screen_input_text · Screen Agent MCP: Risk & Policy

WHAT IT DOES

What screen_input_text does on Screen Agent

AI agents invoke screen_input_text to trigger actions in Screen Agent. 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 screen_input_text needs a policy

This tool types text into desktop UI elements, which constitutes executing an external operation with real-world side effects. Misuse could trigger form submissions, send messages, execute commands in terminals/run dialogs, or manipulate application state in ways that are difficult to reverse. The blast radius is high because arbitrary text input into any focused window can cause significant unintended consequences.

From the tool's definition 在屏幕上输入文字 (Input text on screen); part of a Windows desktop automation server that 'allows agents to interact with desktop applications via actions like clicking and typing'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

screen_input_text Rate-limited

screen_input_text 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": {
    "screen_input_text": {
      "limits": [
        {
          "counter": "screen_input_text_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 Screen Agent, so you can run agents against it safely.

FAQ

Questions about screen_input_text

What does the screen_input_text tool do? +

在屏幕上输入文字。需要先调用 screen_get_layout 绑定目标窗口。. It is categorised as a Execute tool in the Screen Agent MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on screen_input_text? +

Register the Screen Agent MCP server in PolicyLayer and add a rule for screen_input_text: 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 Screen Agent. Nothing to install.

What risk level is screen_input_text? +

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

Can I rate-limit screen_input_text? +

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

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

screen_input_text is provided by the Screen Agent MCP server (lqszhsp/screen-agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.