A Spring Boot-based MCP server that provides system resource monitoring tools for CPU, memory, and process information across Linux, macOS, and Windows platforms.
Both tools lack input parameter schemas entirely (empty {} objects), violating the critical requirement that every tool must have a documented input schema. Descriptions exist but are minimal (50-60 chars) and lack actionable context for LLM selection. No parameter descriptions, no output schema documentation, and no error recovery guidance. Tools return unstructured string responses rather than structured JSON. No tool annotations (readOnlyHint, idempotentHint) despite being read-only operations. This server falls well below production baseline.
현재 호스트의 CPU 및 메모리 사용량 정보를 조회합니다
현재 호스트에서 가장 많은 CPU 자원을 사용하는 프로세스 정보를 조회합니다.
No input schemas defined. Both tools declare Input: {} with no parameter definitions, violating the critical requirement that every tool must have a documented input schema with types and descriptions.
Descriptions are too brief (50-60 chars) and lack actionable context. They state WHAT the tool does but not WHEN to use it, what it returns, or how it differs from similar tools. LLMs cannot reliably select between tools with such minimal guidance.
Tools return unstructured string responses instead of structured JSON objects. LLMs cannot reliably parse free-text output or extract fields for downstream tool calls. Responses should be JSON with typed fields (processName, pid, cpuUsage, memoryUsage, etc.).
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 35 | 2026-07-28+ | v2 |
No tool annotations present. Both tools are read-only and idempotent but lack readOnlyHint and idempotentHint annotations. These hints help LLMs reason about safety and retry behavior.
Error handling returns plain text error messages instead of structured error responses with recovery guidance. Exceptions are caught and converted to strings, providing no actionable next steps for the LLM.