Key-Tool · Windows- MCP: Risk & Policy

WHAT IT DOES

What Key-Tool does on Windows-MCP

AI agents invoke Key-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 Key-Tool needs a policy

Pressing keys can trigger arbitrary system actions (e.g., Enter to confirm dialogs, Delete to remove files, Win+R to run commands). Combined with sibling tools like Powershell-Tool and Launch-Tool on a Windows automation server, keystroke injection represents an Execute-level capability with high blast radius. The description is sparse, lowering confidence slightly, but the tool's nature is clear from context.

From the tool's definition 'Press individual keyboard keys. Supports special keys' — simulates keyboard input on the Windows OS, triggering system-level actions depending on which keys are pressed

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

Key-Tool Rate-limited

Key-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": {
    "Key-Tool": {
      "limits": [
        {
          "counter": "key-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 Key-Tool

What does the Key-Tool tool do? +

Press individual keyboard keys. Supports special keys like. 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 Key-Tool? +

Register the Windows- MCP server in PolicyLayer and add a rule for Key-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 Key-Tool? +

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

Can I rate-limit Key-Tool? +

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

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

Key-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.