AI agents call search_books to retrieve information from Lyceum without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data from the Calibre library without creating, modifying, or deleting any content. It is a straightforward search function that returns matching books. The blast radius of misuse is minimal—an AI could only waste resources on excessive queries or retrieve unwanted information, neither of which causes material harm.
From the tool's definition Tool is described as 'Search books' with no side effects mentioned. It only queries data by title, author, tag, or series name using search syntax.
Attacks that exploit this kind of access
Search books by title, author, tag, or series name. Supports search syntax (e.g. author:Asimov, tag:sci-fi). It is categorised as a Read tool in the Lyceum MCP Server, which means it retrieves data without modifying state.
Register the Lyceum MCP server in PolicyLayer and add a rule for search_books: 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.
search_books is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_books 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 search_books. 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.
search_books 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 →