Get random books for discovery.
AI agents call get_random_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 retrieves data (random book selections) from a local Calibre library without side effects. It fits the Read category: retrieves or queries data with no side effects. The read-only nature of the server and the passive discovery function indicate minimal risk even if misused.
From the tool's definition Tool name 'get_random_books' and server description emphasizing 'read-only access' and 'searching metadata'. No modification, deletion, or execution capabilities described.
Attacks that exploit this kind of access
Get random books for discovery. 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 get_random_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.
get_random_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 get_random_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 get_random_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.
get_random_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 →