AI agents call delete-silence to permanently remove resources in Alertmanager — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool removes silence configurations from Alertmanager, which are irreversible actions that cannot be recovered once executed. While the description is empty (lowering confidence slightly), the clear deletion semantics in the name combined with the context of managing alert silences—where deletion permanently removes alert suppression rules—justifies the Destructive category.
From the tool's definition Tool name is 'delete-silence' which performs irreversible deletion of silence rules in Alertmanager. The verb 'delete' indicates removal that cannot be undone.
Documented attack patterns abuse exactly the kind of access delete-silence gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Alertmanager, and nothing reaches the server without passing your rules. This is the rule we recommend for delete-silence:
{
"version": "1",
"default": "deny",
"hide": [
"delete-silence"
]
}delete-silence disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
delete-silence. It is categorised as a Destructive tool in the Alertmanager MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Alertmanager MCP server in PolicyLayer and add a rule for delete-silence: 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 Alertmanager. Nothing to install.
delete-silence 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-silence 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-silence. 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-silence is provided by the Alertmanager MCP server (kaznak/alertmanager-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Alertmanager, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 Alertmanager tools catalogued and risk-classified — across an index of 43,000+ MCP servers.