Skip to main content
Glama

Manage Proxies

manage_proxies
Destructive

Create, attach, or toggle proxy media for a Premiere Pro project item, and set app-wide proxy display on or off with read-back verification.

Instructions

Create or attach proxies for a project item, or set Premiere's proxy display. 'toggle' is application-wide, not per item: it changes app.getEnableProxies()/setEnableProxies() for every sequence and monitor, and item_id is only checked to exist. Pass enabled: true or false to set a known state; omitting enabled flips the current state, so two calls undo each other. The result reports previousEnabled and proxiesEnabled read back from Premiere. Note: 'create' only requests a proxy encode from Adobe Media Encoder and returns an unverified handoff. Independently verify the AME queue or output file before calling this tool again with action 'attach' and proxy_path set to the output_path you passed here. Optional start_batch requests processing of every ready AME queue job, including unrelated jobs. There is no single-call create-and-attach in Premiere's ExtendScript API.

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>",
      "action": "<action>"
    },
    "name": "manage_proxies"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYesAction to perform on proxies
enabledNoFor 'toggle' only: sets the application-wide proxy display to this state (true shows proxies, false shows full-resolution media) and verifies it by reading app.getEnableProxies() back. Omit to flip the current state, which is discouraged because the outcome depends on a state you have not read.
item_idYesNode ID or name of the project item, or the sequence ID of a sequence
proxy_pathNoPath to an existing proxy file (required for 'attach')
output_pathNoFull output path for the proxy to be rendered to (required for 'create')
preset_pathNoPath to a proxy ingest preset (.epr) for 'create'. If omitted, the server lists Premiere's IngestPresets/Proxy presets and AME H.264 system presets, skips every preset whose output destination is Same as Project (Adobe's shipped proxy presets are), and uses the first remaining one. Fails with a clear error when none qualify.
start_batchNoOpt 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_keyNoOptional 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_targetNoOptional reviewed CEP sequence/clip identity and exact tick ranges. Checked before every generated command; UXP refuses this CEP-only guard.
expected_project_pathNoOptional 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

NameRequiredDescriptionDefault
okYesWhether the tool completed successfully.
dataNoTool-specific result data when ok is true; on failure, diagnostic detail when the tool provides it.
toolYesThe registered MCP tool name.
errorNoFailure detail when ok is false.
receiptNoVersioned common mutation receipt; success never implies rendered verification.
idempotencyNoPresent 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.

  1. First observedv1.30.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and idempotentHint=false; the description adds genuinely new behavioral facts, notably that 'create' is an unverified handoff to Media Encoder, that 'toggle' mutates global application state and merely checks item_id existence, and that the result reports previousEnabled/proxiesEnabled read back from Premiere. It is consistent with the annotations throughout. Only mild gap: it does not restate irreversibility or permission requirements in one place, though 'destructive' hints cover the safety profile.

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?

Dense but front-loaded: the primary purpose comes first, followed by the per-action caveats, with no filler sentences. It is a single long block rather than visually separated bullets, which slightly slows scanning of the distinct caveats, but every clause carries real information.

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 10-parameter, nested-schema mutation tool with an output schema, the description covers the risky parts an agent cannot infer: global state mutation, the non-atomic create/attach handoff, and batch side effects. Return values are covered by the output schema, and the guard/idempotency parameters are thoroughly documented in the schema itself.

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; the description goes beyond it by explaining the cross-parameter contract that 'attach' should use the proxy_path equal to the output_path previously passed to 'create' – a workflow binding the schema cannot express. It also reinforces the enabled/flip semantics and the scope of start_batch. It adds less on item_id, preset_path and the guard/idempotency parameters, which the schema handles.

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?

Opens with a specific verb+resource and enumerates the three actions: creating or attaching proxies for a project item, plus setting Premiere's application-wide proxy display. It explicitly distinguishes 'toggle' (application-wide, not per item) from the item-scoped 'create' and 'attach', so an agent can tell the three modes apart without opening the 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?

Gives explicit when/when-not guidance for each branch: pass enabled for a known state rather than omitting it to flip, verify the AME queue before calling again with 'attach' and the same output_path, and be aware start_batch touches unrelated jobs. It also states that a single-call create-and-attach does not exist, which preempts a plausible wrong assumption by the agent.

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

Deploy Server

Other Tools