Remove a dependency from the project.
AI agents call foundry_remove 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.
Removing a project dependency is a destructive operation: it deletes the dependency entry and associated files from the project, which cannot be trivially undone without re-adding and reconfiguring it. This has a high blast radius as an AI agent misusing it could break the project's build or functionality by removing critical dependencies.
From the tool's definition 'Remove a dependency from the project' — removing a dependency is an irreversible modification that deletes a component from the project configuration, potentially breaking functionality.
Attacks that exploit this kind of access
Remove a dependency from the project. 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 foundry_remove: 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.
foundry_remove 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 foundry_remove 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 foundry_remove. 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.
foundry_remove 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 →