실행 중인 주요 프로세스 목록을 보여줍니다.
AI agents call app_list_running to retrieve information from K-Personal MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that enumerates running processes. It retrieves information about the system state but does not modify, execute, or delete anything. The blast radius is minimal—an AI agent cannot cause harm by querying process lists. Severity is low because the information exposed is limited to process names/IDs already visible to the user on their own system.
From the tool's definition Tool name 'app_list_running' and description '실행 중인 주요 프로세스 목록을 보여줍니다' (shows a list of running main processes) indicate this retrieves or queries data about currently running processes without side effects.
Attacks that exploit this kind of access
실행 중인 주요 프로세스 목록을 보여줍니다. It is categorised as a Read tool in the K-Personal MCP MCP Server, which means it retrieves data without modifying state.
Register the K-Personal MCP server in PolicyLayer and add a rule for app_list_running: 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.
app_list_running is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the app_list_running 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.
Set action: deny in the PolicyLayer policy for app_list_running. 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.
app_list_running 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →