ax_drag · MacWright MCP: Risk & Policy

WHAT IT DOES

What ax_drag does on MacWright

AI agents invoke ax_drag to trigger actions in MacWright. 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 ax_drag needs a policy

Drag operations are UI interactions that can cause significant side effects depending on context: moving files between folders, reordering data, or triggering application-specific actions. This is an Execute action because it performs an external operation whose effects depend entirely on the arguments (source and destination elements/coordinates).

From the tool's definition 'drag from it to either another labeled element or specific screen coordinates' — triggers a UI drag action that can move files, reorder items, or trigger drag-drop operations with external effects

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ax_drag Rate-limited

ax_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": {
    "ax_drag": {
      "limits": [
        {
          "counter": "ax_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 MacWright, so you can run agents against it safely.

FAQ

Questions about ax_drag

What does the ax_drag tool do? +

Find a native UI element by label text and drag from it to either another labeled element or specific screen coordinates. It is categorised as a Execute tool in the MacWright MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ax_drag? +

Register the MacWright MCP server in PolicyLayer and add a rule for ax_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 MacWright. Nothing to install.

What risk level is ax_drag? +

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

Can I rate-limit ax_drag? +

Yes. Add a rate_limit block to the ax_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 ax_drag completely? +

Set action: deny in the PolicyLayer policy for ax_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 ax_drag? +

ax_drag is provided by the MacWright MCP server (ruchit-p/macwright). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.