os_system_ui · OScribe MCP: Risk & Policy

WHAT IT DOES

What os_system_ui does on OScribe

AI agents invoke os_system_ui to trigger actions in OScribe. 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 os_system_ui needs a policy

This tool executes actions on the operating system itself by identifying and providing coordinates for system UI elements that can be clicked to trigger OS-level operations. While it doesn't directly execute shell commands, it enables automated interaction with critical system controls that could launch applications, modify settings, access sensitive system functions, or trigger security dialogs.

From the tool's definition Tool enables control of Windows system UI elements (taskbar, Start button, system tray, desktop icons, action center, widgets) and returns clickable coordinates for interaction.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

os_system_ui Rate-limited

os_system_ui 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": {
    "os_system_ui": {
      "limits": [
        {
          "counter": "os_system_ui_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 OScribe, so you can run agents against it safely.

FAQ

Questions about os_system_ui

What does the os_system_ui tool do? +

Get all Windows system UI elements (taskbar, Start button, system tray, desktop icons, action center, widgets). Use this to interact with OS-level UI independently of application windows. Returns clickable coordinates for all system elements. It is categorised as a Execute tool in the OScribe MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on os_system_ui? +

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

What risk level is os_system_ui? +

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

Can I rate-limit os_system_ui? +

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

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

os_system_ui is provided by the OScribe MCP server (mikealkeal/oscribe). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.