Premiere Pro MCP Server

Export Sequence Job Start

export_sequence_job_start

Starts an asynchronous Adobe Media Encoder export of the active sequence and returns a job ID immediately, so long renders don't block the call. Poll job status until it reports completed or failed.

Instructions

Start an asynchronous Adobe Media Encoder export of the active sequence and return a job id at once, so long renders (such as full episodes) do not hold the MCP call open. Poll get_export_job_status until it reports completed or failed. Requires a saved project, an .epr preset_path (Same as Project presets are refused), an existing output folder, and an output_path with no file yet (existing files are always refused; AME may otherwise rename or overwrite). The output extension must match the preset; a missing extension is added. range follows export_sequence: in_to_out and work_area fail closed instead of encoding the whole timeline. start_batch (default true) asks AME to start every ready queue job, including unrelated ones. Success means AME accepted the job (committed_unverified); render completion and the file are verified later by get_export_job_status. Jobs are tracked only by this server process.

Input Schema

Name	Required	Description
`range`	No	What to render: the entire sequence (default), the sequence in/out range, or an enabled work area around part of the sequence. Ranged modes are refused when they would encode the whole timeline.
`output_path`	Yes	Full output file path that does not exist yet, in an existing folder (e.g., '/Users/me/exports/episode-12.mp4')
`preset_path`	Yes	Required path to an Adobe Media Encoder preset file (.epr) with an explicit output location (not Same as Project)
`start_batch`	No	Ask Adobe Media Encoder to start its queue after queuing this job (default true). This starts every ready AME job, including unrelated ones. Pass false to only queue it; the job then stays queued until the AME queue is started (start_batch_encode).
`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 one HTTP session) 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.

Addedv1.25.0Oct 24, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well past the annotations (destructiveHint=false, openWorldHint=false, idempotentHint=false) and discloses real behavioral traits: existing files are always refused because AME may rename or overwrite, ranged modes fail closed rather than encoding the whole timeline, start_batch true will also start unrelated ready jobs, and success means only committed_unverified with the file verified later. It also warns that jobs are tracked only by this server process, which an agent needs before assuming durability across restarts.

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-loads purpose and the polling instruction before the precondition list, and every sentence carries an operational fact. A few clauses restate what the schema already documents (preset_path must be .epr and not Same as Project, start_batch semantics), which keeps it slightly dense but not padded.

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 7-parameter mutation with nested guard objects and an output schema, the description covers everything an agent needs to invoke it correctly: prerequisites, failure modes, queue side effects, and what a success result actually means. Return-value detail is correctly delegated to the output schema.

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 lacks: the extension must match the preset and a missing extension is added, ranged modes fail closed, and the success state for output_path is committed_unverified rather than a finished file. The nested guard parameters (expected_cep_target, expected_project_path) are left to the schema's own descriptions.

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 ("Start an asynchronous Adobe Media Encoder export of the active sequence") plus the immediate effect (returns a job id) and the reason (long renders must not hold the MCP call open). That clearly separates it from the synchronous export_sequence, and it names get_export_job_status as the completion path.

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 clear context for use (long renders, poll get_export_job_status until completed/failed) and lays out hard preconditions - saved project, .epr preset_path that is not Same as Project, existing output folder, output_path with no file, matching extension. It stops short of an explicit exclusion, never saying when to prefer export_sequence or add_to_render_queue instead, so the routing to the synchronous alternative is implied rather than stated.

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

Deploy Server