cc_mouse_click · K-Personal MCP: Risk & Policy

WHAT IT DOES

What cc_mouse_click does on K-Personal MCP

AI agents invoke cc_mouse_click to trigger actions in K-Personal MCP. 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 cc_mouse_click needs a policy

Simulates mouse click actions at arbitrary screen coordinates. This is a desktop automation Execute action — clicking can trigger UI buttons, links, confirmations, file operations, purchases, or any other interactive UI element depending on what is on screen. The blast radius is high because misuse could activate destructive or financial UI actions (e.g., clicking 'Delete', 'Confirm Purchase', etc.).

From the tool's definition 마우스 클릭을 수행합니다 (performs mouse click at specified coordinates)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cc_mouse_click Rate-limited

cc_mouse_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": {
    "cc_mouse_click": {
      "limits": [
        {
          "counter": "cc_mouse_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 K-Personal MCP, so you can run agents against it safely.

FAQ

Questions about cc_mouse_click

What does the cc_mouse_click tool do? +

지정한 좌표에서 마우스 클릭을 수행합니다. 좌표 생략 시 현재 위치에서 클릭합니다. It is categorised as a Execute tool in the K-Personal MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on cc_mouse_click? +

Register the K-Personal MCP server in PolicyLayer and add a rule for cc_mouse_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 K-Personal MCP. Nothing to install.

What risk level is cc_mouse_click? +

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

Can I rate-limit cc_mouse_click? +

Yes. Add a rate_limit block to the cc_mouse_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 cc_mouse_click completely? +

Set action: deny in the PolicyLayer policy for cc_mouse_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 cc_mouse_click? +

cc_mouse_click is provided by the K-Personal MCP server (lee30934-byte/k-personal-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.