key_press · Mcp Desktop MCP: Risk & Policy

WHAT IT DOES

What key_press does on Mcp Desktop

AI agents invoke key_press to trigger actions in Mcp Desktop. 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_press needs a policy

Key presses can trigger arbitrary OS-level actions (e.g., Cmd+Q to quit apps, Cmd+Delete to delete files, or terminal commands if a terminal is focused). This constitutes executing external operations with potentially wide blast radius depending on context. The description is minimal but the action is clear.

From the tool's definition 'Press a key or key combination' — triggers keyboard input actions on the desktop, which can execute commands, trigger shortcuts, or manipulate applications

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

key_press Rate-limited

key_press 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_press": {
      "limits": [
        {
          "counter": "key_press_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, so you can run agents against it safely.

FAQ

Questions about key_press

What does the key_press tool do? +

Press a key or key combination. Examples:. It is categorised as a Execute tool in the Mcp Desktop 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_press? +

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

What risk level is key_press? +

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

Can I rate-limit key_press? +

Yes. Add a rate_limit block to the key_press 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_press completely? +

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

key_press is provided by the Mcp Desktop MCP server (mocha06/mcp-desktop). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.