AI agents call readarr_list_books 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 and lists data from a media library without side effects or state changes. It is categorized as Read. Severity is medium rather than low because the homelab server grants 'full control' over infrastructure, and leaking media library contents could expose user media consumption patterns, metadata, or reveal information about media collections.
From the tool's definition Tool name 'readarr_list_books' and description 'List all books in the Readarr library with download status and file size' indicate a read-only retrieval operation that queries and returns book inventory data without modification.
Attacks that exploit this kind of access
List all books in the Readarr library with download status and file size. 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_list_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 Homelab. Nothing to install.
readarr_list_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 readarr_list_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 readarr_list_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.
readarr_list_books 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 →