Skip to main content
Glama
Sign In
premiere-pro-mcp

premiere-pro-mcp

by matt-j-penny
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Apply Lut

apply_lut

Attempts to apply a .cube or .3dl LUT to a clip; on CEP this is unsupported and fails before changing the clip, so use Lumetri Color > Creative > Look instead.

Instructions

Unavailable on the CEP backend: Premiere's scripting API cannot load a LUT file into Lumetri Color. Its Input LUT and Look parameters are menu indexes over a curated set of bundled looks, and writing a file path to the LUT asset parameters is accepted but not rendered (seen on Premiere Pro 25.2.3, macOS, by comparing exported frames with the same LUT applied by ffmpeg; other builds were not tested). Fails before changing the clip. Apply the LUT in Lumetri Color > Creative > Look (Browse...) instead.

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": {
      "node_id": "<node_id>",
      "lut_path": "<lut_path>"
    },
    "name": "apply_lut"
  }
}

Input Schema

NameRequiredDescriptionDefault
node_idYesNode ID of the clip
lut_pathYesFull path to the .cube or .3dl LUT file
idempotency_keyNoOptional 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_targetNoOptional reviewed CEP sequence/clip identity and exact tick ranges. Checked before every generated command; UXP refuses this CEP-only guard.
expected_project_pathNoOptional 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

NameRequiredDescriptionDefault
okYesWhether the tool completed successfully.
dataNoTool-specific result data when ok is true; on failure, diagnostic detail when the tool provides it.
toolYesThe registered MCP tool name.
errorNoFailure detail when ok is false.
receiptNoVersioned common mutation receipt; success never implies rendered verification.
idempotencyNoPresent 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.

  1. First observedv1.30.0

TDQS

A4.4/5.0
Behavior5/5

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

Goes far beyond the annotations by disclosing the exact failure mode (Input LUT/Look are menu indexes; writing a file path to the LUT asset parameters is accepted but not rendered), the tested environment (Premiere Pro 25.2.3, macOS), the evidence method (exported-frame comparison with ffmpeg), and the important state guarantee 'Fails before changing the clip'. The last point tells the agent nothing is partially mutated despite destructiveHint=false and readOnlyHint=false, which the annotations alone cannot convey.

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?

The unavailability verdict is front-loaded in the first clause, followed by justification and the recommended alternative. The build/OS/ffmpeg detail is heavier than strictly necessary but earns its place by making the 'does not work' claim credible; a tighter phrasing could have compressed it into one clause.

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

Completeness5/5

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

For a five-parameter, nested-schema tool with an output schema, the description supplies the one thing the schema and annotations cannot: that the operation is ineffective on this backend and what to do instead. An agent has everything needed to decide not to call it and to route the user elsewhere.

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% and the five parameters (including idempotency_key and the nested expected_cep_target guard) are documented in detail in the schema itself. The description adds no syntax or format meaning for node_id, lut_path, or the guard object, so the baseline of 3 applies even though the tool is unusable in practice.

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?

The description makes clear that this is the tool for loading a LUT file into Lumetri Color on the CEP backend, and immediately states it is unavailable there. The verb+resource (apply LUT to a clip) is conveyed through the failure explanation and the Creative > Look workaround rather than a direct opening sentence, but the agent can still tell what the tool would do and why it is distinct from siblings like apply_effect or apply_audio_effect.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It is explicit that the tool should not be used at all: 'Unavailable on the CEP backend' up front, plus a concrete when-not condition and a named alternative path ('Apply the LUT in Lumetri Color > Creative > Look (Browse...) instead'). No inference is required about selection.

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

Deploy Server

Other Tools