screen_click · Screen Agent MCP: Risk & Policy

WHAT IT DOES

What screen_click does on Screen Agent

AI agents invoke screen_click 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_click needs a policy

The tool name and server description indicate this performs click actions on desktop UI elements. Clicking can trigger arbitrary operations (launching programs, confirming dialogs, submitting forms, deleting files via UI) depending on what is clicked. This qualifies as Execute due to triggering external operations whose effects depend on arguments.

From the tool's definition Tool name 'screen_click' on a Windows desktop automation MCP server that 'allows agents to interact with desktop applications via actions like clicking'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

screen_click Rate-limited

screen_click 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_click": {
      "limits": [
        {
          "counter": "screen_click_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_click

What does the screen_click tool do? +

screen_click. 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_click? +

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

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

Can I rate-limit screen_click? +

Yes. Add a rate_limit block to the screen_click 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_click completely? +

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

screen_click 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.