AI agents call list_processes to retrieve information from LuzzyTool without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and enumerates information about running processes without modifying, executing, or terminating them. It is a pure information-retrieval operation (list/query pattern) with minimal blast radius even if misused—an AI agent learning about running processes cannot directly cause harm through this tool alone.
From the tool's definition Tool name 'list_processes' combined with description stating it 'lists all background processes spawned through spawn_process in the current MCP session' indicates a read-only query operation with no modifications or side effects.
Attacks that exploit this kind of access
【监控操作】列出当前 MCP 会话中所有通过 spawn_process 启动的后台进程。. It is categorised as a Read tool in the LuzzyTool MCP Server, which means it retrieves data without modifying state.
Register the LuzzyTool MCP server in PolicyLayer and add a rule for list_processes: 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 LuzzyTool. Nothing to install.
list_processes 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 list_processes 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 list_processes. 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.
list_processes is provided by the LuzzyTool MCP server (luzzymeow/luzzytool). 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 →