application-start · Dokploy MCP Server MCP: Risk & Policy

WHAT IT DOES

What application-start does on Dokploy MCP Server

AI agents invoke application-start to trigger actions in Dokploy MCP Server. 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 application-start needs a policy

Starting an application is an Execute action—it runs/triggers an external operation whose effects depend on which application is targeted. While the action is reversible (can be stopped), it commits an operational change to running infrastructure.

From the tool's definition Tool name 'application-start' combined with description 'Starts an application in Dokploy' indicates it triggers an external operational effect (starting a service/application).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

application-start Rate-limited

application-start 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": {
    "application-start": {
      "limits": [
        {
          "counter": "application-start_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 Dokploy MCP Server, so you can run agents against it safely.

FAQ

Questions about application-start

What does the application-start tool do? +

Starts an application in Dokploy. It is categorised as a Execute tool in the Dokploy MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on application-start? +

Register the Dokploy MCP Server MCP server in PolicyLayer and add a rule for application-start: 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 Dokploy MCP Server. Nothing to install.

What risk level is application-start? +

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

Can I rate-limit application-start? +

Yes. Add a rate_limit block to the application-start 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 application-start completely? +

Set action: deny in the PolicyLayer policy for application-start. 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 application-start? +

application-start is provided by the Dokploy MCP Server MCP server (limehawk/dokploy-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.