premiere-pro-mcp

Overview Schema Source Related Servers Discussions Admin

Add Keyframe

add_keyframe

Adds a keyframe to a Premiere Pro effect property at a chosen clip time and reads it back, warning if the time is outside the clip's visible range.

Instructions

Add and read back a keyframe on an effect property. The receipt warns when its time is outside the clip's visible range. Two-component numeric values must match the current host value shape; Motion Position and Anchor Point use normalized 0–1 coordinates only. Colour keys refuse because CEP has no lossless time-specific colour setter. This verifies stored parameter data only; render/playback verification remains host-dependent.

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>",
      "effect_name": "<effect_name>",
      "property_name": "<property_name>",
      "time_seconds": "<time_seconds>",
      "value": "<value>"
    },
    "name": "add_keyframe"
  }
}

Input Schema

Name	Required	Description
`value`	Yes	Finite scalar or numeric vector matching the host property shape. Motion Position/Anchor Point require normalized 0–1 pairs. Colour arrays are recognized but refused without a lossless colour-key API.
`node_id`	Yes	Node ID of the clip
`effect_name`	Yes	Display name of the effect
`time_seconds`	Yes	Seconds from the clip's start on the timeline (0 is the clip's first frame) where to add the keyframe
`property_name`	Yes	Display name of the property
`property_index`	No	Optional property index from get_effect_properties; required when property_name is duplicated.
`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.

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?

Annotations only declare readOnly=false, destructive=false, idempotent=false; the description adds real context beyond that — the receipt warns on out-of-range times, colour keys are refused because CEP lacks a lossless time-specific colour setter, and verification covers stored parameter data only while render/playback stays host-dependent. It does not mention the idempotency or expected-target guard behavior that the schema carries, leaving a small gap.

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, each carrying a distinct fact: the operation, the receipt warning, the value-shape/refusal rule, and the verification scope. Front-loaded with the action and free of padding, though the value-shape sentence partially duplicates the schema text.

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 9-parameter mutation tool with nested identity guards and an output schema (the receipt), the description covers the operation, its refusal modes, and the limits of what the receipt proves. The heavy identity and idempotency parameters are exhaustively documented in the schema, so nothing critical 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 the schema already documents every parameter in depth. The description's notes on value shape and normalized 0-1 coordinates largely restate the schema's own value description rather than adding new meaning, so 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?

The first sentence gives a specific verb and resource ('Add and read back a keyframe on an effect property'), which clearly separates it from remove_keyframe or set_keyframe_interpolation by verb alone. It never names a sibling or states a routing rule, so differentiation is implicit rather than explicit.

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?

Usage constraints are implied through refusals: colour keys are rejected, two-component values must match the host shape, and Motion Position/Anchor Point require normalized 0-1 pairs. There is no explicit 'use this instead of X' or when-not guidance relative to the keyframe siblings, so the agent must infer the routing.

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

Deploy Server