detect_scene_edits
Detects scene changes in selected clips and optionally adds cuts or markers.
This record as markdown: /tools/adobe-premiere-pro-mcp/detect-scene-edits.md
What detect_scene_edits does on Adobe Premiere Pro
AI agents use detect_scene_edits to create or update resources in Adobe Premiere Pro, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Adobe Premiere Pro environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
action | string | — | Action to take at detected edit points |
sequenceId | string | Yes | The ID of the sequence |
sensitivity | string | — | Detection sensitivity (e.g., "Low", "Medium", "High") |
allowUnsafeSynchronous | boolean | — | Actually invoke Premiere scene detection synchronously; can block CEP for a long time |
applyCutsToLinkedAudio | boolean | — | Whether to apply cuts to linked audio |
Parameters from the server's own tool schema.
Why detect_scene_edits is rated Medium
The tool performs read-like analysis (detecting scene changes) but optionally writes changes to the project by adding cuts or markers. Since it can modify the timeline/project data, Write is the appropriate category. The severity is medium because misuse could alter timeline structure, though changes in a video editing context are generally reversible.
From the tool's definition Detects scene changes in selected clips and optionally adds cuts or markers
Attacks that exploit this kind of access
The rule that runs detect_scene_edits safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Adobe Premiere Pro, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For detect_scene_edits, this is the rule to start with:
detect_scene_edits stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Adobe Premiere Pro, apply this rule, and every detect_scene_edits call is checked against it from then on.
Questions about detect_scene_edits
Detects scene changes in selected clips and optionally adds cuts or markers. It is categorised as a Write tool in the Adobe Premiere Pro MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
detect_scene_edits accepts 5 parameters: action, sequenceId, sensitivity, allowUnsafeSynchronous, applyCutsToLinkedAudio. Required: sequenceId. The full parameter table on this page comes from the server's own tool schema.
Register the Adobe Premiere Pro MCP server in PolicyLayer and add a rule for detect_scene_edits: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Adobe Premiere Pro. Nothing to install.
detect_scene_edits is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the detect_scene_edits rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for detect_scene_edits. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
detect_scene_edits is provided by the Adobe Premiere Pro MCP server (adobe-premiere-pro-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Adobe Premiere Pro, and thousands of servers like it.
This server
Across the catalogue