triple_click · Mcp Desktop MCP: Risk & Policy

WHAT IT DOES

What triple_click does on Mcp Desktop

AI agents invoke triple_click to trigger actions in Mcp Desktop. 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 triple_click needs a policy

This tool performs a physical UI interaction (triple-click) at arbitrary screen coordinates, triggering mouse events that can affect any application currently on screen. While its primary stated effect is text selection, it can also activate UI elements, trigger actions, or cause unintended interactions depending on what is at the target coordinates.

From the tool's definition Triple-click at the given screen coordinates. Selects all text in the clicked input field — the mouse-native alternative to cmd+a for web inputs.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

triple_click Rate-limited

triple_click 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": {
    "triple_click": {
      "limits": [
        {
          "counter": "triple_click_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 Mcp Desktop, so you can run agents against it safely.

FAQ

Questions about triple_click

What does the triple_click tool do? +

Triple-click at the given screen coordinates. Selects all text in the clicked input field — the mouse-native alternative to cmd+a for web inputs. It is categorised as a Execute tool in the Mcp Desktop MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on triple_click? +

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

What risk level is triple_click? +

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

Can I rate-limit triple_click? +

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

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

triple_click is provided by the Mcp Desktop MCP server (mocha06/mcp-desktop). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.