List favorite roles
AI agents call favorites_list to retrieve information from Claude Role Library without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays favorite roles, which is a read-only operation with no side effects. Users can safely invoke it to view their role selections without risk of data loss, code execution, or unintended modifications. The local-first YAML-based architecture means it reads from user-controlled storage.
From the tool's definition 'List favorite roles' is a query operation that retrieves stored preferences without modifying data or triggering external actions.
Attacks that exploit this kind of access
List favorite roles. It is categorised as a Read tool in the Claude Role Library MCP Server, which means it retrieves data without modifying state.
Register the Claude Role Library MCP server in PolicyLayer and add a rule for favorites_list: 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_list is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the favorites_list 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_list. 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_list 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 →