Undo the last operation. Returns information about what was undone.
AI agents use bulc_undo to create or update resources in BULC Building Designer — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your BULC Building Designer environment.
Undo reverts modifications made by Write-category operations (creating rooms, walls, meshes) but does not irreversibly delete data—the original state is restored and the undone action can be reapplied (redo). This places it in Write rather than Destructive.
From the tool's definition The tool name is 'bulc_undo' and the description states it 'Undo the last operation.' Undo is a reversible operation that reverts the last write action (create_room, create_wall, etc.) back to a prior state without permanently destroying data.
Attacks that exploit this kind of access
Undo the last operation. Returns information about what was undone. It is categorised as a Write tool in the BULC Building Designer MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the BULC Building Designer MCP server in PolicyLayer and add a rule for bulc_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 BULC Building Designer. Nothing to install.
bulc_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 bulc_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 bulc_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.
bulc_undo is provided by the BULC Building Designer MCP server (using76/bulc_mcp). 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 →