cleanup_expired_sandboxes
Destroy expired sandboxes.
This record as markdown: /tools/agent-jail-mcp/cleanup-expired-sandboxes.md
What cleanup_expired_sandboxes does on Agent Jail
AI agents call cleanup_expired_sandboxes to permanently remove resources in Agent Jail, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why cleanup_expired_sandboxes is rated Critical
An AI agent that decides to call cleanup_expired_sandboxes doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Agent Jail is gone. There is no undo for destructive operations.
Attacks that exploit this kind of access
The rule that runs cleanup_expired_sandboxes safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Agent Jail, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For cleanup_expired_sandboxes, this is the rule to start with:
cleanup_expired_sandboxes is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Agent Jail, apply this rule, and every cleanup_expired_sandboxes call is checked against it from then on.
Questions about cleanup_expired_sandboxes
Destroy expired sandboxes. It is categorised as a Destructive tool in the Agent Jail MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Agent Jail MCP server in PolicyLayer and add a rule for cleanup_expired_sandboxes: 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 Agent Jail. Nothing to install.
cleanup_expired_sandboxes 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_expired_sandboxes 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_expired_sandboxes. 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_expired_sandboxes is provided by the Agent Jail MCP server (idiscoord13-sketch/agent-jail-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Agent Jail, and thousands of servers like it.
Across the catalogue