High Risk →

key_down

Hold down a specific keyboard key until released.

How to control key_down ↓

AI agents invoke key_down to trigger actions in Computer Control 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.

High Risk

This tool simulates holding a keyboard key on the user's computer. It can be used to trigger arbitrary keyboard shortcuts, modifier key combinations (e.g., holding Ctrl, Alt, Shift, Win/Cmd), or continuous input, enabling broad system-level actions such as opening system dialogs, triggering shortcuts that delete or modify data, or combined with other tools to perform complex automated actions.

From the tool's definition Hold down a specific keyboard key until released

Documented attack patterns abuse exactly the kind of access key_down gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and Computer Control MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for key_down:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "key_down": {
      "limits": [
        {
          "counter": "key_down_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

key_down 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.

  1. Create a free account and register Computer Control MCP — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RATE-LIMIT THIS TOOL →

Free to start. No card required.

Go deeper

What does the key_down tool do? +

Hold down a specific keyboard key until released. It is categorised as a Execute tool in the Computer Control 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_down? +

Register the Computer Control MCP server in PolicyLayer and add a rule for key_down: 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 Control MCP. Nothing to install.

What risk level is key_down? +

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

Can I rate-limit key_down? +

Yes. Add a rate_limit block to the key_down 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_down completely? +

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

key_down is provided by the Computer Control MCP server (ab498/computer-control-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Computer Control MCP tool call.

Deterministic rules across all 15 Computer Control MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

15 Computer Control MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.