Get metric metadata
AI agents call prom_metadata 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 metadata about Prometheus metrics, which is a non-destructive read operation with no side effects on the monitored system or data. It merely exposes information about available metrics and their properties. The blast radius of misuse is minimal—an agent could only discover what metrics exist, not modify or delete data.
From the tool's definition Tool name 'prom_metadata' and description 'Get metric metadata' indicate retrieval of metric information without modification. Prometheus metadata queries are read-only operations that return descriptive information about available metrics.
Attacks that exploit this kind of access
Get metric metadata. 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_metadata: 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_metadata 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_metadata 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_metadata. 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_metadata 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 →