os_mouse_up · OScribe MCP: Risk & Policy

WHAT IT DOES

What os_mouse_up does on OScribe

AI agents invoke os_mouse_up 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_mouse_up needs a policy

This tool triggers a physical UI interaction (mouse button release) on the desktop, completing an action sequence that can interact with any application. While the action itself is mechanical, in context it completes drag operations that could have wide-ranging effects depending on what is being dragged where. It's an execution of a desktop automation action with side effects determined by the surrounding context.

From the tool's definition Release mouse button at current cursor position. Use after os_mouse_down to complete manual drag operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

os_mouse_up Rate-limited

os_mouse_up 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_mouse_up": {
      "limits": [
        {
          "counter": "os_mouse_up_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_mouse_up

What does the os_mouse_up tool do? +

Release mouse button at current cursor position. Use after os_mouse_down to complete manual drag operations. For simple drag-and-drop, prefer os_drag instead. 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_mouse_up? +

Register the OScribe MCP server in PolicyLayer and add a rule for os_mouse_up: 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_mouse_up? +

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

Can I rate-limit os_mouse_up? +

Yes. Add a rate_limit block to the os_mouse_up 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_mouse_up completely? +

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

os_mouse_up 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.