chrome_keyboard · Chrome MCP Server MCP: Risk & Policy

WHAT IT DOES

What chrome_keyboard does on Chrome MCP Server

AI agents invoke chrome_keyboard to trigger actions in Chrome 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 chrome_keyboard needs a policy

Simulating keyboard input is an Execute-level action because it can trigger a wide range of browser behaviors depending on what keys are sent — from submitting forms and activating shortcuts (e.g., Ctrl+W to close tabs, Ctrl+T to open new ones) to typing into fields.

From the tool's definition 'Simulate keyboard input and shortcuts' — actively triggers keyboard events in the browser, which can submit forms, trigger shortcuts, navigate pages, or activate arbitrary browser/OS functions

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

chrome_keyboard Rate-limited

chrome_keyboard 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": {
    "chrome_keyboard": {
      "limits": [
        {
          "counter": "chrome_keyboard_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 Chrome MCP Server, so you can run agents against it safely.

FAQ

Questions about chrome_keyboard

What does the chrome_keyboard tool do? +

Simulate keyboard input and shortcuts. It is categorised as a Execute tool in the Chrome 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 chrome_keyboard? +

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

What risk level is chrome_keyboard? +

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

Can I rate-limit chrome_keyboard? +

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

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

chrome_keyboard is provided by the Chrome MCP Server MCP server (mnisred/mcp-chrome). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.