bytebot_press_keys · ByteBot MCP Server MCP: Risk & Policy

WHAT IT DOES

What bytebot_press_keys does on ByteBot MCP Server

AI agents invoke bytebot_press_keys to trigger actions in ByteBot MCP Server. 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 bytebot_press_keys needs a policy

This tool directly triggers keyboard input on a desktop system, including modifier key combinations. Keyboard shortcuts can execute arbitrary system-level actions (e.g., Ctrl+Alt+Del, Alt+F4, Ctrl+Z, Win+R to open Run dialog), run commands, delete data, or control applications. The blast radius is high because a misused sequence of keystrokes can trigger destructive or unauthorized operations on the host machine.

From the tool's definition Press keyboard keys including modifiers (Ctrl, Shift, Alt, etc.). Use this for keyboard shortcuts like Ctrl+C, Ctrl+V, Alt+Tab.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

bytebot_press_keys Rate-limited

bytebot_press_keys 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": {
    "bytebot_press_keys": {
      "limits": [
        {
          "counter": "bytebot_press_keys_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 ByteBot MCP Server, so you can run agents against it safely.

FAQ

Questions about bytebot_press_keys

What does the bytebot_press_keys tool do? +

Press keyboard keys including modifiers (Ctrl, Shift, Alt, etc.). Use this for keyboard shortcuts like Ctrl+C, Ctrl+V, Alt+Tab. It is categorised as a Execute tool in the ByteBot MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on bytebot_press_keys? +

Register the ByteBot MCP Server MCP server in PolicyLayer and add a rule for bytebot_press_keys: 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 ByteBot MCP Server. Nothing to install.

What risk level is bytebot_press_keys? +

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

Can I rate-limit bytebot_press_keys? +

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

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

bytebot_press_keys is provided by the ByteBot MCP Server MCP server (sensuslab/spark-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.