Remove a role from favorites
AI agents call favorites_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.
The tool removes a role from the favorites list, which is an irreversible deletion of that association (the item is removed from favorites without an undo mechanism). However, the blast radius is low since it only affects a user's favorites list within a local YAML-based storage system, and the underlying role itself is not deleted—only the favorites reference is removed.
From the tool's definition Remove a role from favorites
Attacks that exploit this kind of access
Remove a role from favorites. 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 favorites_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.
favorites_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 favorites_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 favorites_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.
favorites_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 →