AI agents call monitoring_get_metrics 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.
This tool retrieves metrics and historical monitoring data without creating, modifying, or deleting any information. It is a read-only operation that queries existing data, fitting the Read category definition. The severity is low because metric retrieval poses minimal risk even if misused by an AI agent—it cannot modify system state, trigger external actions, or cause financial impact.
From the tool's definition Tool name 'monitoring_get_metrics' and description 'Get current metrics and historical data' indicate retrieval of monitoring data with no modification or side effects.
Attacks that exploit this kind of access
Get current metrics and historical data. 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_metrics: 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_metrics 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_metrics 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_metrics. 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_metrics 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 →