Get the top N processes consuming the most CPU
AI agents call get_top_cpu_processes to retrieve information from MCProcessMonitor without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves process metrics (CPU usage rankings) for analysis purposes. It does not execute commands, modify system state, delete data, or trigger external operations. The blast radius of misuse is minimal—an AI agent could only gather information about system resource consumption, which is informational in nature.
From the tool's definition Tool description states 'Get the top N processes consuming the most CPU' — a retrieval operation with no modification, deletion, or execution of processes.
Attacks that exploit this kind of access
Get the top N processes consuming the most CPU. It is categorised as a Read tool in the MCProcessMonitor MCP Server, which means it retrieves data without modifying state.
Register the MCProcessMonitor MCP server in PolicyLayer and add a rule for get_top_cpu_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 MCProcessMonitor. Nothing to install.
get_top_cpu_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 get_top_cpu_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 get_top_cpu_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.
get_top_cpu_processes is provided by the MCProcessMonitor MCP server (kiralyzoltan98/mcprocessmonitor). 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 →