Premiere Pro MCP Server

Undo

undo

Reverses recent Premiere project actions through QE and blocks the request when the current stack position differs from the required index.

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

Name	Required	Description
`count`	No	Number of times to undo (default: 1)
`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.
`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_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

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"
+}

Changed3 schema fields changedv1.24.0Oct 12, 2026

addedInput schema / properties / expected_cep_target

Added value: +{
+  "additionalProperties": false,
+  "anyOf": [
+    {
+      "required": [
+        "sequence_id"
+      ]
+    },
+    {
+      "required": [
+        "source_item"
+      ]
+    }
+  ],
+  "description": "Optional reviewed CEP sequence/clip identity and exact tick ranges. Checked before every generated command; UXP refuses this CEP-only guard.",
+  "properties": {
+    "backend": {
+      "const": "cep",
+      "description": "Backend namespace for these IDs.",
+      "type": "string"
+    },
+    "clip": {
+      "additionalProperties": false,
+      "description": "Optional exact reviewed timeline clip.",
+      "properties": {
+        "effect": {
+          "additionalProperties": false,
+          "description": "Reviewed effect and parameter identity checked before mutation.",
+          "properties": {
+            "display_name": {
+              "description": "Optional exact host display name.",
+              "maxLength": 512,
+              "minLength": 1,
+              "type": "string"
+            },
+            "match_name": {
+              "description": "Effect match name from host inspection.",
+              "maxLength": 512,
+              "minLength": 1,
+              "type": "string"
+            },
+            "parameter_index": {
+              "description": "Inspected zero-based parameter index.",
+              "maximum": 255,
+              "minimum": 0,
+              "type": "integer"
+            },
+            "parameter_name": {
+              "description": "Exact inspected parameter name.",
+              "maxLength": 512,
+              "minLength": 1,
+              "type": "string"
+            }
+          },
+          "required": [
+            "match_name",
+            "parameter_index",
+            "parameter_name"
+          ],
+          "type": "object"
+        },
+        "end_ticks": {
+          "description": "Exact expected exclusive timeline end ticks.",
+          "pattern": "^-?\\d{1,30}$",
+          "type": "string"
+        },
+        "in_ticks": {
+          "description": "Exact expected source In ticks.",
+          "pattern": "^-?\\d{1,30}$",
+          "type": "string"
+        },
+        "node_id": {
+          "description": "Stable CEP node ID.",
+          "maxLength": 512,
+          "minLength": 1,
+          "type": "string"
+        },
+        "out_ticks": {
+          "description": "Exact expected exclusive source Out ticks.",
+          "pattern": "^-?\\d{1,30}$",
+          "type": "string"
+        },
+        "project_item_id": {
+          "description": "Expected source project-item node ID.",
+          "maxLength": 512,
+          "minLength": 1,
+          "type": "string"
+        },
+        "start_ticks": {
+          "description": "Exact expected timeline start ticks.",
+          "pattern": "^-?\\d{1,30}$",
+          "type": "string"
+        },
+        "track_index": {
+          "description": "Expected zero-based track index; identity still checked.",
+          "maximum": 255,
+          "minimum": 0,
+          "type": "integer"
+        },
+        "track_type": {
+          "description": "Expected media track group.",
+          "enum": [
+            "video",
+            "audio"
+          ],
+          "type": "string"
+        }
+      },
+      "required": [
+        "node_id",
+        "track_type",
+        "track_index"
+      ],
+      "type": "object"
+    },
+    "project_document_id": {
+      "description": "Exact Premiere project document ID observed during review.",
+      "maxLength": 512,
+      "minLength": 1,
+      "type": "string"
+    },
+    "sequence_id": {
+      "description": "Stable expected active sequence ID.",
+      "maxLength": 512,
+      "minLength": 1,
+      "type": "string"
+    },
+    "source_item": {
+      "additionalProperties": false,
+      "description": "Reviewed source identity for a source-only operation.",
+      "properties": {
+        "media_path": {
+          "description": "Optional exact source-media path.",
+          "maxLength": 4096,
+          "minLength": 1,
+          "type": "string"
+        },
+        "node_id": {
+          "description": "Exact project-item node ID.",
+          "maxLength": 512,
+          "minLength": 1,
+          "type": "string"
+        }
+      },
+      "required": [
+        "node_id"
+      ],
+      "type": "object"
+    }
+  },
+  "required": [
+    "backend"
+  ],
+  "type": "object"
+}

addedInput schema / properties / expected_project_path

Added value: +{
+  "description": "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.",
+  "maxLength": 4096,
+  "minLength": 1,
+  "type": "string"
+}

addedOutput schema / properties / receipt

Added value: +{
+  "additionalProperties": true,
+  "description": "Versioned common mutation receipt; success never implies rendered verification.",
+  "type": "object"
+}

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

A4.3/5.0

Behavior5/5

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

Annotations only say non-read-only, non-destructive, non-idempotent; the description carries the real weight: project-wide undo history, only Premiere-recorded actions are undoable, UXP/workflow commands are not counted, the guard verifies position only and cannot prove which action is on top, and the marker barrier's persistence and blind spots are spelled out.

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?

Front-loaded with the action and its experimental QE basis, and nearly every sentence adds a distinct constraint. It is a dense single paragraph with some redundancy ("matching position alone does not prove which action is on top" and "Matching the QE index verifies stack position only"), which costs it the top score.

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 complex, high-risk mutation tool with nested guards and an output schema, the description covers the failure modes an agent must plan around: untracked markers, UXP-sent commands, engine resets, and other clients. Little that affects a correct call is left unstated.

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 baseline is 3, but the description adds operational meaning beyond the schema: count should be the undoSteps value from the producing tool result, and expected_undo_stack_index matching position alone does not prove which action is on top. acknowledge_untracked_markers semantics are reinforced but largely restated from the schema.

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?

It states a specific verb and resource ("Undo the most recent Premiere project action(s) through QE") and immediately bounds it to actions Premiere records. It does not name how it differs from close siblings like multiple_undo or redo, so an agent must infer the split from the count parameter.

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?

Clear when-to-use: after a QE edit that returned undoSteps, pass that value as count. It also gives an explicit exclusion ("A marker receipt with undoTracked:false... calling Undo for it would reverse an earlier action") and requires the expected_undo_stack_index guard. It never routes to redo/multiple_undo as alternatives, so a sibling comparison is left implicit.

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

Deploy Server