AI agents call radarr_get_movie 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 and retrieves existing movie information from Radarr by ID. It performs no mutations, deletions, or external actions. The operation is safe and read-only, with minimal blast radius if misused by an AI agent—it would only expose existing movie metadata already stored in the media server.
From the tool's definition Tool name 'radarr_get_movie' and description 'Récupère les détails complets d'un film par son ID Radarr' (Retrieves complete details of a film by its Radarr ID) indicate a read-only query operation that retrieves movie metadata without modification or side…
Attacks that exploit this kind of access
Récupère les détails complets d'un film par son ID Radarr. 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_movie: 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_movie 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_movie 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_movie. 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_movie 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 →