AI agents call monitoring_alerts to retrieve information from Infra Ops without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves alert data from Prometheus Alertmanager without modifying, deleting, or executing any operations. It has minimal blast radius—misuse would only expose monitoring information already available through the alerting system. Classified as Read with low severity.
From the tool's definition Tool name 'monitoring_alerts' and description 'Get active alerts from a Prometheus Alertmanager endpoint' indicate a retrieval operation. The verb 'Get' and the passive nature of querying alert status confirm this is a read-only operation with no side effects.
Attacks that exploit this kind of access
Get active alerts from a Prometheus Alertmanager endpoint. It is categorised as a Read tool in the Infra Ops MCP Server, which means it retrieves data without modifying state.
Register the Infra Ops MCP server in PolicyLayer and add a rule for monitoring_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 Infra Ops. Nothing to install.
monitoring_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 monitoring_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 monitoring_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.
monitoring_alerts is provided by the Infra Ops MCP server (skyvanguard/infra-ops-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 →