Monitor running processes and collect metrics
AI agents call monitor_processes to retrieve information from Terminal X without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and observes system state (running processes and their metrics) without triggering execution, modification, or deletion of resources. It is a passive monitoring capability with no side effects, fitting the Read category. Severity is low because unauthorized access to process metrics poses minimal immediate risk compared to command execution or destructive operations.
From the tool's definition Tool name 'monitor_processes' and description 'Monitor running processes and collect metrics' indicate data retrieval and observation only. No execution, modification, or destructive action is implied.
Attacks that exploit this kind of access
Monitor running processes and collect metrics. It is categorised as a Read tool in the Terminal X MCP Server, which means it retrieves data without modifying state.
Register the Terminal X MCP server in PolicyLayer and add a rule for monitor_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 Terminal X. Nothing to install.
monitor_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 monitor_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 monitor_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.
monitor_processes is provided by the Terminal X MCP server (rnd-pro/terminal-x-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 →