login_probe · Firegex MCP: Risk & Policy

WHAT IT DOES

What login_probe does on Firegex

AI agents invoke login_probe to trigger actions in Firegex. 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 login_probe needs a policy

The tool actively executes an authentication lifecycle rather than passively reading data. It performs an operation (forcing auth) and returns a side-effecting result (an authenticated session/status). This is an Execute-level action since it triggers an external operation (authentication) whose effects depend on credentials/context.

From the tool's definition "Force the auth lifecycle" — actively triggers an authentication process, not merely reading status

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

login_probe Rate-limited

login_probe 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": {
    "login_probe": {
      "limits": [
        {
          "counter": "login_probe_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 Firegex, so you can run agents against it safely.

FAQ

Questions about login_probe

What does the login_probe tool do? +

Force the auth lifecycle and return the (now-authenticated) status. It is categorised as a Execute tool in the Firegex MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on login_probe? +

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

What risk level is login_probe? +

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

Can I rate-limit login_probe? +

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

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

login_probe is provided by the Firegex MCP server (umbra2728/firegex-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.