type_text_input · Macinput MCP: Risk & Policy

WHAT IT DOES

What type_text_input does on Macinput

AI agents invoke type_text_input to trigger actions in Macinput. 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 type_text_input needs a policy

Typing text into a focused input target is an active execution of desktop GUI interaction. The blast radius is high because the focused target could be a terminal, chat application, email client, or any other sensitive application, and the AI agent has no inherent restriction on what text is typed.

From the tool's definition 'Type unicode text into the currently focused macOS input target' — triggers keyboard input actions on the desktop GUI, which can have wide-ranging side effects depending on the focused application (e.g., executing commands in a terminal, sending messages,…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

type_text_input Rate-limited

type_text_input 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": {
    "type_text_input": {
      "limits": [
        {
          "counter": "type_text_input_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 Macinput, so you can run agents against it safely.

FAQ

Questions about type_text_input

What does the type_text_input tool do? +

Type unicode text into the currently focused macOS input target. It is categorised as a Execute tool in the Macinput MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on type_text_input? +

Register the Macinput MCP server in PolicyLayer and add a rule for type_text_input: 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 Macinput. Nothing to install.

What risk level is type_text_input? +

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

Can I rate-limit type_text_input? +

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

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

type_text_input is provided by the Macinput MCP server (sigma711/macinput). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.