desktop_app_launch · MCP Desktop Tools MCP: Risk & Policy

WHAT IT DOES

What desktop_app_launch does on MCP Desktop Tools

AI agents invoke desktop_app_launch to trigger actions in MCP Desktop Tools. 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 desktop_app_launch needs a policy

Launching arbitrary applications is an Execute action because it triggers external operations with effects determined by the arguments (application path/name). An AI agent could be tricked into launching malware, spyware, or privilege escalation tools.

From the tool's definition Tool description states it can 'Launch an application by path, name, or URI'. The sibling tools confirm this is a desktop automation server with system-level capabilities including browser control, keyboard/mouse input, and clipboard access.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

desktop_app_launch Rate-limited

desktop_app_launch 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": {
    "desktop_app_launch": {
      "limits": [
        {
          "counter": "desktop_app_launch_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 Desktop Tools, so you can run agents against it safely.

FAQ

Questions about desktop_app_launch

What does the desktop_app_launch tool do? +

Launch an application by path, name, or URI. It is categorised as a Execute tool in the MCP Desktop Tools MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on desktop_app_launch? +

Register the MCP Desktop Tools MCP server in PolicyLayer and add a rule for desktop_app_launch: 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 Desktop Tools. Nothing to install.

What risk level is desktop_app_launch? +

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

Can I rate-limit desktop_app_launch? +

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

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

desktop_app_launch is provided by the MCP Desktop Tools MCP server (k1ta141k/mcp-desktop-tools). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.