This record as markdown: /tools/easehee-rhino-mcp/rhino-undo.md
What rhino_undo does on Rhino
AI agents use rhino_undo to create or update resources in Rhino, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Rhino environment.
Why rhino_undo is rated Medium
While undo can revert destructive actions, it is itself a reversible modification tool—not destructive, since undo operations themselves can be undone (via redo). It falls under Write rather than Destructive because the modification is intentionally reversible. The severity is medium because an AI agent repeatedly calling undo could erase user work, but the user can undo the undo, mitigating full data loss.
From the tool's definition The tool name 'rhino_undo' and description 'Undo the last operation(s) in the Rhino document' indicate it modifies the state of the Rhino document by reverting changes. Undo is a reversible operation that alters document state.
Attacks that exploit this kind of access
The rule that runs rhino_undo safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Rhino, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For rhino_undo, this is the rule to start with:
rhino_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 Rhino, apply this rule, and every rhino_undo call is checked against it from then on.
Questions about rhino_undo
Undo the last operation(s) in the Rhino document. It is categorised as a Write tool in the Rhino MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Rhino MCP server in PolicyLayer and add a rule for rhino_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 Rhino. Nothing to install.
rhino_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 rhino_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 rhino_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.
rhino_undo is provided by the Rhino MCP server (easehee/rhino-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Rhino, and thousands of servers like it.
This server
Across the catalogue