Discard an entire experiment — no changes are kept.
AI agents call discard_experiment to permanently remove resources in Livepilot — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
An AI agent that decides to call discard_experiment doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Livepilot is gone — there is no undo for destructive operations.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Discard an entire experiment — no changes are kept. It is categorised as a Destructive tool in the Livepilot MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Livepilot MCP server in PolicyLayer and add a rule for discard_experiment: 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 Livepilot. Nothing to install.
discard_experiment 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 discard_experiment 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 discard_experiment. 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.
discard_experiment is provided by the Livepilot MCP server (livepilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.