Discover all available metrics
AI agents call prom_discover to retrieve information from Prometheus MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and enumerates available metrics from a Prometheus instance. It is a pure read operation that discovers data without modifying, executing code, deleting, or creating resources. The blast radius of misuse is minimal—an agent could at most learn what metrics are monitored, which is informational only. No destructive, financial, or code execution capability is present.
From the tool's definition Tool name 'prom_discover' and description 'Discover all available metrics' indicate a query/discovery operation with no side effects. Returns metadata about what metrics exist in Prometheus.
Attacks that exploit this kind of access
Discover all available metrics. It is categorised as a Read tool in the Prometheus MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Prometheus MCP Server MCP server in PolicyLayer and add a rule for prom_discover: 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 Prometheus MCP Server. Nothing to install.
prom_discover 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 prom_discover 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 prom_discover. 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.
prom_discover is provided by the Prometheus MCP Server MCP server (yanmxa/prometheus-mcp-server). 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 →