premiere-pro-mcp

Overview Schema Source Related Servers Discussions Admin

Insert From Source

insert_from_source

Insert the Source Monitor clip at the playhead in Adobe Premiere Pro, then optionally razor QE sync-locked tracks and verify the resulting placement and target tails.

Instructions

Insert the clip from the Source Monitor at the playhead (insert edit). Experimental: a target clip spanning the playhead is QE-razored before insertion to attempt to preserve its split tail. By default the tool also razors and shifts every QE sync-locked track, then reads the placement and target tails back; a displaced tail is reported as committed_unverified. Pass scope 'target_tracks' to ripple only the named pair (this will desync other tracks).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "insert_from_source"
  }
}

Input Schema

Name	Required	Description
`scope`	No	Which tracks shift: 'sync_locked' (default) matches Premiere's insert and keeps sync-locked tracks in sync; 'target_tracks' ripples only the named pair and WILL desync other tracks.
`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.
`audio_track_index`	No	Target audio track index (default: 0)
`video_track_index`	No	Target video track index (default: 0)
`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

A3.9/5.0

Behavior5/5

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

Annotations only cover the safety flags (readOnly=false, destructive=false, idempotentHint=false); the description adds the genuinely load-bearing behavior: the experimental QE razor of a clip spanning the playhead, the automatic razoring/shifting of sync-locked tracks, the placement and target-tail read-back, and the committed_unverified outcome for a displaced tail. It also warns that 'target_tracks' will desync other tracks, which is exactly the consequence an agent needs before choosing a scope.

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?

Three sentences, front-loaded with the core action before the experimental caveats and the scope option; nothing is padding. Some density in the middle sentence (QE-razored, sync-locked, committed_unverified) makes it slower to parse than it needs to be, but every clause carries real behavioral information.

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?

For a mutation tool with an output schema and rich annotations, the description supplies the risky/experimental context an agent cannot get from structured fields, including the verification read-back and the failure label. It leaves the identity-guard parameters and the idempotency behavior entirely to the schema, which is a reasonable division but means the description alone would not fully prepare an agent for the guard refusals.

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 coverage is 100% and the scope parameter is itself documented with a matching desync warning, so the description's restatement of scope adds little beyond the schema. Track indices, idempotency_key, and the expected_cep_target guards are not discussed in the description at all, which is acceptable given the schema carries them but means no added meaning.

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?

States a specific verb and resource ('Insert the clip from the Source Monitor at the playhead (insert edit)'), which pins down both the operation and the source of the content. It does not name overwrite_from_source as the contrasting sibling, so an agent must infer the insert-vs-overwrite distinction from the parenthetical rather than being routed explicitly.

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 implicit guidance about defaults (sync-locked razoring and shifting, then read-back) and when to choose the 'target_tracks' scope, including the desync consequence. It never says when to use this tool instead of overwrite_from_source or add_to_timeline, and no prerequisites (open source clip, in/out marks set) are stated.

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

Deploy Server