AI agents call monitoring_get_alerts to retrieve information from AgentOS without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The primary function is retrieving alert information, which is a read-only query operation with no side effects. While alert management could theoretically include status changes, the description emphasizes 'get' (retrieve) as the core action. Even if status updates were possible, this would be Write-level risk at most. No data deletion, code execution, or financial impact is indicated.
From the tool's definition Tool name 'monitoring_get_alerts' and description 'Get active alerts' indicate retrieval of alert data without modification.
Attacks that exploit this kind of access
Get active alerts and manage alert status. It is categorised as a Read tool in the AgentOS MCP Server, which means it retrieves data without modifying state.
Register the AgentOS MCP server in PolicyLayer and add a rule for monitoring_get_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 AgentOS. Nothing to install.
monitoring_get_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_get_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_get_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_get_alerts is provided by the AgentOS MCP server (netflypsb/agentos). 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 →