AI agents use readarr_add_book to create or update resources in Homelab — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Homelab environment.
This tool creates a new record (book entry) in Readarr and triggers a search/download action. While it modifies state (adds data), it is reversible—the added book can be removed. It does not permanently delete data, execute arbitrary code, or involve financial transactions. The 'trigger download' aspect represents an initiated operation but not direct code execution.
From the tool's definition Tool name 'readarr_add_book' and description 'Add a book to Readarr and trigger an automatic download search' indicate creation of a new media entry and initiation of a download process.
Attacks that exploit this kind of access
Add a book to Readarr and trigger an automatic download search. It is categorised as a Write tool in the Homelab MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Homelab MCP server in PolicyLayer and add a rule for readarr_add_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_add_book is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the readarr_add_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_add_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_add_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 →