Premiere Pro MCP Server

Build Edit Review Evidence

build_edit_review_evidence

Creates before/after contact sheets, optional bounded MP4 excerpts, and checksum receipts from two rendered videos so editors can visually review cuts, transitions, titles, and masks.

Instructions

Create new before/after contact sheets, optional bounded MP4 excerpts, and checksum receipts from two reviewed rendered videos. Supports visual review of cuts, transitions, titles and masks; still grids do not verify temporal behavior or authenticate host lineage.

Input Schema

Name	Required	Description
`after_sheet`	Yes	New after .png contact-sheet destination.
`after_video`	Yes	Existing rendered video captured after the edit.
`before_sheet`	Yes	New before .png contact-sheet destination.
`before_video`	Yes	Existing rendered video captured before the edit.
`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.
`after_review_clip`	No	Optional distinct new absolute after .mp4 excerpt destination; requires before_review_clip.
`before_review_clip`	No	Optional new absolute before .mp4 excerpt destination; requires after_review_clip.
`operation_revision`	Yes	Reviewed operation/snapshot revision that this evidence accompanies; declared, not host-authenticated.
`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.
`review_start_seconds`	No	Output-relative excerpt start, default zero.
`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.
`review_duration_seconds`	No	Bounded review excerpt duration, default three seconds.

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?

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, and idempotentHint=false, so the safety profile is largely covered. The description adds useful behavioral context beyond annotations: it creates new contact sheets, optional bounded MP4 excerpts, and checksum receipts, and it explicitly warns that still grids do not verify temporal behavior or authenticate host lineage.

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?

The description is two tightly constructed sentences with no filler, and the core output and key limitation are front-loaded. Every clause adds useful information for an agent deciding whether and how to call the tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a 12-parameter tool with nested objects, 100% schema description coverage, and an output schema, the description provides a sufficient high-level summary of what the tool does and what it cannot do. It could be slightly more complete by explicitly routing temporal or lineage verification to an alternative, but the essential calling context is present.

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%, so the schema already carries detailed parameter meaning. The description reinforces the core before/after video and sheet concepts and the optional bounded excerpts, but it does not add substantive semantics for parameters such as operation_revision, expected_cep_target, idempotency_key, or review timing beyond what the schema provides.

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 (Create) and concrete resources: before/after contact sheets, optional bounded MP4 excerpts, and checksum receipts from two reviewed rendered videos. It is clear what the tool produces, though it does not explicitly differentiate itself from nearby tools such as generate_media_contact_sheet or verify_temporal_render_artifact.

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?

The description gives implied usage context by saying it supports visual review of cuts, transitions, titles, and masks, and it notes that still grids do not verify temporal behavior or authenticate host lineage. However, it does not explicitly say when to choose this tool over alternatives or name any sibling tool as the alternative for temporal verification or lineage authentication.

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

Deploy Server