Remove a role
AI agents call roles_remove to permanently remove resources in Claude Role Library — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs an irreversible deletion operation on stored role data. Once removed, the role cannot be recovered without external backups. Although the blast radius is constrained to role metadata rather than critical production data, the destructive nature and lack of undo capability place it in the Destructive category rather than Write.
From the tool's definition Tool name 'roles_remove' with description 'Remove a role' indicates deletion of stored role data. The sibling tools confirm a YAML-based role storage system where roles are persisted locally. Removing a role irreversibly deletes that configuration.
Attacks that exploit this kind of access
Remove a role. It is categorised as a Destructive tool in the Claude Role Library MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude Role Library MCP server in PolicyLayer and add a rule for roles_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 Claude Role Library. Nothing to install.
roles_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 roles_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 roles_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.
roles_remove is provided by the Claude Role Library MCP server (tony427/claude-role-library). 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 →