Medium Risk

mouse_move

Moves the mouse to specified coordinates

How to control mouse_move ↓

AI agents use mouse_move to create or update resources in MCP Desktop Automation — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Desktop Automation environment.

Medium Risk

An AI agent can call mouse_move faster than any human can review — one bad instruction and it creates or modifies resources in MCP Desktop Automation by the hundred, each call as confident as the last.

Documented attack patterns abuse exactly the kind of access mouse_move gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Desktop Automation, and nothing reaches the server without passing your rules. This is the rule we recommend for mouse_move:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "mouse_move": {
      "limits": [
        {
          "counter": "mouse_move_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

mouse_move stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register MCP Desktop Automation — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Go deeper

What does the mouse_move tool do? +

Moves the mouse to specified coordinates. It is categorised as a Write tool in the MCP Desktop Automation MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on mouse_move? +

Register the MCP Desktop Automation MCP server in PolicyLayer and add a rule for mouse_move: 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 MCP Desktop Automation. Nothing to install.

What risk level is mouse_move? +

mouse_move is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit mouse_move? +

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

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

mouse_move is provided by the MCP Desktop Automation MCP server (tanob/mcp-desktop-automation). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP Desktop Automation tool call.

Deterministic rules across all 6 MCP Desktop Automation tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

6 MCP Desktop Automation tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.