AI agents call radarr_get_queue to retrieve information from Nas without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the current state of a download queue in Radarr (a media server component). It performs a read-only operation that retrieves information about pending downloads without modifying, executing, or deleting anything. The French description confirms it is a GET/retrieval operation. No blast radius from misuse—worst case is viewing data already visible to the user.
From the tool's definition Tool name 'radarr_get_queue' and description 'Récupère la queue de téléchargement en cours' (Retrieves the current download queue) indicates a retrieval operation with no side effects.
Attacks that exploit this kind of access
Récupère la queue de téléchargement en cours. It is categorised as a Read tool in the Nas MCP Server, which means it retrieves data without modifying state.
Register the Nas MCP server in PolicyLayer and add a rule for radarr_get_queue: 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 Nas. Nothing to install.
radarr_get_queue 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 radarr_get_queue 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 radarr_get_queue. 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.
radarr_get_queue is provided by the Nas MCP server (matthieurosset/nas-mcp-server). 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 →