Undo the last operation
AI agents use undo to create or update resources in AI-Canvas MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AI-Canvas MCP Server environment.
While 'undo' restores prior state, it is fundamentally a write operation that modifies the current design document. It does not delete data irreversibly (Destructive category), but it does change document state. Severity is medium because misuse could revert intentional changes, but the operation is itself reversible via redo.
From the tool's definition Tool named 'undo' with description 'Undo the last operation' – reverses a modification to design state, restoring a previous state. This is a write-class operation (modifies design documents) that is reversible (can be re-done).
Attacks that exploit this kind of access
Undo the last operation. It is categorised as a Write tool in the AI-Canvas MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AI-Canvas MCP Server 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 AI-Canvas MCP Server. 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 AI-Canvas MCP Server MCP server (laoluojuhai/ai-canvas). 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 →