delete_contact_point
AI agents call delete_contact_point to permanently remove resources in Mcp Read Only Grafana — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of contact points is irreversible—once removed, notification routing is lost and cannot be automatically restored without reconfiguration. This affects alerting infrastructure and could cause operational blindness if a critical notification endpoint is deleted. The tool description is empty but the name and server context provide sufficient evidence.
From the tool's definition Tool name 'delete_contact_point' indicates deletion of a contact point (notification endpoint). The server description emphasizes it is 'read-only by default' with 'write-capable commands for mutations', positioning this tool as a mutation operation.
Attacks that exploit this kind of access
delete_contact_point. It is categorised as a Destructive tool in the Mcp Read Only Grafana MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Read Only Grafana MCP server in PolicyLayer and add a rule for delete_contact_point: 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 Mcp Read Only Grafana. Nothing to install.
delete_contact_point 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_contact_point 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_contact_point. 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_contact_point is provided by the Mcp Read Only Grafana MCP server (lukleh/mcp-read-only-grafana). 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 →