Skip to main content
Glama
leancoderkavy

Premiere Pro MCP Server

by leancoderkavy
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Manage Project Context

manage_project_context
Destructive

Capture active sequence and source metadata, enrich it with revision-bound editorial evidence, and inspect or clear the local index to keep Premiere Pro project data current.

Instructions

Capture, enrich, import revision-bound editorial evidence, inspect, or clear a durable local Premiere project-context index. Capture stores bounded active-sequence/source metadata; local enrichment and evidence import add caller-approved transcripts, speaker labels, shots, audio observations, notes, or opaque frame references without re-analyzing media. Never include secrets or unrelated customer data.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesCapture active context, enrich it, import revision-bound editorial evidence, inspect status, or clear one local project index.
recordsNoFor enrich, up to 512 transcript, shot, audio, or note records
replaceNoFor enrich, replace prior enrichments while retaining captured core records
evidenceNoFor import_evidence, up to 512 caller-approved records with strict source/timeline revision guards. The server does not read referenced frame files, invoke analysis, or contact a provider.
project_idNoProject context ID returned by capture; optional for status to list projects

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okYesWhether the tool completed successfully.
dataNoTool-specific result data when ok is true.
toolYesThe registered MCP tool name.
errorNoFailure detail when ok is false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv1.14.9
    • changedInput schema / properties / action / description
      Previous value: -"Capture active context, enrich it, inspect status, or clear one local project index"New value: +"Capture active context, enrich it, import revision-bound editorial evidence, inspect status, or clear one local project index."
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "capture",
-  "enrich",
-  "status",
-  "clear"
-]New value: +[
+  "capture",
+  "enrich",
+  "import_evidence",
+  "status",
+  "clear"
+]
    • addedInput schema / properties / evidence
      Added value: +{
+  "description": "For import_evidence, up to 512 caller-approved records with strict source/timeline revision guards. The server does not read referenced frame files, invoke analysis, or contact a provider.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "end_seconds": {
+        "description": "Optional end in seconds at or after start_seconds.",
+        "minimum": 0,
+        "type": "number"
+      },
+      "frame_reference_id": {
+        "description": "For frame_reference, an opaque fixture or review-frame identifier, never a native file path or URL.",
+        "maxLength": 256,
+        "type": "string"
+      },
+      "id": {
+        "description": "Optional stable evidence ID for deterministic replacement.",
+        "maxLength": 256,
+        "type": "string"
+      },
+      "keywords": {
+        "description": "Optional local search keywords.",
+        "items": {
+          "description": "One local search keyword.",
+          "maxLength": 256,
+          "type": "string"
+        },
+        "maxItems": 64,
+        "type": "array"
+      },
+      "metadata": {
+        "description": "Optional small scalar metadata. Credential-like and path-like keys are discarded before local storage.",
+        "type": "object"
+      },
+      "name": {
+        "description": "Optional bounded display name for the local evidence record.",
+        "maxLength": 512,
+        "type": "string"
+      },
+      "sequence_id": {
+        "description": "Optional captured sequence ID. Requires the exact current timeline_revision.",
+        "maxLength": 512,
+        "type": "string"
+      },
+      "source_id": {
+        "description": "Optional captured source ID. Requires the exact current source_revision.",
+        "maxLength": 512,
+        "type": "string"
+      },
+      "source_revision": {
+        "description": "Required exact source revision whenever source_id is supplied.",
+        "maxLength": 256,
+        "type": "string"
+      },
+      "speaker_label": {
+        "description": "For transcript_passage or speaker_label, an editor-supplied speaker label. It is not inferred by this server.",
+        "maxLength": 160,
+        "type": "string"
+      },
+      "start_seconds": {
+        "description": "Optional non-negative source or sequence start in seconds.",
+        "minimum": 0,
+        "type": "number"
+      },
+      "text": {
+        "description": "Caller-approved local evidence text. Required except for speaker_label and frame_reference, which can derive a bounded local note.",
+        "maxLength": 20000,
+        "type": "string"
+      },
+      "timeline_item_id": {
+        "description": "Optional captured timeline item ID. Requires the exact current timeline_revision.",
+        "maxLength": 512,
+        "type": "string"
+      },
+      "timeline_revision": {
+        "description": "Required exact timeline revision whenever sequence_id or timeline_item_id is supplied.",
+        "maxLength": 256,
+        "type": "string"
+      },
+      "track_index": {
+        "description": "Optional recorded track index when the evidence is tied to a timeline item.",
+        "minimum": 0,
+        "type": "number"
+      },
+      "track_type": {
+        "description": "Optional recorded track type when the evidence is tied to a timeline item.",
+        "enum": [
+          "video",
+          "audio"
+        ],
+        "type": "string"
+      },
+      "type": {
+        "description": "Evidence shape: transcript passage, speaker label, shot log, audio observation, operator note, or an opaque frame reference.",
+        "enum": [
+          "transcript_passage",
+          "speaker_label",
+          "shot_log",
+          "audio_observation",
+          "operator_note",
+          "frame_reference"
+        ],
+        "type": "string"
+      }
+    },
+    "required": [
+      "type"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
    • removedInput schema / properties / records / items / additionalProperties
      Removed value: -{}
    • removedInput schema / properties / records / items / properties / metadata / additionalProperties
      Removed value: -{}
    • removedInput schema / properties / records / items / properties / metadata / propertyNames
      Removed value: -{
-  "type": "string"
-}
  2. Changed2 schema fields changedv1.14.4
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": false,
+  "properties": {
+    "data": {
+      "description": "Tool-specific result data when ok is true."
+    },
+    "error": {
+      "description": "Failure detail when ok is false.",
+      "type": "string"
+    },
+    "ok": {
+      "description": "Whether the tool completed successfully.",
+      "type": "boolean"
+    },
+    "tool": {
+      "description": "The registered MCP tool name.",
+      "minLength": 1,
+      "type": "string"
+    }
+  },
+  "required": [
+    "ok",
+    "tool"
+  ],
+  "type": "object"
+}
  3. Addedv1.11.3

TDQS

A4/5.0
Behavior4/5

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

Annotations already signal destructiveness and non-read-only behavior; the description adds valuable context beyond those flags: the index is durable and local, evidence import is caller-approved, media is not re-analyzed, and secrets or unrelated customer data must never be included. It does not contradict annotations and provides meaningful side-effect context, though the full destructive scope of 'clear' is left implicit.

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?

Three sentences, each earning its place: the first states the full action scope, the second clarifies the capture/enrich/import data contract and constraint, and the third is a necessary safety warning. The key verbs and resource are front-loaded with no filler.

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?

For a complex five-action tool with rich schemas and an output schema, the description provides enough high-level context for an agent to understand the tool's purpose and safety posture. Per-field specifics, revision guards, and limits are delegated to the schema, which is acceptable; a bit more about the relationship between actions and the returned project_id would make it fully complete.

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 adds some conceptual alignment by naming transcripts, speaker labels, shots, audio observations, notes, and frame references, which map to the record/evidence kinds, but it does not add syntax-level meaning beyond what the schema already documents.

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?

The description opens with a precise list of specific operations—capture, enrich, import evidence, inspect, clear—applied to a clearly defined resource: a durable local Premiere project-context index. This makes the tool's role immediately distinguishable from read-style siblings like search_project_context, even without naming them.

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 description gives useful in-tool guidance: capture stores bounded metadata, while enrichment and evidence import add caller-approved content without re-analyzing media. It implies a workflow of capture-then-enrich, but it never explicitly addresses when to choose this tool over siblings such as search_project_context or create_editorial_context_pack, and it offers no exclusions.

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