browser_keyboard_press · MCProxy MCP: Risk & Policy

WHAT IT DOES

What browser_keyboard_press does on MCProxy

AI agents invoke browser_keyboard_press to trigger actions in MCProxy. 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 browser_keyboard_press needs a policy

This tool simulates keyboard input in a headless browser, which can trigger form submissions (Enter), select all text (Control+a), navigate interfaces, or confirm dialogs. It is an Execute-category action because it drives external browser operations whose effects depend on context and arguments. Misuse could submit forms, confirm destructive dialogs, or navigate to unintended states.

From the tool's definition 'Press a single key' for actions like 'Enter, Tab, Escape, arrows, Backspace, or key combinations like Control+a, Shift+Tab' — triggers browser actions and interactions

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_keyboard_press Rate-limited

browser_keyboard_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": {
    "browser_keyboard_press": {
      "limits": [
        {
          "counter": "browser_keyboard_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 MCProxy, so you can run agents against it safely.

FAQ

Questions about browser_keyboard_press

What does the browser_keyboard_press tool do? +

Press a single key. Use for Enter, Tab, Escape, arrows, Backspace, or key combinations like Control+a, Shift+Tab. It is categorised as a Execute tool in the MCProxy MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on browser_keyboard_press? +

Register the MCProxy MCP server in PolicyLayer and add a rule for browser_keyboard_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 MCProxy. Nothing to install.

What risk level is browser_keyboard_press? +

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

Can I rate-limit browser_keyboard_press? +

Yes. Add a rate_limit block to the browser_keyboard_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 browser_keyboard_press completely? +

Set action: deny in the PolicyLayer policy for browser_keyboard_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 browser_keyboard_press? +

browser_keyboard_press is provided by the MCProxy MCP server (saladtechnologies/mcproxy). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.