port_scan · Keel MCP: Risk & Policy

WHAT IT DOES

What port_scan does on Keel

AI agents invoke port_scan to trigger actions in Keel. 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 port_scan needs a policy

Port scanning involves actively sending network probes to external hosts, which is an external operation with potential legal and security implications. It goes beyond passive data retrieval; it executes network reconnaissance activity against a target host. Misuse could involve scanning unauthorized systems, triggering security alerts, or being used as part of an attack chain.

From the tool's definition 'Scan common TCP ports on a host' — actively probes network ports on remote systems

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

port_scan Rate-limited

port_scan 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": {
    "port_scan": {
      "limits": [
        {
          "counter": "port_scan_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 Keel, so you can run agents against it safely.

FAQ

Questions about port_scan

What does the port_scan tool do? +

Scan common TCP ports on a host. It is categorised as a Execute tool in the Keel MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on port_scan? +

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

What risk level is port_scan? +

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

Can I rate-limit port_scan? +

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

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

port_scan is provided by the Keel MCP server (seayniclabs/keel). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.