premiere-pro-mcp

Overview Schema Source Related Servers Discussions Admin

Select Clips By Pattern

select_clips_by_pattern

Selects every Nth matching clip (with an offset) by name, duration, time range, or track, then reports the selection count without altering the timeline.

Instructions

Select every Nth clip (with an offset) among clips that match optional name, duration, time-range, track, and enabled filters, then read back the selection count. Covers 'select every other clip on V1' and similar repetitive selections without changing the timeline.

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": "select_clips_by_pattern"
  }
}

Input Schema

Name	Required	Description
`offset`	No	Zero-based index of the first candidate to select (default 0). Must be below every_nth.
`every_nth`	No	Select one clip out of every N candidates (default 1 = all candidates).
`name_regex`	No	Case-insensitive ECMAScript 3 compatible regular expression the clip name must match.
`track_type`	No	Track type to scan (default video).
`count_scope`	No	Whether the Nth count restarts on each track (default) or runs across all scanned tracks in timeline order.
`end_seconds`	No	Only clips overlapping before this sequence time.
`track_index`	No	Restrict to one track index.
`name_contains`	No	Case-insensitive substring the clip name must contain.
`start_seconds`	No	Only clips overlapping at or after this sequence time.
`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.
`add_to_selection`	No	Keep the existing selection instead of replacing it (default false).
`include_disabled`	No	Include disabled clips as candidates (default true).
`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.
`max_duration_seconds`	No	Maximum clip duration.
`min_duration_seconds`	No	Minimum clip duration.
`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

A4.2/5.0

Behavior3/5

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

Annotations already declare destructiveHint=false and readOnlyHint=false, and the description reinforces the boundary by saying the timeline is not modified, which clarifies that only selection state changes. However it omits other behavioral facts the schema knows about, such as idempotency-key retry semantics and add_to_selection behavior, so it adds only modest value beyond the annotations.

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?

Two sentences, front-loaded with the core mechanism and followed by scope and a concrete example. No filler or redundant restatement of the title.

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?

The tool is complex (16 params, nested objects), but an output schema exists so return values need not be explained, and the schema documents every parameter thoroughly. The description covers the mechanism, filter scope, and non-mutating behavior; only the idempotency/guard semantics are left implicit, which is acceptable given the schema.

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 summarizes the filter families (name, duration, time-range, track, enabled) and highlights the offset pairing, giving an agent a quick mental model before opening the 16-parameter schema. It still leaves the nested expected_cep_target and idempotency_key semantics entirely to the schema.

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 (select), a specific resource (clips), and a distinctive mechanism (every Nth with offset) plus the filter set it operates over. The 'select every other clip on V1' example makes it immediately distinguishable from sibling selectors like select_clips_by_color or select_clips_in_range.

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 use case ('select every other clip on V1' and similar repetitive selections) and a boundary ('without changing the timeline'). It does not explicitly name alternative tools or state when-not to use it, so it stops short of a 5.

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

Deploy Server