Premiere Pro MCP Server

Create Editorial Plan

create_editorial_plan

Read-onlyIdempotent

Generate a local, evidence-backed editorial plan for workflows like organize, stringout, rough cut, caption review, or platform cutdowns without calling an LLM or changing Premiere.

Instructions

Create a local, evidence-backed editorial workflow plan from captured project context. It never calls an LLM, uploads media, or changes Premiere.

Input Schema

TableJSON Schema

Name	Required	Description
`intent`	Yes	The editorial goal used to retrieve relevant local evidence.
`workflow`	Yes	The workflow to plan. Every workflow remains review-only.
`project_id`	Yes	Project context ID returned by manage_project_context capture.
`sequence_id`	No	Optional exact sequence ID filter for evidence retrieval.
`max_candidates`	No	Maximum evidence candidates to include; defaults to 8.
`platform_targets`	No	Required only for platform_cutdown. These are proposed derivative sequence dimensions; this tool does not create or reframe a sequence.
`organization_rules`	No	Required only for organize. Rules are supplied by the editor or MCP client; the server does not infer categories from filenames alone.

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."

Changed34 schema fields changedv1.14.9Sep 8, 2026
- addedInput schema / additionalProperties
```
Added value: +false
```
- addedInput schema / properties / intent / maxLength
```
Added value: +1000
```
- addedInput schema / properties / intent / minLength
```
Added value: +1
```
- addedInput schema / properties / max_candidates / maximum
```
Added value: +32
```
- addedInput schema / properties / max_candidates / minimum
```
Added value: +1
```
- addedInput schema / properties / max_candidates / type
```
Added value: +"integer"
```
- changedInput schema / properties / organization_rules / items / additionalProperties
```
Previous value: -{}New value: +false
```
- addedInput schema / properties / organization_rules / items / properties / color_index / maximum
```
Added value: +14
```
- addedInput schema / properties / organization_rules / items / properties / color_index / minimum
```
Added value: +0
```
- addedInput schema / properties / organization_rules / items / properties / color_index / type
```
Added value: +"integer"
```
- addedInput schema / properties / organization_rules / items / properties / keywords / items / maxLength
```
Added value: +512
```
- addedInput schema / properties / organization_rules / items / properties / keywords / items / minLength
```
Added value: +1
```
- addedInput schema / properties / organization_rules / items / properties / keywords / maxItems
```
Added value: +64
```
- addedInput schema / properties / organization_rules / items / properties / keywords / minItems
```
Added value: +1
```
- addedInput schema / properties / organization_rules / items / properties / name / maxLength
```
Added value: +255
```
- addedInput schema / properties / organization_rules / items / properties / name / minLength
```
Added value: +1
```
- addedInput schema / properties / organization_rules / maxItems
```
Added value: +16
```
- changedInput schema / properties / platform_targets / items / additionalProperties
```
Previous value: -{}New value: +false
```
- addedInput schema / properties / platform_targets / items / properties / height / maximum
```
Added value: +8192
```
- addedInput schema / properties / platform_targets / items / properties / height / minimum
```
Added value: +16
```
- addedInput schema / properties / platform_targets / items / properties / height / type
```
Added value: +"integer"
```
- addedInput schema / properties / platform_targets / items / properties / name / maxLength
```
Added value: +64
```
- addedInput schema / properties / platform_targets / items / properties / name / minLength
```
Added value: +1
```
- addedInput schema / properties / platform_targets / items / properties / sequence_name / maxLength
```
Added value: +255
```
- addedInput schema / properties / platform_targets / items / properties / sequence_name / minLength
```
Added value: +1
```
- addedInput schema / properties / platform_targets / items / properties / width / maximum
```
Added value: +8192
```
- addedInput schema / properties / platform_targets / items / properties / width / minimum
```
Added value: +16
```
- addedInput schema / properties / platform_targets / items / properties / width / type
```
Added value: +"integer"
```
- addedInput schema / properties / platform_targets / maxItems
```
Added value: +8
```
- addedInput schema / properties / platform_targets / minItems
```
Added value: +1
```
- addedInput schema / properties / project_id / maxLength
```
Added value: +512
```
- addedInput schema / properties / project_id / minLength
```
Added value: +1
```
- addedInput schema / properties / sequence_id / maxLength
```
Added value: +128
```
- addedInput schema / properties / sequence_id / minLength
```
Added value: +1
```

Changed2 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"

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"
+}

Addedv1.13.0Aug 23, 2026

TDQS

A3.7/5.0

Behavior4/5

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

The description explicitly states 'It never calls an LLM, uploads media, or changes Premiere,' which adds meaningful behavioral context beyond the readOnlyHint/openWorldHint annotations. This clarifies data locality and side-effect boundaries. It could mention whether the plan is persisted or returned only, but the coverage is strong.

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, front-loaded with the main action and immediately followed by critical behavioral constraints. No filler or redundancy.

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?

Given the tool has an output schema and 100% schema coverage, the description covers the essential purpose and behavioral limits. It is nearly complete, though explicit guidance on when to use it versus preview_editorial_plan would make it fully self-contained for an agent navigating a large sibling set.

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 parameter semantics are largely handled by the schema descriptions. The description adds useful framing that the plan is 'evidence-backed' and 'from captured project context', which ties the project_id and intent parameters together conceptually. It doesn't add new param-level detail beyond the schema, so it stays at 4 rather than 5.

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 and resource: 'Create a local, evidence-backed editorial workflow plan'. It adds meaningful scope qualifiers (local, evidence-backed, from captured project context). It doesn't explicitly distinguish itself from the close siblings preview_editorial_plan or create_context_edit_plan, which leaves some ambiguity about when this differs from previewing.

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?

The description says what it does but not when to use it versus alternatives like preview_editorial_plan or create_context_edit_plan. No exclusions, prerequisites (beyond schema references to manage_project_context), or conditions are given. An agent has to infer usage from the schema.

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

Deploy Server