computer_scroll · LocalAnt MCP: Risk & Policy

WHAT IT DOES

What computer_scroll does on LocalAnt

AI agents invoke computer_scroll to trigger actions in LocalAnt. 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 computer_scroll needs a policy

This tool executes UI automation actions (simulated key presses) on the local PC. It falls under Execute as it triggers external operations (input events) whose effects depend on the target element and context. While relatively benign in isolation, misuse could interact with sensitive UI elements or forms.

From the tool's definition 'Scroll the focused element by sending Page Up/Down key presses' — triggers keyboard input/browser automation actions on the PC

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

computer_scroll Rate-limited

computer_scroll 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": {
    "computer_scroll": {
      "limits": [
        {
          "counter": "computer_scroll_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 LocalAnt, so you can run agents against it safely.

FAQ

Questions about computer_scroll

What does the computer_scroll tool do? +

Scroll the focused element by sending Page Up/Down key presses (click the target area first. It is categorised as a Execute tool in the LocalAnt MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on computer_scroll? +

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

What risk level is computer_scroll? +

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

Can I rate-limit computer_scroll? +

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

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

computer_scroll is provided by the LocalAnt MCP server (yuga-hashimoto/localant). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.