list_prometheus_metric_names
List metric names in a Prometheus datasource. Retrieves all metric names and filters them using regex.
This record as markdown: /tools/0xteamhq-mcp-grafana/list-prometheus-metric-names.md
What list_prometheus_metric_names does on Grafana MCP Server
AI agents call list_prometheus_metric_names to retrieve information from Grafana MCP Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why list_prometheus_metric_names is rated Low
This tool only queries and lists metric metadata from Prometheus without executing arbitrary queries, modifying data, or triggering external operations. It is a straightforward data retrieval operation with minimal blast radius if misused—an attacker could learn what metrics exist in the system but cannot access actual metric values, modify infrastructure, or execute code.
From the tool's definition Tool description states it 'Retrieves all metric names' and 'filters them using regex'. The verb 'Retrieves' and the read-only nature of listing metric names (no datasource modification or query execution) clearly indicate a retrieval operation.
Attacks that exploit this kind of access
The rule that runs list_prometheus_metric_names safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Grafana MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For list_prometheus_metric_names, this is the rule to start with:
list_prometheus_metric_names is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Grafana MCP Server, apply this rule, and every list_prometheus_metric_names call is checked against it from then on.
Questions about list_prometheus_metric_names
List metric names in a Prometheus datasource. Retrieves all metric names and filters them using regex. It is categorised as a Read tool in the Grafana MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Grafana MCP Server MCP server in PolicyLayer and add a rule for list_prometheus_metric_names: 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 Grafana MCP Server. Nothing to install.
list_prometheus_metric_names 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 list_prometheus_metric_names 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 list_prometheus_metric_names. 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.
list_prometheus_metric_names is provided by the Grafana MCP Server MCP server (0xteamhq/mcp-grafana). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Grafana MCP Server, and thousands of servers like it.
This server
Across the catalogue