query_prometheus

THE RISK

High Risk

Why query_prometheus needs a policy

The tool executes queries (PromQL) against an external datasource. While read-only in typical usage, 'execute' queries against external systems fall under Execute category. Misuse could expose sensitive metrics or overload the Prometheus instance with expensive queries, but it cannot modify data, making severity medium rather than high.

From the tool's definition "Execute PromQL queries against a Prometheus datasource"

Documented attack patterns abuse exactly the kind of access query_prometheus gives an agent:

POLICY

How to control query_prometheus

PolicyLayer is an MCP gateway — it sits between your AI agents and Grafana FastMCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for query_prometheus:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "query_prometheus": {
      "limits": [
        {
          "counter": "query_prometheus_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

query_prometheus stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Grafana FastMCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Grafana FastMCP Server tools

Execute find_error_pattern_logs Run the ErrorPatternLogs check via Sift and return the analysis result. Execute find_slow_requests Run the SlowRequests check via Sift and return the analysis result. Execute query_loki_logs Execute a LogQL query against a Loki datasource and return the matching log entries. Write add_activity_to_incident Add a user note to an incident Write create_incident Create a new Grafana incident with the provided details. Write update_dashboard update_dashboard Read fetch fetch Read fetch_pyroscope_profile Fetch a Pyroscope profile in DOT format for a given query.

All 45 Grafana FastMCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Grafana FastMCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about query_prometheus

What does the query_prometheus tool do? +

Execute PromQL queries against a Prometheus datasource. It is categorised as a Execute tool in the Grafana FastMCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on query_prometheus? +

Register the Grafana FastMCP Server 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 Grafana FastMCP Server. Nothing to install.

What risk level is query_prometheus? +

query_prometheus is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit query_prometheus? +

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.

How do I block query_prometheus completely? +

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.

What MCP server provides query_prometheus? +

query_prometheus is provided by the Grafana FastMCP Server MCP server (sandersouza/grafanafastmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Grafana FastMCP Server tool call.

Start from Grafana FastMCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →