premiere-pro-mcp

Overview Schema Source Related Servers Discussions Admin

Encode Project Item

encode_project_item

Queue a Premiere project item for Adobe Media Encoder using a preset and output path; optionally start the ready AME queue. Verify the returned job ID independently because the handoff is unverified.

Instructions

Request an Adobe Media Encoder encode for a project item. Requires a saved project. The returned job ID is an unverified handoff; verify queue presence or the output file independently. Optional start_batch requests processing of every ready AME queue job, including unrelated jobs.

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": {
      "item_id": "<item_id>",
      "output_path": "<output_path>",
      "preset_path": "<preset_path>"
    },
    "name": "encode_project_item"
  }
}

Input Schema

Name	Required	Description
`item_id`	Yes	Node ID or name of the project item to encode, or the sequence ID of a sequence
`output_path`	Yes	Full output file path
`preset_path`	Yes	Path to an AME preset file (.epr)
`start_batch`	No	Opt in to start the entire ready Adobe Media Encoder queue after this handoff, including unrelated jobs. Default false (enqueue only). A successful call does not verify that any render started or completed.
`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.
`remove_on_completion`	No	Remove from queue on completion (default: true)
`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

A3.7/5.0

Behavior4/5

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

Goes well beyond the annotations (which only say non-readonly, non-idempotent, non-destructive, closed-world) by disclosing that the returned job ID is an unverified handoff requiring independent confirmation of queue presence or output file. It also scopes the side effect of start_batch to the entire AME queue including unrelated jobs, which is a real caveat an agent must know. It stops short of describing failure modes or the CEP/UXP guard behavior documented in the schema.

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?

Three tight sentences, front-loaded with the action and the precondition, with no filler. The third sentence partially duplicates the start_batch schema description, which is the only redundancy.

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

Completeness4/5

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

With an output schema present, the description correctly focuses on the risky part of the return value (unverified job ID) rather than documenting the payload, and it flags the saved-project requirement. Given 8 parameters including nested guard objects and a non-obvious batch side effect, the definition covers what an agent needs to call safely, though the CEP/UXP guard semantics are left entirely to the schema.

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 baseline is 3. The description only elaborates on start_batch, and even that largely restates the schema's own wording ('including unrelated jobs'); item_id, output_path, preset_path, and the large guard/idempotency parameters get no additional meaning from the description.

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?

States a specific verb and resource ('Request an Adobe Media Encoder encode for a project item') plus the key precondition ('Requires a saved project'). It does not name the closely related siblings encode_file or start_batch_encode, so an agent must infer which of the three to pick, but the resource scope is unambiguous.

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?

Provides one hard prerequisite (a saved project) and warns that the start_batch flag extends processing to unrelated queue jobs, which is useful decision context. However, it never says when to use this tool instead of encode_file or start_batch_encode, nor when to omit start_batch, so routing is left to inference.

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

Deploy Server