premiere-pro-mcp

Overview Schema Source Related Servers Discussions Admin

Add Marker

add_marker

Adds a marker at a specified time to the active sequence or clip and reads back its name, comments, color, and duration.

Instructions

Add a marker to the active sequence or a clip and read its name, comments, color and duration back. EXPERIMENTAL (QE DOM): the receipt reports undoStackIndex movement, which does not prove QE can reverse the marker. Every marker attempt protects an engine undo boundary; undoTracked:false means the marker did not observably advance the QE index. Marker start and end storage are compared at exact integer ticks; unsupported time writes remain unverified with the created marker identity when available.

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": {
      "time_seconds": "<time_seconds>"
    },
    "name": "add_marker"
  }
}

Input Schema

Name	Required	Description
`name`	No	Name/label for the marker
`color`	No	Marker color index (0=Green, 1=Red, 2=Purple, 3=Orange, 4=Yellow, 5=White, 6=Blue, 7=Cyan)
`node_id`	No	Optional clip node ID to add the marker to that clip instead of the sequence. Premiere 25.2.3 timeline clips have no marker collection, so this refuses there and names the source time to use with add_marker_to_project_item.
`comments`	No	Comments for the marker
`time_seconds`	Yes	Time position in seconds for the marker
`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	Duration of the marker in seconds (0 for point marker)
`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

B3.3/5.0

Behavior4/5

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

Annotations only declare the generic write profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), and the description substantially adds to it: EXPERIMENTAL/QE DOM status, the fact that each attempt protects an engine undo boundary, that undoTracked:false signals the marker did not advance the QE index, and that start/end storage is compared at exact integer ticks with unsupported time writes left unverified. That is genuine behavioral context an agent could not get from annotations, though the QE-internal jargon is hard to act on.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded in one clean sentence, but the remaining three sentences are dense internal jargon ('QE DOM', 'undoStackIndex', 'protects an engine undo boundary') whose operational meaning is unclear, and the final sentence about unverified time writes is vague. It is not padded with filler, but it is not efficiently readable either.

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

Completeness3/5

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

An output schema exists and schema coverage is complete, so return values and parameters are well covered. However, for a 9-parameter mutation tool the description never says what happens on failure beyond cryptic QE notes, gives no guidance about the clip-vs-sequence route or batch alternatives, and the experimental caveats are stated too abstractly for an agent to plan a retry.

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%, including detailed per-field docs (color index legend, node_id fallback behavior, idempotency_key semantics), so the schema already carries parameter meaning. The description adds only the tick-comparison note about start/end storage, which is marginal on top of that coverage — baseline 3 applies.

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?

The opening sentence states a specific verb and resource ('Add a marker') and scopes it to the active sequence or a clip, plus notes the read-back of name, comments, color and duration. It does not, in the description prose itself, differentiate against siblings such as add_marker_to_project_item or add_markers_batch — that routing only appears in the node_id parameter description inside 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 Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use or when-not-to-use guidance in the description: nothing tells the agent to prefer add_markers_batch for multiple markers, update_marker for edits, or add_marker_to_project_item when the clip route fails. The only routing hint lives in the schema's node_id field, so the description itself leaves usage selection 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