Oct 3, 2026

addedInput schema / properties / acknowledge_untracked_markers

Added value: +{
+  "description": "Explicitly acknowledge that QE steps reverse or restore prior non-marker actions, because marker reversal is not verified. Default false; marker boundaries refuse the entire request before any step.",
+  "type": "boolean"
+}

changedInput schema / properties / expected_undo_stack_index / description

Previous value: -"Optional safety guard: the undoStackIndex a tool result reported right after the call you want to reverse. The step is refused, with nothing changed, when Premiere's undo-stack position differs from it. This compares the position only: if actions were undone and new ones recorded since, the position can match again and undo would reverse the newer action."New value: +"Required safety guard: the undoStackIndex a tool result reported right after the call you want to reverse. The step is refused, with nothing changed, when Premiere's undo-stack position differs from it. The guard compares the position only; matching position cannot prove which action is on top."

addedInput schema / required

Added value: +[
+  "expected_undo_stack_index"
+]

Changed3 schema fields changedv1.18.6Sep 30, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

addedInput schema / properties / expected_undo_stack_index

Added value: +{
+  "description": "Optional safety guard: the undoStackIndex a tool result reported right after the call you want to reverse. The step is refused, with nothing changed, when Premiere's undo-stack position differs from it. This compares the position only: if actions were undone and new ones recorded since, the position can match again and undo would reverse the newer action.",
+  "type": "number"
+}

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."

Changed2 schema fields changedv1.14.4Aug 29, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": false,
+  "properties": {
+    "data": {
+      "description": "Tool-specific result data when ok is true."
+    },
+    "error": {
+      "description": "Failure detail when ok is false.",
+      "type": "string"
+    },
+    "ok": {
+      "description": "Whether the tool completed successfully.",
+      "type": "boolean"
+    },
+    "tool": {
+      "description": "The registered MCP tool name.",
+      "minLength": 1,
+      "type": "string"
+    }
+  },
+  "required": [
+    "ok",
+    "tool"
+  ],
+  "type": "object"
+}

Addedv1.4.0Jul 27, 2026
Removedv1.1.5Jul 19, 2026
First observedv1.1.1May 28, 2026

TDQS

A4.2/5.0

Behavior5/5

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

Goes far beyond the annotations: EXPERIMENTAL status, undocumented QE DOM paths, project-wide undo history, step-by-step position check with a stated blind spot ('matching position alone does not prove which action is on top'), persistence of the marker barrier across reloads, and enumerated limits (UXP, manual UI, engine resets). The destructiveHint=false annotation is not contradicted, though the warning that Undo 'would reverse an earlier action' is exactly the risk an agent must weigh.

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

Conciseness3/5

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

One dense paragraph with the critical EXPERIMENTAL warning and safety-guard behavior front-loaded, but verbose and repetitive: the caveat that a matching index proves position only is stated twice. Much of the length is earned by the tool's complexity, but it could be tightened.

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 mutant, experimental QE-backed tool with a required safety guard, the description covers prerequisites, failure modes (refused step, marker barrier), permission/acknowledgment semantics, and known blind spots. An output schema exists, so return values need not be described.

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 baseline is 3, but the description adds real meaning: it explains that the undoSteps value from a prior call should be passed as count to reverse exactly that call, and that expected_undo_stack_index is a positional guard rather than proof of the top action. That connects the parameters to the workflow rather than restating their types.

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 names a specific verb and resource ('Undo the most recent Premiere project action(s) through QE') and pins down the mechanism (PS undo-stack position verified via undoStackIndex). It implicitly scopes itself away from untracked actions, but never names the adjacent siblings redo or multiple_undo, so an agent must infer the boundary itself.

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?

Strong when-to-use guidance: only actions Premiere records are undoable, pass the undoSteps a QE edit returned as count, and acknowledge_untracked_markers is required to pass a marker receipt boundary. Clear conditions, but no explicit routing against the sibling undo-family tools.

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

Deploy Server