os_click_at · OScribe MCP: Risk & Policy

WHAT IT DOES

What os_click_at does on OScribe

AI agents invoke os_click_at 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_click_at needs a policy

Clicking at arbitrary screen coordinates triggers UI interactions in any application — this is an Execute-category action. The blast radius is high because an AI agent could click buttons, confirm dialogs, submit forms, or trigger destructive operations in any running application without knowing the exact consequence in advance.

From the tool's definition 'Click at specific screen coordinates' and 'controls any application via screenshot and AI vision, enabling UI automation through natural language commands'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

os_click_at Rate-limited

os_click_at 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_click_at": {
      "limits": [
        {
          "counter": "os_click_at_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_click_at

What does the os_click_at tool do? +

Click at specific screen coordinates (moves and clicks in one action). Prefer using os_move + os_click for more precise control. 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_click_at? +

Register the OScribe MCP server in PolicyLayer and add a rule for os_click_at: 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_click_at? +

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

Can I rate-limit os_click_at? +

Yes. Add a rate_limit block to the os_click_at 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_click_at completely? +

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

os_click_at 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.