Add a role to favorites
AI agents use favorites_add to create or update resources in Claude Role Library — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Role Library environment.
This tool creates or modifies data (favorites associations) in a reversible manner. Adding a role to favorites is a non-destructive write operation that changes the state of a user's preferences. It has no side effects beyond local data modification, no code execution, and can be easily undone via the sibling 'favorites_remove' tool.
From the tool's definition Tool named 'favorites_add' with description 'Add a role to favorites' - this creates/modifies a favorites list by adding entries.
Attacks that exploit this kind of access
Add a role to favorites. It is categorised as a Write tool in the Claude Role Library MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claude Role Library MCP server in PolicyLayer and add a rule for favorites_add: 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_add is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the favorites_add 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_add. 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_add 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 →