AI agents call plex_get_recommendations 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 only fetches recommendations—a read-only operation with no side effects. It queries existing data from Plex without creating, modifying, deleting, or executing any operations. The blast radius of misuse is minimal, as recommendations are non-actionable suggestions.
From the tool's definition Tool name 'plex_get_recommendations' and description 'Récupère des recommandations basées sur un film ou une série' (Retrieves recommendations based on a movie or series) indicate a query operation that retrieves suggestion data without modifying any state.
Attacks that exploit this kind of access
Récupère des recommandations basées sur un film ou une série. 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 plex_get_recommendations: 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.
plex_get_recommendations 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 plex_get_recommendations 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 plex_get_recommendations. 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.
plex_get_recommendations 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 →