browser_keyboard_type · MCProxy MCP: Risk & Policy

WHAT IT DOES

What browser_keyboard_type does on MCProxy

AI agents invoke browser_keyboard_type 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_type needs a policy

Typing into a browser element is an interactive browser action that can trigger form submissions, searches, logins, or other operations depending on the context. It goes beyond a simple read or write of data — it executes input into a live browser session with potentially wide-ranging side effects (e.g., submitting credentials, entering payment info, triggering JS events).

From the tool's definition 'Type text at the currently focused element' — triggers keyboard input actions in a controlled headless browser, constituting an external browser operation whose effects depend on what text is typed and where

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_keyboard_type Rate-limited

browser_keyboard_type 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_type": {
      "limits": [
        {
          "counter": "browser_keyboard_type_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_type

What does the browser_keyboard_type tool do? +

Type text at the currently focused element. Use this after clicking an input field with click_at. More human-like than browser_type which uses selectors. 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_type? +

Register the MCProxy MCP server in PolicyLayer and add a rule for browser_keyboard_type: 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_type? +

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

Can I rate-limit browser_keyboard_type? +

Yes. Add a rate_limit block to the browser_keyboard_type 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_type completely? +

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

browser_keyboard_type 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.