Fetch all currently firing alerts from Prometheus Alertmanager.
AI agents call prometheus_get_active_alerts to retrieve information from PilotOps MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries alert state from Prometheus without modifying, deleting, or executing any operations. It has no capability to change system state, trigger actions, or affect data. The blast radius of misuse is minimal—an attacker would only gain visibility into current alert status, which is already expected to be human-readable monitoring data.
From the tool's definition Tool name 'prometheus_get_active_alerts' and description 'Fetch all currently firing alerts from Prometheus Alertmanager' indicate a retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access prometheus_get_active_alerts gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and PilotOps MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for prometheus_get_active_alerts:
{
"version": "1",
"default": "deny",
"tools": {
"prometheus_get_active_alerts": {}
}
}prometheus_get_active_alerts is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Fetch all currently firing alerts from Prometheus Alertmanager. It is categorised as a Read tool in the PilotOps MCP MCP Server, which means it retrieves data without modifying state.
Register the PilotOps MCP server in PolicyLayer and add a rule for prometheus_get_active_alerts: 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 PilotOps MCP. Nothing to install.
prometheus_get_active_alerts 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 prometheus_get_active_alerts 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 prometheus_get_active_alerts. 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.
prometheus_get_active_alerts is provided by the PilotOps MCP server (muhammedehab35/pilot_ops-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from PilotOps MCP, 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.
12 PilotOps MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.