range-query · Prometheus MCP: Risk & Policy

WHAT IT DOES

What range-query does on Prometheus

AI agents invoke range-query to trigger actions in Prometheus. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why range-query needs a policy

This tool runs a PromQL range query against a live Prometheus instance. While it is read-only in nature (retrieving time-series data), it actively executes a query expression whose behavior and resource consumption depend on the arguments provided. A poorly crafted or malicious PromQL query could cause high load on the Prometheus server.

From the tool's definition "Execute a range Prometheus query" — the word 'Execute' explicitly describes running a PromQL query against a Prometheus instance over a time range.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

range-query Rate-limited

range-query 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "range-query": {
      "limits": [
        {
          "counter": "range-query_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Prometheus, so you can run agents against it safely.

FAQ

Questions about range-query

What does the range-query tool do? +

Execute a range Prometheus query. It is categorised as a Execute tool in the Prometheus MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on range-query? +

Register the Prometheus MCP server in PolicyLayer and add a rule for range-query: 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. Nothing to install.

What risk level is range-query? +

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

Can I rate-limit range-query? +

Yes. Add a rate_limit block to the range-query 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 range-query completely? +

Set action: deny in the PolicyLayer policy for range-query. 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 range-query? +

range-query is provided by the Prometheus MCP server (mateusdata/prometheus-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.