List available metrics. Use to discover what
AI agents call prometheus_metrics to retrieve information from Overwatch MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about available metrics from Prometheus without querying data, modifying state, or executing operations. It is a read-only discovery operation with minimal blast radius if misused—an agent can only enumerate metrics, not access sensitive data values or trigger actions. Classified as Read with low severity.
From the tool's definition Tool name is 'prometheus_metrics' and description indicates it 'List available metrics' for discovery purposes, with no modification or execution capability.
Attacks that exploit this kind of access
List available metrics. Use to discover what. It is categorised as a Read tool in the Overwatch MCP MCP Server, which means it retrieves data without modifying state.
Register the Overwatch MCP server in PolicyLayer and add a rule for prometheus_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 Overwatch MCP. Nothing to install.
prometheus_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 prometheus_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 prometheus_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.
prometheus_metrics is provided by the Overwatch MCP server (malindarathnayake/overwatch-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 →