AI agents call system_process_list to retrieve information from Infra Ops without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries process information from the system and returns data for inspection. It performs no side effects: it does not execute, modify, delete, or control any processes. The optional filtering and sorting are read-only operations on the result set. Blast radius is minimal—worst case, an AI agent gains visibility into running processes, which is informational only.
From the tool's definition Tool name and description indicate 'List running processes' with 'optional filtering' and 'sorting' — purely retrieval operations with no modification or execution capability.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
List running processes with optional filtering by name and sorting by cpu, memory, or pid. It is categorised as a Read tool in the Infra Ops MCP Server, which means it retrieves data without modifying state.
Register the Infra Ops MCP server in PolicyLayer and add a rule for system_process_list: 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 Infra Ops. Nothing to install.
system_process_list 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 system_process_list 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 system_process_list. 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.
system_process_list is provided by the Infra Ops MCP server (skyvanguard/infra-ops-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 →