media_restart · Homelab MCP: Risk & Policy

WHAT IT DOES

What media_restart does on Homelab

AI agents invoke media_restart 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 media_restart needs a policy

This tool executes a restart command on a running container, which is an external operation that triggers a state change in the homelab infrastructure. While not destructive (the container is not deleted), it causes service downtime and depends on runtime arguments to determine which container is affected.

From the tool's definition Tool name 'media_restart' and description 'Restart a media service container on the devbox' indicate execution of a container restart operation, which is an external action with side effects that depend on which service is targeted.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

media_restart Rate-limited

media_restart 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": {
    "media_restart": {
      "limits": [
        {
          "counter": "media_restart_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 media_restart

What does the media_restart tool do? +

Restart a media service container on the devbox. 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 media_restart? +

Register the Homelab MCP server in PolicyLayer and add a rule for media_restart: 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 media_restart? +

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

Can I rate-limit media_restart? +

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

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

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