AI agents call prowlarr.health 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.
Health check operations are diagnostic reads that return system status without modifying state or executing arbitrary operations. The empty description reduces confidence slightly, but the tool name strongly indicates a read-only health status retrieval. No side effects expected from querying system health. Assigned low severity as health information is non-sensitive in this media server context.
From the tool's definition Tool name 'prowlarr.health' suggests a health check query operation. The pattern matches other sibling tools like 'jellyfin.system_info' which are read-only status queries.
Attacks that exploit this kind of access
prowlarr.health. 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 prowlarr.health: 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.
prowlarr.health 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 prowlarr.health 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 prowlarr.health. 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.
prowlarr.health 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 →