devbox_docker_compose · Homelab MCP: Risk & Policy

WHAT IT DOES

What devbox_docker_compose does on Homelab

AI agents invoke devbox_docker_compose 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 devbox_docker_compose needs a policy

This tool executes Docker Compose commands that start, stop, and restart containers—operations whose effects depend on which project and command are specified. While not destructive (containers can be restarted), it clearly fits Execute because it triggers external system operations. The 'up' and 'down' commands modify the running state of services, and 'pull' fetches images from registries.

From the tool's definition The tool description states it can 'Run docker compose up/down/restart/pull/logs for a project on the devbox.' The verbs 'up', 'down', 'restart', and 'pull' are all active operations that execute external Docker commands and trigger state changes in…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

devbox_docker_compose Rate-limited

devbox_docker_compose 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": {
    "devbox_docker_compose": {
      "limits": [
        {
          "counter": "devbox_docker_compose_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 devbox_docker_compose

What does the devbox_docker_compose tool do? +

Run docker compose up/down/restart/pull/logs for a project 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 devbox_docker_compose? +

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

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

Can I rate-limit devbox_docker_compose? +

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

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

devbox_docker_compose 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.