premiere-pro-mcp

Overview Schema Source Related Servers Discussions Admin

Detect Source Scene Changes

detect_source_scene_changes

Detect probable visual cuts in a local video file using FFmpeg scene scores, so you can identify source changes without modifying a Premiere timeline.

Instructions

Detect probable visual cuts in a local source file using FFmpeg scene scores. Read-only and source-relative; it does not cut a Premiere timeline.

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": {
      "media_path": "<media_path>"
    },
    "name": "detect_source_scene_changes"
  }
}

Input Schema

Name	Required	Description
`threshold`	No	Scene-score threshold from 0.01 through 1 (default: 0.3)
`media_path`	Yes	Path to an existing local video file
`maximum_events`	No	Maximum returned changes (default: 500; maximum: 2000)
`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.
`minimum_interval_seconds`	No	Keep only the strongest event within this interval (default: 0.25)

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

B3.1/5.0

Behavior1/5

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

The description asserts 'Read-only', while the annotations declare readOnlyHint=false and idempotentHint=false, so the agent receives flatly conflicting signals about whether this call can mutate state. Beyond that conflict, the description adds nothing on runtime cost for long files, temp-file or FFmpeg process side effects, or failure modes ('probable' is the only hedge given, unexplained). This is a direct annotation contradiction.

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 short sentences, front-loaded with the core operation and followed by the scoping caveat; no filler or restatement of the title. The only cost is that the second sentence carries the inaccurate 'Read-only' claim, but structurally the text is tight.

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

Completeness3/5

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

Because an output schema exists and parameter documentation is complete, the description need not explain return values, and it does not need to. However, for a media-analysis tool that shells out to FFmpeg, the omission of expected runtime, failure conditions, and the read-only/mutating question leaves the agent under-informed relative to the tool's complexity and nested guard parameters.

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 all seven parameters, including threshold, maximum_events and minimum_interval_seconds, are already documented in the schema; baseline 3 applies. The description adds no meaning beyond the schema, not even a note on how the threshold or minimum_interval_seconds trade sensitivity against event count.

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 ('detect probable visual cuts in a local source file') plus the technique ('FFmpeg scene scores'), so the agent knows exactly what is computed. The clause 'source-relative; it does not cut a Premiere timeline' partially separates it from timeline-oriented siblings such as detect_scene_edits, but no sibling is named explicitly, leaving residual ambiguity for an agent choosing between the several scene-detection tools.

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?

Implied usage only: the description signals this is for local source media rather than a Premiere timeline, which is a real routing hint. It never states when to prefer it over detect_scene_edits or scene_edit_detection, nor any prerequisite such as FFmpeg availability, file preconditions, or what to do with the detected cuts afterwards.

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

Deploy Server