ping_group · Homelab MCP: Risk & Policy

WHAT IT DOES

What ping_group does on Homelab

AI agents invoke ping_group to trigger actions in Homelab. 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 ping_group needs a policy

Pinging all hosts in an Ansible group executes an external operation against potentially many remote systems. While a ping is typically read-only in nature, it triggers active network/Ansible module execution across infrastructure, making it Execute. Misuse could flood network segments or reveal topology; blast radius is medium given it targets a group of hosts.

From the tool's definition 'Ping all hosts in an Ansible group' — triggers active network operations (ICMP/Ansible ping) against multiple remote hosts

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ping_group Rate-limited

ping_group 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": {
    "ping_group": {
      "limits": [
        {
          "counter": "ping_group_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 Homelab, so you can run agents against it safely.

FAQ

Questions about ping_group

What does the ping_group tool do? +

Ping all hosts in an Ansible group. It is categorised as a Execute tool in the Homelab MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ping_group? +

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

What risk level is ping_group? +

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

Can I rate-limit ping_group? +

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

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

ping_group is provided by the Homelab MCP server (myraffy/homelab-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.