app_kill · K-Personal MCP: Risk & Policy

WHAT IT DOES

What app_kill does on K-Personal MCP

AI agents use app_kill to create or update resources in K-Personal MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your K-Personal MCP environment.

WHY IT NEEDS A POLICY

Why app_kill needs a policy

An AI agent can call app_kill faster than any human can review — one bad instruction and it creates or modifies resources in K-Personal MCP by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

app_kill Rate-limited

app_kill stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "app_kill": {
      "limits": [
        {
          "counter": "app_kill_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 app_kill

What does the app_kill tool do? +

이름이 일치하는 프로세스를 종료합니다. 예: notepad.exe. It is categorised as a Write tool in the K-Personal MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on app_kill? +

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

app_kill is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit app_kill? +

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

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

app_kill 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.