Clean cache and artifacts directories. Useful before fresh compilation.
AI agents call hardhat_clean to permanently remove resources in HashPilot — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cleaning cache and artifacts directories removes files irreversibly (or at least without a built-in undo mechanism). While these are generated/cached files that can typically be regenerated by recompilation, the action itself is a deletion of directory contents and cannot be undone directly. This falls under Destructive rather than Write since it deletes rather than modifies data.
From the tool's definition Clean cache and artifacts directories
Attacks that exploit this kind of access
Clean cache and artifacts directories. Useful before fresh compilation. It is categorised as a Destructive tool in the HashPilot MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the HashPilot MCP server in PolicyLayer and add a rule for hardhat_clean: 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 HashPilot. Nothing to install.
hardhat_clean 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 hardhat_clean 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 hardhat_clean. 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.
hardhat_clean is provided by the HashPilot MCP server (justmert/hashpilot). 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 →