Launch-Tool · Windows- MCP: Risk & Policy

WHAT IT DOES

What Launch-Tool does on Windows-MCP

AI agents invoke Launch-Tool to trigger actions in Windows-MCP. 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 Launch-Tool needs a policy

Launching applications is an Execute action: it triggers external operations whose effects depend on what application is launched and what that application does. While launching a benign app like Notepad is low-risk, an agent could be tricked into launching malware, system tools that modify OS state, or applications that access sensitive data.

From the tool's definition Tool description states 'Launch an application from the Windows Start Menu by name' — directly triggers execution of arbitrary applications on the system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

Launch-Tool Rate-limited

Launch-Tool 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": {
    "Launch-Tool": {
      "limits": [
        {
          "counter": "launch-tool_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 Windows-MCP, so you can run agents against it safely.

FAQ

Questions about Launch-Tool

What does the Launch-Tool tool do? +

Launch an application from the Windows Start Menu by name (e.g.,. It is categorised as a Execute tool in the Windows-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on Launch-Tool? +

Register the Windows- MCP server in PolicyLayer and add a rule for Launch-Tool: 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 Windows-MCP. Nothing to install.

What risk level is Launch-Tool? +

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

Can I rate-limit Launch-Tool? +

Yes. Add a rate_limit block to the Launch-Tool 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 Launch-Tool completely? +

Set action: deny in the PolicyLayer policy for Launch-Tool. 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 Launch-Tool? +

Launch-Tool is provided by the Windows- MCP server (zhouke2020/cursortouch-windows-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.