The integration of Large Language Models (LLMs) into network operations (AIOps) is hindered by two fundamental challenges: the stochastic grounding problem, where LLMs struggle to reliably parse unstructured, vendor-specific CLI output, and the security gap of granting autonomous agents shell access. This paper introduces MCP-Diag, a hybrid neuro-symbolic architecture built upon the Model Context Protocol (MCP). We propose a deterministic translation layer that converts raw stdout from canonical utilities (dig, ping, traceroute) into rigorous JSON schemas before AI ingestion. We further introduce a mandatory "Elicitation Loop" that enforces Human-in-the-Loop (HITL) authorization at the protocol level. Our preliminary evaluation demonstrates that MCP-Diag achieving 100% entity extraction accuracy with less than 0.9% execution latency overhead and 3.7x increase in context token usage.

翻译：将大型语言模型（LLM）集成到网络运维（AIOps）中面临两个基本挑战：一是随机接地问题，即LLM难以可靠地解析非结构化的、供应商特定的CLI输出；二是授予自主代理Shell访问权限所带来的安全鸿沟。本文介绍了MCP-Diag，一种基于模型上下文协议（MCP）构建的混合神经符号架构。我们提出了一种确定性翻译层，在AI摄取之前，将来自标准工具（dig, ping, traceroute）的原始标准输出转换为严格的JSON模式。我们进一步引入了一个强制性的"启发循环"，在协议层面强制执行人在回路（HITL）授权。我们的初步评估表明，MCP-Diag实现了100%的实体提取准确率，执行延迟开销低于0.9%，上下文令牌使用量增加了3.7倍。