editor_undo
Undo the most recent edit in the editor's undo history (like Ctrl-Z). Defaults to the edited scene's history; pass scope='global' for the editor-wide history. Returns whether an action was undone, its name, and the remaining undo/redo depth.
This record as markdown: /tools/breakpoint-mcp/editor-undo.md
What editor_undo does on Breakpoint
AI agents use editor_undo to create or update resources in Breakpoint, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Breakpoint environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
scope | string | — | Which history to step: 'scene' (default, the edited scene) or 'global' (editor-wide) |
Parameters from the server's own tool schema.
Why editor_undo is rated Medium
While undo is reversible and could be called Write rather than Destructive, it modifies the editor state by removing or rolling back previous changes. The operation itself is not destructive (data isn't permanently deleted), but it does alter the current state of work.
From the tool's definition Tool performs 'Undo the most recent edit in the editor's undo history' - reverses modifications made to a scene or editor state. This is a reversible operation that modifies state (counteracts previous edits) rather than destructively removing data.
Attacks that exploit this kind of access
The rule that runs editor_undo safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Breakpoint, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For editor_undo, this is the rule to start with:
editor_undo 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 Breakpoint, apply this rule, and every editor_undo call is checked against it from then on.
Questions about editor_undo
Undo the most recent edit in the editor's undo history (like Ctrl-Z). Defaults to the edited scene's history; pass scope='global' for the editor-wide history. Returns whether an action was undone, its name, and the remaining undo/redo depth. It is categorised as a Write tool in the Breakpoint MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
editor_undo accepts 1 parameter: scope. The full parameter table on this page comes from the server's own tool schema.
Register the Breakpoint MCP server in PolicyLayer and add a rule for editor_undo: 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 Breakpoint. Nothing to install.
editor_undo 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 editor_undo 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 editor_undo. 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.
editor_undo is provided by the Breakpoint MCP server (breakpoint-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Breakpoint, and thousands of servers like it.
This server
Across the catalogue