cloudron_control_app · Mcp Cloudron MCP: Risk & Policy

WHAT IT DOES

What cloudron_control_app does on Mcp Cloudron

AI agents invoke cloudron_control_app to trigger actions in Mcp Cloudron. 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 cloudron_control_app needs a policy

This tool executes commands that trigger state changes in running applications (stopping/starting/restarting services). While not destructive (data is not deleted/overwritten) or financial, it directly executes operational commands on infrastructure. The blast radius is high: a misconfigured call could disrupt critical self-hosted services.

From the tool's definition Tool description states it controls app lifecycle with actions 'start, stop, restart' — these trigger external operations whose effects depend on the specified action argument. The tool returns a task ID indicating async execution of these operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cloudron_control_app Rate-limited

cloudron_control_app 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": {
    "cloudron_control_app": {
      "limits": [
        {
          "counter": "cloudron_control_app_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 Mcp Cloudron, so you can run agents against it safely.

FAQ

Questions about cloudron_control_app

What does the cloudron_control_app tool do? +

Control app lifecycle (start, stop, restart). Returns 202 Accepted with task ID for async operation tracking via cloudron_task_status. It is categorised as a Execute tool in the Mcp Cloudron MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on cloudron_control_app? +

Register the Mcp Cloudron MCP server in PolicyLayer and add a rule for cloudron_control_app: 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 Mcp Cloudron. Nothing to install.

What risk level is cloudron_control_app? +

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

Can I rate-limit cloudron_control_app? +

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

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

cloudron_control_app is provided by the Mcp Cloudron MCP server (serenichron/mcp-cloudron). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.