premiere-pro-mcp

Overview Schema Source Related Servers Discussions Admin

Detect Motion Peaks

detect_motion_peaks

Identify probable high-motion moments in a bounded local video sample by comparing decoded frames, returning read-only editorial candidates for review.

Instructions

Find probable high-motion moments in a bounded local video sample from decoded frame differences. Read-only editorial candidates; camera movement, flashes, cuts, and subject motion are not semantically distinguished.

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_motion_peaks"
  }
}

Input Schema

Name	Required	Description
`threshold`	No	Minimum mean luma-frame difference from 0 through 255 (default: 12)
`use_cache`	No	Opt in to bounded process-memory caching keyed by source path/identity, media content SHA-256, exact options, revision, and analysis version. Files over 256 MiB analyze uncached. Default false.
`media_path`	Yes	Existing local video file
`maximum_events`	No	Maximum returned candidates from 1 through 1000 (default: 200)
`sample_seconds`	No	Decode duration from 1 through 300 seconds (default: 60)
`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.
`analysis_revision`	No	Optional project/timeline revision to isolate otherwise-identical analysis inputs.
`samples_per_second`	No	Frame samples per second from 1 through 10 (default: 4)
`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	Minimum peak spacing from 0.1 through 30 seconds (default: 1)

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

A3.8/5.0

Behavior4/5

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

Goes beyond the annotations by disclosing the algorithmic basis (frame differencing) and the key limitation that camera movement, flashes, cuts and subject motion are conflated – directly useful for judging false positives. The word "Read-only" sits in mild tension with readOnlyHint=false, though it appears to describe the advisory nature of the returned candidates rather than a safety guarantee.

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 with no filler: the first states what is detected and how, the second states the interpretation limits. Front-loaded and every clause carries 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 an 11-parameter tool with nested objects and an output schema, the description covers method, scope, and interpretive caveats, which is the part structured fields cannot express. Return-shape details are correctly left to the output schema; only explicit sibling routing is missing.

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 every parameter is already documented in detail (sampling rate, threshold range, sample duration, caching semantics). The description only echoes the "bounded sample" idea and adds no format, default, or interaction detail beyond the schema, so the baseline 3 applies.

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?

Names a concrete verb and resource ("Find probable high-motion moments") and adds the detection mechanism ("decoded frame differences") plus its scope ("bounded local video sample"). It implicitly separates itself from scene-edit detection by stating that cuts are not semantically distinguished, though no sibling is named 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?

"Read-only editorial candidates" signals the intended use: reviewing suggestions before an edit. But there is no explicit when-to-use/when-not guidance and no alternative named (e.g. detect_scene_edits for hard cuts), so the agent must infer selection from the caveat sentence.

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

Deploy Server