hold_key · Computer Use Windows MCP: Risk & Policy

WHAT IT DOES

What hold_key does on Computer Use Windows

AI agents invoke hold_key to trigger actions in Computer Use Windows. 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 hold_key needs a policy

This tool sends keyboard input to the active window, which can trigger arbitrary application actions (e.g., holding Alt+F4 to close apps, keyboard shortcuts that delete data, system-level commands). It executes external operations whose effects depend on the key arguments passed, making it Execute category.

From the tool's definition 'Press and hold a key or key combination for the specified duration, then release' — triggers keyboard input actions on the Windows desktop

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

hold_key Rate-limited

hold_key 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": {
    "hold_key": {
      "limits": [
        {
          "counter": "hold_key_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 Computer Use Windows, so you can run agents against it safely.

FAQ

Questions about hold_key

What does the hold_key tool do? +

Press and hold a key or key combination for the specified duration, then release. ${FRONTMOST_GATE_DESC}. It is categorised as a Execute tool in the Computer Use Windows MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on hold_key? +

Register the Computer Use Windows MCP server in PolicyLayer and add a rule for hold_key: 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 Computer Use Windows. Nothing to install.

What risk level is hold_key? +

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

Can I rate-limit hold_key? +

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

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

hold_key is provided by the Computer Use Windows MCP server (wimi321/windows-computer-use-skill). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.