sonarr.series_delete
AI agents call sonarr.series_delete to permanently remove resources in Arr Stack — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Delete operations are by definition irreversible and destructive. Deletion of a TV series entry in Sonarr would remove associated metadata and potentially linked media. This is categorized as Destructive (not merely Write) because deletions cannot be undone through normal operations. Severity is high because an LLM agent could inadvertently delete entire media collections.
From the tool's definition Tool named 'sonarr.series_delete' — the verb 'delete' in the name indicates irreversible removal of data. The description is empty, but the naming pattern is unambiguous.
Attacks that exploit this kind of access
sonarr.series_delete. It is categorised as a Destructive tool in the Arr Stack MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Arr Stack MCP server in PolicyLayer and add a rule for sonarr.series_delete: 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.
sonarr.series_delete is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the sonarr.series_delete 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 sonarr.series_delete. 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.
sonarr.series_delete 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 →