获取当前平台的 CPU 占用率
AI agents call getCpuUsage to retrieve information from Current operating environment without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries CPU utilization statistics from the operating environment. It performs a read-only operation with no side effects, no data modification, no code execution, and no destructive or financial impact. The information retrieved is informational only. Confidence is high because the intent is unambiguous.
From the tool's definition Tool name 'getCpuUsage' and description 'get current platform's CPU usage' indicate retrieval of system metrics without modification.
Attacks that exploit this kind of access
获取当前平台的 CPU 占用率. It is categorised as a Read tool in the Current operating environment MCP Server, which means it retrieves data without modifying state.
Register the Current operating environment MCP server in PolicyLayer and add a rule for getCpuUsage: 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 Current operating environment. Nothing to install.
getCpuUsage 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 getCpuUsage 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 getCpuUsage. 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.
getCpuUsage is provided by the Current operating environment MCP server (jackxuyi/env-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 →