run_check · MCP Prometheus MCP: Risk & Policy

WHAT IT DOES

What run_check does on MCP Prometheus

AI agents invoke run_check to trigger actions in MCP 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 run_check needs a policy

The tool runs diagnostic checks against Prometheus metrics and potentially custom PromQL queries, which constitutes code/query execution. While the blast radius is constrained to read-only monitoring data retrieval in typical usage, PromQL execution can be complex and the actual effects depend on query arguments.

From the tool's definition Tool name 'run_check' combined with server context indicating 'diagnostic checks' and 'custom PromQL execution' suggests execution of monitoring queries. Sibling tool 'run_all_checks' corroborates this pattern. Empty description limits certainty slightly.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_check Rate-limited

run_check 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": {
    "run_check": {
      "limits": [
        {
          "counter": "run_check_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 MCP Prometheus, so you can run agents against it safely.

FAQ

Questions about run_check

What does the run_check tool do? +

run_check. It is categorised as a Execute tool in the MCP 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 run_check? +

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

What risk level is run_check? +

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

Can I rate-limit run_check? +

Yes. Add a rate_limit block to the run_check 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 run_check completely? +

Set action: deny in the PolicyLayer policy for run_check. 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 run_check? +

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