Search for text within multiple books' content.
AI agents call search_multiple_books to retrieve information from Neolibrarian MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs text search across multiple books in a local Calibre library, which is a pure read operation with no side effects. The server explicitly provides read-only access, and the tool name and description indicate passive information retrieval only. Confidence is high because the intent is unambiguous and corroborated by the server's read-only design.
From the tool's definition Tool description states 'Search for text within multiple books' content' and server is described as 'read-only access' with 'searching metadata' and 'full-text search' capabilities. The sibling tools all follow read patterns (get_*, search_*, analyze_*).
Attacks that exploit this kind of access
Search for text within multiple books' content. It is categorised as a Read tool in the Neolibrarian MCP MCP Server, which means it retrieves data without modifying state.
Register the Neolibrarian MCP server in PolicyLayer and add a rule for search_multiple_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 Neolibrarian MCP. Nothing to install.
search_multiple_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_multiple_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_multiple_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_multiple_books is provided by the Neolibrarian MCP server (pshap/mcp-neolibrarian). 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 →