Premiere Pro MCP Server

Get Capabilities

get_capabilities

Read-onlyIdempotent

Discover available Premiere Pro operations, backend coverage, authority, and verification needs; query by task keywords or exact names to find ranked, session-specific tools.

Instructions

Discover Premiere operations and report backend coverage, authority, and verification requirements. Use tool_query with task keywords (for example transcript, captions, or review frames) for ranked, bounded matches available in this session. Use tool_names for exact lookups or tool_offset/tool_limit for paging. Discovery never grants authority or proves a live host is ready.

Input Schema

TableJSON Schema

Name	Required	Description
`tool_limit`	No	Maximum tool catalog entries to return. Omit with tool_offset to preserve the complete legacy response.
`tool_names`	No	Optional exact tool-name allowlist. Returns only those catalog entries while retaining the overall capability summary.
`tool_query`	No	Optional case-insensitive keywords matched against tool names and descriptions. Exact names rank first. Search defaults to 20 results with descriptions and session availability; page with tool_offset/tool_limit.
`tool_offset`	No	Zero-based offset into the filtered tool catalog. Pair with tool_limit for an explicitly sized page.
`available_only`	No	Filter to tools registered under this session's authority and tool packs. Defaults to true for tool_query, false otherwise. Set false to diagnose unavailable matches; this does not enable them.

Output Schema

TableJSON 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.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.18.6Sep 30, 2026

changedOutput schema / properties / data / description

Previous value: -"Tool-specific result data when ok is true."New value: +"Tool-specific result data when ok is true; on failure, diagnostic detail when the tool provides it."

Changed13 schema fields changedv1.14.9Sep 8, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

addedInput schema / properties / available_only

Added value: +{
+  "description": "Filter to tools registered under this session's authority and tool packs. Defaults to true for tool_query, false otherwise. Set false to diagnose unavailable matches; this does not enable them.",
+  "type": "boolean"
+}

addedInput schema / properties / tool_limit / maximum
```
Added value: +128
```
addedInput schema / properties / tool_limit / minimum
```
Added value: +1
```
addedInput schema / properties / tool_limit / type
```
Added value: +"integer"
```
addedInput schema / properties / tool_names / items / maxLength
```
Added value: +256
```
addedInput schema / properties / tool_names / items / minLength
```
Added value: +1
```
addedInput schema / properties / tool_names / maxItems
```
Added value: +128
```
addedInput schema / properties / tool_names / minItems
```
Added value: +1
```
addedInput schema / properties / tool_names / uniqueItems
```
Added value: +true
```
addedInput schema / properties / tool_offset / minimum
```
Added value: +0
```
addedInput schema / properties / tool_offset / type
```
Added value: +"integer"
```

addedInput schema / properties / tool_query

Added value: +{
+  "description": "Optional case-insensitive keywords matched against tool names and descriptions. Exact names rank first. Search defaults to 20 results with descriptions and session availability; page with tool_offset/tool_limit.",
+  "maxLength": 256,
+  "minLength": 1,
+  "pattern": "\\S",
+  "type": "string"
+}

Changed5 schema fields changedv1.14.4Aug 29, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

addedInput schema / properties / tool_limit

Added value: +{
+  "description": "Maximum tool catalog entries to return. Omit with tool_offset to preserve the complete legacy response."
+}

addedInput schema / properties / tool_names

Added value: +{
+  "description": "Optional exact tool-name allowlist. Returns only those catalog entries while retaining the overall capability summary.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / tool_offset

Added value: +{
+  "description": "Zero-based offset into the filtered tool catalog. Pair with tool_limit for an explicitly sized page."
+}

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"
+}

Addedv1.4.0Jul 27, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world behavior. The description adds meaningful context beyond annotations by warning that discovery never grants authority or proves a live host is ready, which is an important behavioral limitation for an agent.

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?

The description is four short sentences, front-loaded with what the tool does, followed by concrete query guidance and a key limitation. Every sentence earns its place without repetition or bloat.

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?

Given that the tool has no required parameters, complete schema coverage, annotations covering safety, and an output schema, the description provides enough context for correct invocation. It covers purpose, query modes, and the critical caveat that discovery does not grant authority or prove host readiness.

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 all five parameters in detail. The description repeats some query-mode usage and adds keyword examples, but it does not mention available_only and adds little parameter semantics beyond what the schema already provides.

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 states a specific verb and resource: discover Premiere operations and report backend coverage, authority, and verification requirements. It clearly distinguishes this catalog-discovery tool from action-oriented siblings, and the opening sentence front-loads the tool's scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

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

It gives clear internal usage guidance: use tool_query for ranked, bounded keyword matches, tool_names for exact lookups, and tool_offset/tool_limit for paging. It does not explicitly name when to choose this tool over similar capability/inspection siblings, so it falls short of the highest tier but is much better than mere implied usage.

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

Deploy Server