discard_experiment
Discard an entire experiment — no changes are kept.
This record as markdown: /tools/io-github-dreamrec-livepilot/discard-experiment.md
What discard_experiment does on Livepilot
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.
Why discard_experiment is rated Critical
This tool irreversibly deletes or discards an entire experiment without recovery. While the blast radius is limited to a single experiment rather than a full project, the action cannot be undone and represents permanent data loss. This meets the definition of Destructive category.
From the tool's definition Tool name is 'discard_experiment' with description 'Discard an entire experiment — no changes are kept.' The phrase 'no changes are kept' explicitly indicates irreversible deletion of data.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs discard_experiment safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Livepilot, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For discard_experiment, this is the rule to start with:
discard_experiment 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 Livepilot, apply this rule, and every discard_experiment call is checked against it from then on.
Questions about discard_experiment
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.
More on Livepilot, and thousands of servers like it.
Across the catalogue