premiere-pro-mcp

Overview Schema Source Related Servers Discussions Admin

Search Project Context

search_project_context

Read-onlyIdempotent

Search a Premiere project-context index for sources, timeline placements, transcripts, shots, audio, and notes, returning bounded evidence with stable IDs and revisions without modifying Premiere.

Instructions

Search a durable Premiere project-context index for relevant sources, timeline placements, transcript passages, shots, audio observations, and notes. Returns bounded evidence with stable IDs and revisions; it never changes Premiere.

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": {
      "project_id": "<project_id>",
      "query": "<query>"
    },
    "name": "search_project_context"
  }
}

Input Schema

Name	Required	Description
`kinds`	No	Optional context-kind filter
`query`	Yes	Natural-language or keyword query matched against indexed evidence
`project_id`	Yes	Project context ID returned by manage_project_context capture
`max_results`	No	Maximum 50; default 12
`sequence_id`	No	Optional exact sequence ID filter
`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.
`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

A3.8/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description still adds real value beyond them: results are 'bounded evidence' carrying 'stable IDs and revisions', which tells the agent results are referenceable in downstream tools and that staleness can be detected. It omits pagination/continuation behavior, which is a minor gap given the max_results cap.

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

Conciseness5/5

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

Two sentences, zero filler, with the resource and the safety guarantee front-loaded. Every clause (durability, evidence kinds, bounded returns, stable IDs/revisions, non-mutation) carries distinct information.

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 and full schema description coverage across all 8 parameters, the description carries only the burden of purpose and guarantees, which it discharges. The one thing an agent might still want — how to page or widen a search when results are truncated — is not addressed, but that is a small omission for an otherwise well-specified tool.

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 schema already documents query, kinds, max_results, project_id, and the guard parameters, making 3 the baseline. The description's enumeration of evidence types loosely maps to the `kinds` filter values but adds no syntax or selection guidance beyond the schema. Note the schema includes a heavy idempotency_key/edit-oriented parameter that is inert for a read-only search, and the description does nothing to clarify that.

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 ('Search') and a specific resource ('durable Premiere project-context index'), then enumerates exactly what kinds of evidence are indexed (sources, timeline placements, transcript passages, shots, audio observations, notes). An agent knows precisely what corpus is being queried. It stops short of naming how it differs from sibling search_project_items, so it falls short of a 5.

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?

The phrase 'never changes Premiere' implicitly rules out mutation use cases, and 'context index' implies a different corpus than live project inspection, but no explicit when-to-use or when-to-prefer-an-alternative guidance is given. An agent must infer from the sibling names whether to use this or search_project_items / manage_project_context.

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

Deploy Server