Remove a page from the authenticated user\
AI agents use unfavorite_page to create or update resources in Collectives — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Collectives environment.
Unfavoriting a page removes a user preference/association but does not delete the page itself. This is a reversible modification to user data (favorites list), making it a Write operation. The blast radius is low since it only affects the current user's favorites and can be easily reversed by re-favoriting.
From the tool's definition 'unfavorite_page' and 'Remove a page from the authenticated user' — removes a favorite/bookmark association
Attacks that exploit this kind of access
Remove a page from the authenticated user\. It is categorised as a Write tool in the Collectives MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Collectives MCP server in PolicyLayer and add a rule for unfavorite_page: 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 Collectives. Nothing to install.
unfavorite_page 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 unfavorite_page 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 unfavorite_page. 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.
unfavorite_page is provided by the Collectives MCP server (megamaced/nc_collectives-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 →