lg_probing_auto_select · Looking-Glass- MCP: Risk & Policy

WHAT IT DOES

What lg_probing_auto_select does on Looking-Glass-MCP

AI agents invoke lg_probing_auto_select to trigger actions in Looking-Glass-MCP. 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 lg_probing_auto_select needs a policy

The sibling tool 'lg_probing_user_defined' and the server description strongly indicate this tool performs network probing operations (ping, traceroute, BGP lookups) but with auto-selected vantage points rather than user-defined ones. These are active network operations that trigger external network traffic, classifying as Execute.

From the tool's definition Tool name 'lg_probing_auto_select' on a server described as providing 'network probing capabilities' including 'ping, BGP route lookups, and traceroute operations'. The description is empty, so classification is based on name and server context alone.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

lg_probing_auto_select Rate-limited

lg_probing_auto_select 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": {
    "lg_probing_auto_select": {
      "limits": [
        {
          "counter": "lg_probing_auto_select_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 Looking-Glass-MCP, so you can run agents against it safely.

FAQ

Questions about lg_probing_auto_select

What does the lg_probing_auto_select tool do? +

lg_probing_auto_select. It is categorised as a Execute tool in the Looking-Glass-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on lg_probing_auto_select? +

Register the Looking-Glass- MCP server in PolicyLayer and add a rule for lg_probing_auto_select: 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 Looking-Glass-MCP. Nothing to install.

What risk level is lg_probing_auto_select? +

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

Can I rate-limit lg_probing_auto_select? +

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

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

lg_probing_auto_select is provided by the Looking-Glass- MCP server (jackie-shi/looking-glass-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.