ui_click_by_name · K-Personal MCP: Risk & Policy

WHAT IT DOES

What ui_click_by_name does on K-Personal MCP

AI agents invoke ui_click_by_name 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 ui_click_by_name needs a policy

Clicking a UI control is an Execute-category action because it triggers external operations in an application whose effects depend on which control is targeted. The blast radius is high because clicking arbitrary UI elements (e.g., 'Delete', 'Confirm', 'Send') can cause irreversible or significant side effects depending on context, and an AI agent could misuse this to interact with any on-screen control.

From the tool's definition 클릭합니다 (clicks) — the tool clicks a UI control matched by name, triggering whatever action that control performs in the target application

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ui_click_by_name Rate-limited

ui_click_by_name 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": {
    "ui_click_by_name": {
      "limits": [
        {
          "counter": "ui_click_by_name_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 ui_click_by_name

What does the ui_click_by_name tool do? +

이름이 일치하는 컨트롤을 클릭합니다. 마우스 커서를 움직이지 않고. 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 ui_click_by_name? +

Register the K-Personal MCP server in PolicyLayer and add a rule for ui_click_by_name: 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 ui_click_by_name? +

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

Can I rate-limit ui_click_by_name? +

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

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

ui_click_by_name 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.