run_all_checks · MCP Prometheus MCP: Risk & Policy

WHAT IT DOES

What run_all_checks does on MCP Prometheus

AI agents invoke run_all_checks 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_all_checks needs a policy

This tool executes all predefined diagnostic checks across the monitoring system. While read-only in outcome (returns diagnostic data), the act of 'running' checks constitutes triggering external monitoring operations whose effects depend on system state and check implementation. Misuse could cause resource exhaustion, trigger false alarms, or impact monitoring infrastructure.

From the tool's definition Tool name 'run_all_checks' combined with sibling tool 'run_check' indicates execution of diagnostic operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_all_checks Rate-limited

run_all_checks 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_all_checks": {
      "limits": [
        {
          "counter": "run_all_checks_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_all_checks

What does the run_all_checks tool do? +

run_all_checks. 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_all_checks? +

Register the MCP Prometheus MCP server in PolicyLayer and add a rule for run_all_checks: 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_all_checks? +

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

Can I rate-limit run_all_checks? +

Yes. Add a rate_limit block to the run_all_checks 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_all_checks completely? +

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

run_all_checks 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.