AI agents call cleanup to permanently remove resources in Undo — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool destroys data that cannot be recovered—the entire undo checkpoint stack. Once cleared, users cannot restore previous file states via the undo system. While not modifying actual file content directly, it irreversibly removes the mechanism for undoing modifications, making it Destructive rather than Write.
From the tool's definition Tool name 'cleanup' with description 'Clear all undo checkpoints from the stack' irreversibly deletes all stored checkpoint data. The verb 'clear' combined with 'all' indicates complete, unrecoverable removal of the undo history.
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access cleanup gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Undo, and nothing reaches the server without passing your rules. This is the rule we recommend for cleanup:
{
"version": "1",
"default": "deny",
"hide": [
"cleanup"
]
}cleanup disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Clear all undo checkpoints from the stack. It is categorised as a Destructive tool in the Undo MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Undo MCP server in PolicyLayer and add a rule for cleanup: 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 Undo. Nothing to install.
cleanup is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the cleanup 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 cleanup. 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.
cleanup is provided by the Undo MCP server (khalilbalaree/rewind-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Undo, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 Undo tools catalogued and risk-classified — across an index of 43,000+ MCP servers.