keypress · Linux Computer Use MCP: Risk & Policy

WHAT IT DOES

What keypress does on Linux Computer Use

AI agents invoke keypress to trigger actions in Linux Computer Use. 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 keypress needs a policy

Sending arbitrary keypresses or keyboard chords to a desktop environment can trigger any application action — launching programs, executing commands, deleting files, submitting forms, or interacting with system dialogs. This constitutes executing operations whose effects are entirely argument-dependent and can have wide blast radius on a live desktop.

From the tool's definition Press keys/chords: ['Enter'], ['ctrl','a'], ['ctrl+l','Return']

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

keypress Rate-limited

keypress 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": {
    "keypress": {
      "limits": [
        {
          "counter": "keypress_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 Linux Computer Use, so you can run agents against it safely.

FAQ

Questions about keypress

What does the keypress tool do? +

Press keys/chords: ['Enter'], ['ctrl','a'], ['ctrl+l','Return']. It is categorised as a Execute tool in the Linux Computer Use MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on keypress? +

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

What risk level is keypress? +

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

Can I rate-limit keypress? +

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

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

keypress is provided by the Linux Computer Use MCP server (tak-uukti/linux-computer-use). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.