lg_probing_user_defined · Looking-Glass- MCP: Risk & Policy

WHAT IT DOES

What lg_probing_user_defined does on Looking-Glass-MCP

AI agents invoke lg_probing_user_defined 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_user_defined needs a policy

This tool triggers active network operations (probing commands) from multiple Looking Glass vantage points toward a user-specified target. It is an Execute category because it runs external network commands whose effects depend on the arguments (cmd and target_ip). Misuse could involve probing arbitrary IPs (reconnaissance, DDoS amplification vector), giving it medium severity.

From the tool's definition 'Send cmd probing to target_ip using a list of LG VPs' — executes network probing commands (ping, traceroute, BGP lookups) from external vantage points against a specified target IP

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

lg_probing_user_defined Rate-limited

lg_probing_user_defined 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_user_defined": {
      "limits": [
        {
          "counter": "lg_probing_user_defined_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_user_defined

What does the lg_probing_user_defined tool do? +

Send 'cmd' probing to target_ip using a list of LG VPs. 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_user_defined? +

Register the Looking-Glass- MCP server in PolicyLayer and add a rule for lg_probing_user_defined: 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_user_defined? +

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

Can I rate-limit lg_probing_user_defined? +

Yes. Add a rate_limit block to the lg_probing_user_defined 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_user_defined completely? +

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

lg_probing_user_defined 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.