Premiere Pro MCP Server

Paste Clip Attributes

paste_clip_attributes

Copy a source clip's effect stack—Motion, Opacity, applied effects, and keyframes—onto a target clip on the same track type, verifying each property after pasting.

Instructions

Paste Attributes for one timeline clip: copy the source clip's effect stack (Motion, Opacity, other intrinsic components, and every applied effect) onto a target clip of the same track type, including keyframes. Components are matched by match name and occurrence; a missing non-intrinsic effect is applied through the experimental legacy QE DOM (disable with apply_missing_effects=false). Every written parameter and keyframe value is read back and reported per property as verified, committed_unverified, or failed, with an overall status. Not copied, and listed in notCopied with a reason: parameters whose values ExtendScript cannot read as numbers, booleans, strings, or numeric arrays; Opacity > Blend Mode when it differs (legacy cross-clip enum writes can corrupt it; use set_blend_mode and verify); and keyframe interpolation (no getter exists, so pasted keys use Premiere's default interpolation). MASKS ARE NOT COPIED: neither ExtendScript, QE, nor documented Premiere UXP exposes mask shapes, paths, feather, expansion, or mask keyframes, and masks are invisible to this bridge, so recreate or paste masks manually in Effect Controls. Time Remapping is excluded unless named in components.

Input Schema

TableJSON Schema

Name	Required	Description
`components`	No	Optional component display names or match names to copy (for example ['Motion', 'Opacity', 'Gaussian Blur']). Omit to copy every source component except Time Remapping.
`copy_keyframes`	No	Copy keyframes of animated source properties (default true). Key times keep their offset from each clip's in point. When false, animated source properties are reported in notCopied and left unchanged on the target.
`source_node_id`	Yes	Node ID of the source timeline clip in the active sequence whose attributes are copied
`target_node_id`	Yes	Node ID of the target timeline clip in the active sequence that receives the attributes; must be on the same track type (video or audio) as the source
`apply_missing_effects`	No	Apply source effects that the target lacks through the experimental legacy QE DOM before copying values (default true). When false, missing effects are reported in notCopied.

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.

Changed1 schema field changedv1.18.6Sep 30, 2026

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."

Addedv1.18.0Sep 23, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond the annotations (readOnly=false, idempotent=false, destructive=false) by disclosing what is silently omitted (masks, keyframe interpolation, unreadable parameter types), the experimental QE DOM write path, and a per-property verification/committed_unverified/failed reporting model. This is exactly the destructive/mutation context an agent needs.

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 core action and the most important constraints (same track type, keyframes, verification), but it is one very dense block sentence-chain that is hard to scan. Every clause carries information, so it earns its length, though structure could be improved with breaks.

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?

Given the mutation complexity, a 5-parameter schema, an output schema, and the risky QE DOM fallback, the description covers the critical gaps: what is copied, what is not, why, and how results are verified. An agent can call this correctly without further probing.

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 real semantics: components defaults to 'every source component except Time Remapping,' copy_keyframes changes reporting behavior, and apply_missing_effects controls the QE DOM path. It clarifies defaults and cross-parameter interaction beyond the schema wording.

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?

States a specific verb+resource+scope: copying a source clip's effect stack onto a target clip of the same track type, including keyframes. It clearly distinguishes itself from siblings like copy_effects_between_clips and copy_effect_values by describing whole-stack paste semantics and matching rules.

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?

Explicitly covers when-not behavior (masks cannot be copied, Time Remapping excluded unless named, blend mode should be handled via set_blend_mode) and how to disable the QE DOM path with apply_missing_effects=false. It does not explicitly compare itself against the closest sibling copy tools, but the exclusions and alternatives are clear.

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

Deploy Server