premiere-pro-mcp

Overview Schema Source Related Servers Discussions Admin

Normalize Loudness File

normalize_loudness_file

Normalize an audio or video file to a target LUFS with true-peak limiting, then remeasure and retry the render if encoding misses the target.

Instructions

Create a new loudness-normalized media derivative with FFmpeg, then remeasure that exact output using EBU R128. When the remeasured file misses the target or true-peak ceiling (AAC encoding can raise the true peak), it renders again with a lowered ceiling or offset target, up to max_attempts, keeps the best attempt and reports every attempt's measured I and TP. Never overwrites the input or an existing output file.

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": {
      "input_path": "<input_path>",
      "output_path": "<output_path>"
    },
    "name": "normalize_loudness_file"
  }
}

Input Schema

Name	Required	Description
`input_path`	Yes	Existing local audio or video file
`output_path`	Yes	New output path; must not already exist
`target_lufs`	No	Integrated loudness target from -70 through -5 LUFS (default: -16)
`max_attempts`	No	Renders allowed when the remeasured output misses the target or true-peak ceiling, for example after AAC encoding raises the true peak (default: 2; 1 disables retries)
`tolerance_lu`	No	Post-render integrated-loudness tolerance (default: 1 LU)
`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.
`max_true_peak_dbfs`	No	True-peak ceiling from -9 through 0 dBFS (default: -1.5)
`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

A4.1/5.0

Behavior4/5

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

Beyond the annotations (destructiveHint=false, idempotentHint=false), the description discloses real behavior: a bounded retry loop, why retries happen (AAC encoding raising true peak), how the winner is chosen (best attempt kept), and what is reported (each attempt's measured I and TP). The non-overwrite guarantee reinforces destructiveHint=false rather than contradicting it. It does not cover runtime cost or failure modes outside the retry path.

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?

Four sentences with no filler; the core purpose is front-loaded and the retry/no-overwrite details follow in a logical order. The AAC parenthetical earns its place by explaining why retries exist, though the sentence packing is dense enough that a reader must parse carefully.

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 9-parameter mutation tool with an output schema and fully described parameters, the description covers the essential pipeline and safety behavior. The gap is the expected_cep_target / expected_project_path guard parameters, which are entirely unmentioned in prose and must be discovered from the nested 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 baseline is 3. The description explains the semantics of max_attempts and the target/true-peak interaction, but that meaning is already spelled out in the schema field descriptions, and it says nothing about target_lufs, tolerance_lu, idempotency_key, or the CEP identity guards. It adds little interpretive value beyond the structured fields.

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?

The description names a precise verb and resource — create a loudness-normalized derivative with FFmpeg — and adds the distinguishing second phase (remeasure that exact output with EBU R128). That two-phase render/verify loop separates it functionally from an analyze-only or plain-encode sibling, so an agent can identify the tool without opening the schema.

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?

It clearly establishes the context of use: you have an existing input file and want a new normalized derivative that actually meets the target after encoding. It also states a hard constraint (never overwrites input or existing output). It stops short of naming an alternative for measurement-only or encoding-only needs, so there are no explicit when-not routes.

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

Deploy Server