AI agents invoke sonarr_grab_release to trigger actions in Homelab. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool initiates a download by sending a release to an external download client. It triggers an external operation with real-world side effects (network traffic, disk usage, potential copyright/legal implications). It is not merely writing data to a database but executing an action on an external system, making Execute the appropriate category.
From the tool's definition 'Grab a specific release by its GUID... and send it to the download client' — triggers an external download operation
Attacks that exploit this kind of access
Grab a specific release by its GUID (from sonarr_interactive_search) and send it to the download client. It is categorised as a Execute tool in the Homelab MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Homelab MCP server in PolicyLayer and add a rule for sonarr_grab_release: 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.
sonarr_grab_release is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the sonarr_grab_release 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 sonarr_grab_release. 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.
sonarr_grab_release 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 →