Remove one or more file formats from a book (e.g. remove the MOBI copy but keep EPUB).
AI agents call remove_format 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.
Removing a file format from a book is an irreversible deletion of that format's data. Once removed, the MOBI (or other format) file is gone from the library and cannot be recovered without re-uploading or re-converting. This constitutes a destructive operation with potentially high blast radius if misused on multiple books or critical formats.
From the tool's definition 'Remove one or more file formats from a book' — permanently deletes specific file format copies from a book entry in the Calibre library
Attacks that exploit this kind of access
Remove one or more file formats from a book (e.g. remove the MOBI copy but keep EPUB). 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_format: 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_format 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_format 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_format. 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_format 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 →