Delete a role.
AI agents call delete_role to permanently remove resources in Defined — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a role is a destructive action that cannot be undone—it permanently removes role definitions from the Defined Networking infrastructure. This affects access control and permissions, which have cascading effects on network administration. While not directly damaging data like delete_host might be, role deletion is irreversible and impacts the security posture of the entire system.
From the tool's definition Tool name is 'delete_role' with description 'Delete a role.' The verb 'delete' combined with the context of managing network infrastructure roles indicates an irreversible removal of a role definition.
Attacks that exploit this kind of access
Delete a role. It is categorised as a Destructive tool in the Defined MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Defined MCP server in PolicyLayer and add a rule for delete_role: 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 Defined. Nothing to install.
delete_role 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 delete_role 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 delete_role. 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.
delete_role is provided by the Defined MCP server (quickvm/defined-mcp). 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 →