double_click · Mcp Desktop MCP: Risk & Policy

WHAT IT DOES

What double_click does on Mcp Desktop

AI agents invoke double_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 double_click needs a policy

Double-clicking triggers UI actions on the desktop whose effects depend entirely on what is under the cursor — it could open files, execute programs, confirm dialogs, or activate destructive controls. Because the outcome is context-dependent and can trigger arbitrary application behavior, Execute is the appropriate category.

From the tool's definition Double-click at the given screen coordinates

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

double_click Rate-limited

double_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": {
    "double_click": {
      "limits": [
        {
          "counter": "double_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 double_click

What does the double_click tool do? +

Double-click at the given screen coordinates. Pass verify_app to confirm the right app is frontmost before clicking. 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 double_click? +

Register the Mcp Desktop MCP server in PolicyLayer and add a rule for double_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 double_click? +

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

Can I rate-limit double_click? +

Yes. Add a rate_limit block to the double_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 double_click completely? +

Set action: deny in the PolicyLayer policy for double_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 double_click? +

double_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.