Flags · P MCP: Risk & Policy

WHAT IT DOES

What Flags does on Pmcp

AI agents invoke Flags to trigger actions in Pmcp. 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 Flags needs a policy

Flags triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

Flags Rate-limited

Flags 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": {
    "Flags": {
      "limits": [
        {
          "counter": "flags_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 Pmcp, so you can run agents against it safely.

FAQ

Questions about Flags

What does the Flags tool do? +

Return flag values that Prometheus was configured with. It is categorised as a Execute tool in the Pmcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on Flags? +

Register the P MCP server in PolicyLayer and add a rule for Flags: 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 Pmcp. Nothing to install.

What risk level is Flags? +

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

Can I rate-limit Flags? +

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

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

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