AI agents call search_books to retrieve information from Calibre without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves or queries book data from a local Calibre library without modifying, deleting, or executing external operations. Despite the empty description, the name and context strongly indicate this is a search/retrieval operation. Low blast radius since searches over a local library cannot cause destructive side effects.
From the tool's definition Tool name 'search_books' combined with server's stated purpose 'search books' and sibling tools like 'get_book_info', 'get_epub_path', and 'list_series' which are clearly Read operations.
Attacks that exploit this kind of access
search_books. It is categorised as a Read tool in the Calibre MCP Server, which means it retrieves data without modifying state.
Register the Calibre 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 Calibre. 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 Calibre MCP server (xmkevinchen/calibre-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 →