AI agents use overseerr_request_movie to create or update resources in Nas — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nas environment.
This tool creates a new media request in Overseerr and forwards it to Radarr for download. It creates new data/state (a request record) and triggers an external media acquisition workflow. It is reversible in principle (requests can be deleted), so Write is appropriate rather than Execute or Destructive. Misuse could result in unwanted media downloads consuming storage and bandwidth.
From the tool's definition Fait une demande pour ajouter un film à la bibliothèque (envoie à Radarr)
Attacks that exploit this kind of access
Fait une demande pour ajouter un film à la bibliothèque (envoie à Radarr). It is categorised as a Write tool in the Nas MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nas MCP server in PolicyLayer and add a rule for overseerr_request_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.
overseerr_request_movie 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 overseerr_request_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 overseerr_request_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.
overseerr_request_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 →