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.
@article{arxiv.2601.22633,
title = {MCP-Diag: A Deterministic, Protocol-Driven Architecture for AI-Native Network Diagnostics},
author = {Devansh Lodha and Mohit Panchal and Sameer G. Kulkarni},
journal= {arXiv preprint arXiv:2601.22633},
year = {2026}
}
Comments
Accepted at COMSNETS 2026 Graduate Forum. Best Paper Award (Runner Up). 5 pages, 3 figures