mouse_drag · Computer Use MCP Server MCP: Risk & Policy

WHAT IT DOES

What mouse_drag does on Computer Use MCP Server

AI agents invoke mouse_drag to trigger actions in Computer Use MCP Server. 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 mouse_drag needs a policy

mouse_drag triggers a physical desktop interaction — it simulates a click-hold and drag operation on the user's screen. This is an Execute-category action because it performs an external operation (UI manipulation) whose effects depend on the coordinates provided.

From the tool's definition Drag the mouse from one point to another (logical coordinates)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mouse_drag Rate-limited

mouse_drag 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": {
    "mouse_drag": {
      "limits": [
        {
          "counter": "mouse_drag_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 Computer Use MCP Server, so you can run agents against it safely.

FAQ

Questions about mouse_drag

What does the mouse_drag tool do? +

Drag the mouse from one point to another (logical coordinates). It is categorised as a Execute tool in the Computer Use MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on mouse_drag? +

Register the Computer Use MCP Server MCP server in PolicyLayer and add a rule for mouse_drag: 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 Computer Use MCP Server. Nothing to install.

What risk level is mouse_drag? +

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

Can I rate-limit mouse_drag? +

Yes. Add a rate_limit block to the mouse_drag 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_drag completely? +

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

mouse_drag is provided by the Computer Use MCP Server MCP server (syedazharmbnr1/computer-use-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.