os_focus · OScribe MCP: Risk & Policy

WHAT IT DOES

What os_focus does on OScribe

AI agents invoke os_focus 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_focus needs a policy

Focusing a window is an external UI operation that changes the state of the desktop environment by bringing a specific application window to the foreground. This is an execution-type action (triggering external UI operations) rather than a simple read.

From the tool's definition Focus a window by title or app name

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

os_focus Rate-limited

os_focus 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_focus": {
      "limits": [
        {
          "counter": "os_focus_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_focus

What does the os_focus tool do? +

Focus a window by title or app name. 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_focus? +

Register the OScribe MCP server in PolicyLayer and add a rule for os_focus: 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_focus? +

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

Can I rate-limit os_focus? +

Yes. Add a rate_limit block to the os_focus 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_focus completely? +

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

os_focus 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.