Delete an alert rule by UID
AI agents call delete_alert_rule to permanently remove resources in Grafana MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes alert rule configurations from Grafana. Deletion of alert rules cannot be undone and results in loss of monitoring/alerting infrastructure. This is destructive (irreversible data loss) rather than merely Execute, as the action destroys existing configurations.
From the tool's definition Tool name: delete_alert_rule. Description: 'Delete an alert rule by UID'. The operation is irreversible deletion of alert configuration.
Attacks that exploit this kind of access
Delete an alert rule by UID. It is categorised as a Destructive tool in the Grafana MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Grafana MCP Server MCP server in PolicyLayer and add a rule for delete_alert_rule: 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 Grafana MCP Server. Nothing to install.
delete_alert_rule 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 delete_alert_rule 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 delete_alert_rule. 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.
delete_alert_rule is provided by the Grafana MCP Server MCP server (quanticsoul4772/grafana-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 →