premiere-pro-mcp

Overview Schema Source Related Servers Discussions Admin

Export Sequence

export_sequence

Export the active sequence with an Adobe Media Encoder preset and verify the rendered file's duration and optional audio signal before confirming the write.

Instructions

Export the active sequence directly (Premiere renders it; blocks until done) with an Adobe Media Encoder preset. The output extension must match what the preset writes (an H.264 preset in AME's QuickTime folder writes .mov); a missing extension is added. Refuses an output_path that already exists unless overwrite is true. Fails if Premiere rejects the render, verifies a non-empty file was written (for an overwrite, that the file changed), and checks its duration with ffprobe within one sequence frame. An unavailable or mismatched duration leaves a written artifact unverified. Optional audio_check reports decoded signal, silence, absent audio or an unavailable check; expect_signal makes a silent or absent stream fail verification. Signal does not establish audibility, sync or sound quality. range 'work_area' fails closed unless the work area is enabled and covers only part of the sequence — otherwise Premiere would encode the entire timeline.

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": {
      "output_path": "<output_path>"
    },
    "name": "export_sequence"
  }
}

Input Schema

Name	Required	Description
`range`	No	What to render: the entire sequence (default), the sequence in/out range (set_sequence_in_out_points), or the work area. work_area requires an enabled work area around part of the sequence; unset or full-sequence work areas are refused instead of encoding everything. Set and read back a valid work area where the host supports it, or use in_to_out for a ranged export.
`overwrite`	No	Replace a file that already exists at output_path (default: false, which refuses the export). The replacement is only reported as written when the file's size or modification time changes.
`audio_check`	No	Optional full-file first-audio-stream decode via ffprobe/FFmpeg, with a separate 5-minute decode timeout. report only classifies signal/silence/absence; expect_signal marks a silent or absent stream as a failed check, or unavailable evidence as unverified. Omit for the existing duration-only behavior. Even noise or inaudibly quiet samples count as signal; does not check speech, synchronization or audible quality.
`output_path`	Yes	Full output file path (e.g., '/Users/me/exports/video.mp4')
`preset_path`	No	Path to an AME preset file (.epr). Uses the default H.264 (MP4) Match Source preset if omitted.
`work_area_only`	No	Deprecated alias for range: 'work_area'
`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.
`timeout_minutes`	No	How long to wait for the render (default: 15; long sequences such as full podcast episodes may need more)
`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

A4.2/5.0

Behavior3/5

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

Rich disclosure of failure modes, verification steps (non-empty file, changed file on overwrite, ffprobe duration within one frame), and what audio_check does and does not prove. However, much of this text is duplicated verbatim in the schema parameter descriptions, so it adds less beyond structured fields than it first appears; annotations already declare non-read-only, non-destructive.

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?

Front-loaded: the first clause states the action and its blocking nature, then the preset/extension contract. Later sentences are dense but earn their place by covering verification and audio caveats; the audio_check caveat chain is somewhat repetitive.

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?

Handles the hard parts of a 10-parameter, nested-schema, long-running write tool: timeout behavior, blocking semantics, verification outcome including the 'written but unverified' case, and idempotency retry guidance in the schema. Nothing an agent needs to call it safely 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 meaning the schema does not: the extension must match the preset's output format and is auto-appended, and overwrite refusal semantics are stated up front.

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?

Names a specific verb and resource ('Export the active sequence directly'), states the rendering mechanism ('Premiere renders it; blocks until done'), and implicitly separates itself from the async sibling export_sequence_job_start by emphasizing that the call blocks.

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?

Gives concrete when-to-use guidance for the risky modes: range 'work_area' fails closed unless the work area is enabled and partial, with a fallback to in_to_out; overwrite is opt-in. It does not explicitly say when to prefer export_sequence_job_start or the XML/EDL siblings, which keeps it short of a 5.

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

Deploy Server