Get current CPU usage statistics.
AI agents call get_cpu_usage to retrieve information from System Monitor MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries current CPU usage metrics without creating, modifying, deleting, or executing any operations. It is a straightforward read operation that returns monitoring data. The low severity reflects that misuse poses minimal risk—an agent could only gather system information, not cause harm.
From the tool's definition Tool name 'get_cpu_usage' and description 'Get current CPU usage statistics' indicate data retrieval with no modification or execution of system changes.
Attacks that exploit this kind of access
Get current CPU usage statistics. It is categorised as a Read tool in the System Monitor MCP Server MCP Server, which means it retrieves data without modifying state.
Register the System Monitor MCP Server MCP server in PolicyLayer and add a rule for get_cpu_usage: 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 System Monitor MCP Server. Nothing to install.
get_cpu_usage 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_cpu_usage 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_cpu_usage. 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_cpu_usage is provided by the System Monitor MCP Server MCP server (praveert/cord). 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 →