AI agents call readarr_search_book to retrieve information from Homelab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves book data (Goodreads IDs) based on search criteria (title/author) without creating, modifying, deleting, or executing any operations. It is informational and preparatory in nature, intended to gather data before a separate write operation (readarr_add_book). Pure search/query operations are classified as Read with low severity.
From the tool's definition Tool name indicates 'search' operation; description states it 'Search[es] for a book' and 'Returns Goodreads IDs', which are pure query operations with no side effects or data modification.
Attacks that exploit this kind of access
Search for a book by title or author. Returns Goodreads IDs. Use before readarr_add_book. It is categorised as a Read tool in the Homelab MCP Server, which means it retrieves data without modifying state.
Register the Homelab MCP server in PolicyLayer and add a rule for readarr_search_book: 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 Homelab. Nothing to install.
readarr_search_book 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 readarr_search_book 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 readarr_search_book. 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.
readarr_search_book is provided by the Homelab MCP server (nainounen/homelab-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 →