Run an instant PromQL query through Grafana's Prometheus datasource proxy.
AI agents call query_prometheus to retrieve information from Mcp Grafana without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metric data from Prometheus via a query interface. It has no side effects—it only reads and returns data. The server is explicitly positioned as read-only for diagnostics. While a PromQL query could theoretically be crafted to consume resources, the normal use case is data retrieval, placing it firmly in the Read category.
From the tool's definition Tool description states 'Run an instant PromQL query' which is a read-only diagnostic operation. Server description emphasizes 'read-only diagnostics' and the tool is explicitly a query operation with no modification, deletion, or execution of arbitrary code.
Attacks that exploit this kind of access
Run an instant PromQL query through Grafana's Prometheus datasource proxy. It is categorised as a Read tool in the Mcp Grafana MCP Server, which means it retrieves data without modifying state.
Register the Mcp Grafana MCP server in PolicyLayer and add a rule for query_prometheus: 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 Mcp Grafana. Nothing to install.
query_prometheus 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 query_prometheus 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 query_prometheus. 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.
query_prometheus is provided by the Mcp Grafana MCP server (romaine-life/mcp-grafana). 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 →