screen_explore · Screen Agent MCP: Risk & Policy

WHAT IT DOES

What screen_explore does on Screen Agent

AI agents invoke screen_explore 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_explore needs a policy

This tool autonomously explores the screen and identifies/interacts with clickable elements, which constitutes automated execution of UI actions. It operates within a Windows desktop automation framework that performs clicks and other interactions. Automated exploration could trigger unintended actions across any open application, making it high severity.

From the tool's definition '自动探索屏幕，学习哪些元素可点击' (automatically explores the screen, learning which elements are clickable) — implies automated UI traversal and interaction with desktop elements

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

screen_explore Rate-limited

screen_explore 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_explore": {
      "limits": [
        {
          "counter": "screen_explore_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_explore

What does the screen_explore tool do? +

自动探索屏幕，学习哪些元素可点击。用于了解新界面。. 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_explore? +

Register the Screen Agent MCP server in PolicyLayer and add a rule for screen_explore: 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_explore? +

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

Can I rate-limit screen_explore? +

Yes. Add a rate_limit block to the screen_explore 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_explore completely? +

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

screen_explore 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.