Get metadata for a specific metric
AI agents call get_metric_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 metrics without executing queries, modifying data, or triggering external operations. It is a read-only operation that queries Prometheus for descriptive information about a metric (such as type, help text, etc.). The low severity reflects minimal blast radius — metadata retrieval cannot directly compromise systems or data integrity.
From the tool's definition Tool name is 'get_metric_metadata' and description states 'Get metadata for a specific metric' — a pure retrieval operation with no modification or execution of queries.
Attacks that exploit this kind of access
Get metadata for a specific metric. 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 get_metric_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.
get_metric_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 get_metric_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 get_metric_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.
get_metric_metadata is provided by the Prometheus MCP Server MCP server (raihan0824/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 →