premiere-pro-mcp

Overview Schema Source Related Servers Discussions Admin

Create Source Freeze Frame

create_source_freeze_frame

Creates a freeze frame from a source project item at a media time, decodes the frame with ffmpeg, imports the still, and optionally places it on an empty sequence range with zoom keyframes.

Instructions

Create a freeze frame from a project item at a SOURCE-media time (not a sequence time; for a sequence time use freeze_frame). Decodes the frame with ffmpeg from the item's media file (requires ffmpeg/ffprobe on PATH; no Source Monitor or QE state is used), refuses to overwrite an existing output file, imports the still and sets its Out mark to duration_seconds. Optional place puts it on an empty range of one video track (refuses an occupied or locked range rather than overwriting); optional zoom (requires place) adds Motion Scale and optional Position keyframes at the clip's first and last frame for a punch-in. Every step is read back; partial success reports which steps were committed but not verified. Refuses before any change when the item has no readable local media, the time is past the media end, or the item's interpreted frame rate differs from the file's.

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": {
      "source_item_id": "<source_item_id>",
      "source_time_seconds": "<source_time_seconds>",
      "output_path": "<output_path>"
    },
    "name": "create_source_freeze_frame"
  }
}

Input Schema

Name	Required	Description
`zoom`	No	Optional punch-in keyframes on the placed clip's Motion effect (requires place). Scale is percent as Premiere reports it for the placed still; Position is in sequence pixels.
`place`	No	Optional placement on the active sequence. The range must be empty; nothing is overwritten.
`output_path`	Yes	New .png, .jpg or .jpeg path for the frame. Must not exist; its folder must exist.
`source_item_id`	Yes	Node ID (preferred) or exact name of the source video project item.
`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.
`duration_seconds`	No	Length of the still in seconds, written as its Out mark and read back (default 2, at most 3600).
`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.
`source_time_seconds`	Yes	Seconds from the first frame of the source media (media time zero, not its start timecode and not its In mark). Snapped down to the item's frame grid.
`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

A4.6/5.0

Behavior4/5

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

Annotations only declare readOnlyHint=false, destructiveHint=false and idempotentHint=false; the description goes well beyond that by disclosing the ffmpeg decode path, the no-overwrite policy, the import-plus-Out-mark side effects, the read-back verification of every step, and how partial success is reported. The preflight refusals (no readable local media, time past media end, frame-rate mismatch) are exactly the kind of failure context an agent needs. It stops short of describing the response payload, but an output schema exists to cover that.

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 most decision-relevant fact (source time, not sequence time) is front-loaded in the first clause, and every subsequent sentence carries operational information. It is a dense single paragraph of many semicolon-joined clauses, though, which makes it harder to scan than a short bulleted structure would be for a tool this complex.

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, nested-object, mutation tool with side effects across filesystem and host state, the description covers prerequisites, side effects, verification behavior, partial-failure semantics, and preflight refusals. With an output schema present, no return-value explanation is needed, so nothing an agent requires to call this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning on top: duration_seconds becomes the still's Out mark, zoom is a punch-in on the placed clip's Motion effect and is gated on place, and place must land on an empty range of a video track. The infrastructure parameters (idempotency_key, expected_cep_target, expected_project_path) are left entirely to the schema, which is acceptable given their thorough inline documentation.

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?

States a specific verb and resource ('Create a freeze frame from a project item') and immediately pins the scope to SOURCE-media time, naming the sibling that handles sequence time ('for a sequence time use freeze_frame'). An agent can distinguish this from freeze_frame and capture_frame without opening either schema.

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?

Explicit routing rule to the sibling tool, explicit prerequisites (ffmpeg/ffprobe on PATH, no Source Monitor or QE state), explicit dependency between options (zoom requires place), and explicit refusal conditions before any change. The when-to-use and when-not-to-use cases are both covered.

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

Deploy Server