screen_timing · Screen Agent MCP: Risk & Policy

WHAT IT DOES

What screen_timing does on Screen Agent

AI agents call screen_timing as a supporting operation in Screen Agent workflows.

WHY IT NEEDS A POLICY

Why screen_timing needs a policy

This tool toggles performance timing/profiling on or off. It does not read user data, write or modify content, execute commands, destroy data, or involve financial transactions. It is a diagnostic/instrumentation toggle that only affects internal timing measurements, placing it firmly in the 'Other' category with low severity.

From the tool's definition 控制性能计时功能的开关，用于分析各操作的耗时 (Controls the on/off switch of performance timing functionality, used to analyze the time consumption of each operation)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

screen_timing Rate-limited

screen_timing gets a rate cap, and everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "screen_timing": {
      "limits": [
        {
          "counter": "screen_timing_rate",
          "window": "minute",
          "max": 60,
          "scope": "grant"
        }
      ]
    }
  }
}

SET A RULE FOR 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_timing

What does the screen_timing tool do? +

控制性能计时功能的开关，用于分析各操作的耗时。. It is categorised as a Other tool in the Screen Agent MCP Server, which means it performs auxiliary operations.

How do I enforce a policy on screen_timing? +

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

screen_timing is a Other tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit screen_timing? +

Yes. Add a rate_limit block to the screen_timing 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_timing completely? +

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

screen_timing 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.