AI agents call jellyfin.now_playing to retrieve information from Arr Stack without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite lacking a formal description, the tool name strongly suggests a read operation that queries playback status. The context of Jellyfin (a media server) and the pattern of sibling tools (library_search, recent_additions, system_info) which are all informational reads reinforces this classification.
From the tool's definition Tool name 'jellyfin.now_playing' indicates retrieval of current playback state. The 'now_playing' pattern in media server APIs is a standard query/read operation that returns the currently playing media item without modifying system state.
Attacks that exploit this kind of access
jellyfin.now_playing. It is categorised as a Read tool in the Arr Stack MCP Server, which means it retrieves data without modifying state.
Register the Arr Stack MCP server in PolicyLayer and add a rule for jellyfin.now_playing: 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 Arr Stack. Nothing to install.
jellyfin.now_playing 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 jellyfin.now_playing 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 jellyfin.now_playing. 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.
jellyfin.now_playing is provided by the Arr Stack MCP server (new-usemame/arr-stack-mcp). 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 →