Undo the last atomic operation in SketchUp. One MCP tool-call = one undo step.
AI agents use undo to create or update resources in Sketchup Mcp2 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sketchup Mcp2 environment.
The undo tool reverses a previous action in SketchUp, restoring the application state to what it was before the last operation. This is a reversible state modification (it can be re-done), making it a Write-category operation. Misuse could inadvertently reverse legitimate user work, but the blast radius is low since it only undoes one step at a time and the action itself is recoverable via redo.
From the tool's definition Undo the last atomic operation in SketchUp. One MCP tool-call = one undo step.
Attacks that exploit this kind of access
Undo the last atomic operation in SketchUp. One MCP tool-call = one undo step. It is categorised as a Write tool in the Sketchup Mcp2 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sketchup Mcp2 MCP server in PolicyLayer and add a rule for 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 Sketchup Mcp2. Nothing to install.
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 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 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.
undo is provided by the Sketchup Mcp2 MCP server (zinin/sketchup-mcp2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →