premiere-pro-mcp

Overview Schema Source Related Servers Discussions Admin

Replace Clip

replace_clip

Replace one timeline clip with a different project item on the same track while keeping its exact start/end and avoiding ripple edits to neighboring clips.

Instructions

Replace one timeline clip with a different project item on the same track, keeping the exact timeline start and end. The replacement plays from its own In mark for the original clip's duration; neighbouring clips do not ripple, and a linked partner clip on another track is left in place. The replacement must carry only the track's media type (for example a still or video-only item on a video track): Premiere's overwrite would also place an item's other media on another track. Checks the replacement accepts the source range before removing anything. Refuses without changing anything when the track is locked. Reads the track back: verified when the new clip covers the same span, committed_unverified when the span holds but the source In point cannot be confirmed, otherwise failure with Undo guidance.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "node_id": "<node_id>",
      "new_item_id": "<new_item_id>"
    },
    "name": "replace_clip"
  }
}

Input Schema

Name	Required	Description
`node_id`	Yes	Node ID of the clip to replace
`new_item_id`	Yes	Node ID or name of the new project item to replace with, or the sequence ID of a sequence
`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 the HTTP server process when Streamable HTTP is stateless per request) 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.

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.

First observedv1.30.0Nov 14, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Goes well beyond the annotations: no ripple to neighbours, linked partner clips left in place, replacement plays from its own In point for the original duration, pre-flight range check before anything is removed, refuse-without-change on locked tracks, and a read-back with three named outcomes (verified, committed_unverified, failure with Undo guidance). That is exactly the atomicity and failure-mode information an agent needs. There is mild tension with destructiveHint=false since the original clip is removed, but the description is fully transparent about what is removed and what is preserved.

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 followed by the differentiators (no ripple, linked clips untouched, media-type restriction, verification states). Dense but each clause carries distinct behavioral information; the long final sentence about read-back states is the only slightly overloaded part.

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?

Output schema exists, so return shapes need not be spelled out, yet the description still explains the verification outcome semantics, which is genuinely useful. Preconditions, atomicity and refusal behavior are all covered; the only gap is the optional review-guard parameters, which are left entirely to the schema.

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 documents node_id, new_item_id, idempotency_key and the identity guards. The description adds one real semantic constraint on the replacement item (track media type only, no extra media placed elsewhere) but says nothing about node_id, the review guard objects, or expected_project_path.

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 and resource (replace one timeline clip with a different project item) and immediately pins the scope: same track, exact timeline start and end preserved. It also implies the distinction from overwrite_clip by explaining that overwrite would additionally place an item's other media on another track.

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?

Gives a concrete constraint that selects this tool rather than an overwrite-style alternative: the replacement must carry only the track's media type, e.g. a still or video-only item on a video track. It also states refusal conditions (locked track, replacement not accepting the source range). It stops short of naming a sibling tool explicitly for the cases it excludes.

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

Deploy Server