Permanently remove one or more books from the library. This cannot be undone.
AI agents call remove_book to permanently remove resources in Lyceum — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently deletes books from a library with no undo capability. This meets the Destructive category definition: 'irreversibly deletes or overwrites data, or actions that cannot be undone.' Severity is high because bulk removal of library data could cause significant loss, though the blast radius is limited to a single library rather than system-wide financial or infrastructure impacts.
From the tool's definition 'Permanently remove one or more books from the library. This cannot be undone.' — explicitly indicates irreversible deletion of data.
Attacks that exploit this kind of access
Permanently remove one or more books from the library. This cannot be undone. It is categorised as a Destructive tool in the Lyceum MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Lyceum MCP server in PolicyLayer and add a rule for remove_book: 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 Lyceum. Nothing to install.
remove_book 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 remove_book 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 remove_book. 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.
remove_book is provided by the Lyceum MCP server (matthewp/lyceum). 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 →