AI agents call plex_search 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.
The tool appears to search/query content from a Plex media server without modifying data. Despite the empty description, the naming pattern ('search') combined with context of sibling tools that are all retrieval operations (get_*, search_*) indicates this is a Read operation.
From the tool's definition Tool name 'plex_search' indicates a search operation on Plex media server. Sibling tools in the server include multiple 'get' operations (bazarr_get_episodes_history, bazarr_get_movies, etc.) which are consistently Read category tools that retrieve data…
Attacks that exploit this kind of access
plex_search. 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_search: 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_search 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_search 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_search. 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_search 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 →