prometheus_query · Homelab MCP: Risk & Policy

WHAT IT DOES

What prometheus_query does on Homelab

AI agents invoke prometheus_query to trigger actions in Homelab. 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 prometheus_query needs a policy

Although PromQL is primarily a read-oriented query language, the tool explicitly allows 'arbitrary' queries against a production monitoring system. While Prometheus itself is read-only via PromQL, executing arbitrary queries can expose sensitive metrics data (CPU, RAM, disk, network trends across all homelab infrastructure), and the 'arbitrary' nature means the blast radius includes potential misuse for…

From the tool's definition "Run an arbitrary PromQL query against Prometheus" — executes arbitrary user-supplied PromQL expressions against a live Prometheus instance.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

prometheus_query Rate-limited

prometheus_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": {
    "prometheus_query": {
      "limits": [
        {
          "counter": "prometheus_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 Homelab, so you can run agents against it safely.

FAQ

Questions about prometheus_query

What does the prometheus_query tool do? +

Run an arbitrary PromQL query against Prometheus. Use for ad-hoc metrics: container CPU/RAM, disk trends, network IO, etc. It is categorised as a Execute tool in the Homelab MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on prometheus_query? +

Register the Homelab MCP server in PolicyLayer and add a rule for prometheus_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 Homelab. Nothing to install.

What risk level is prometheus_query? +

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

Can I rate-limit prometheus_query? +

Yes. Add a rate_limit block to the prometheus_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 prometheus_query completely? +

Set action: deny in the PolicyLayer policy for prometheus_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 prometheus_query? +

prometheus_query is provided by the Homelab MCP server (nainounen/homelab-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.