AI agents call radarr_search_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 performs a search operation against TMDB (The Movie Database) and returns results. It retrieves information (search results and metadata like TMDB IDs) without creating, modifying, deleting, or executing any actions on the user's media server. The word 'search' combined with 'returns results' confirms this is a read-only retrieval operation. The French description 'Recherche un film à ajouter via TMDB.
From the tool's definition Tool name 'radarr_search_movie' and description 'Searches for a movie to add via TMDB. Returns search results with TMDB ID' indicate a query/search operation that retrieves and returns data without modifying anything.
Attacks that exploit this kind of access
Recherche un film à ajouter via TMDB. Retourne les résultats de recherche avec TMDB ID. 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_search_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_search_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_search_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_search_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_search_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 →