AI agents use set_cover to create or update resources in Lyceum — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Lyceum environment.
Setting a cover image modifies book metadata in the Calibre library. This is categorized as Write rather than Read (it changes data) or Destructive (the change is reversible—a new cover can be set). Severity is medium because unintended metadata changes could degrade library usability, but they do not delete data or cause financial harm.
From the tool's definition The tool name 'set_cover' and description 'Set a book' (incomplete, likely 'Set a book cover') indicates modifying metadata of an existing book record in the Calibre library. This is a reversible write operation that updates book properties.
Attacks that exploit this kind of access
Set a book. It is categorised as a Write tool in the Lyceum MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Lyceum MCP server in PolicyLayer and add a rule for set_cover: 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.
set_cover 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 set_cover 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 set_cover. 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.
set_cover 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 →