Model Context Protocol Business Analyst (MCP-BA): A Governed and Explainable Framework for Enterprise Analytics : Operationalizing Identity-Aware Reasoning and Context-Driven Decision Intelligence in Enterprise AI
Tejas Patel, Sandeep Shivam, Amit Kumar Padhy, Bharadwaj Vulugunda, Chaitanya Kulkarni, Chandrashekhar Medicherla
Abstract
Large Language Models (LLMs) have demonstrated remarkable capacity for natural-language analytics, yet their adoption in enterprise decision pipelines remains constrained by ungoverned data access, inconsistent context alignment, and the absence of audit traceability. This paper introduces the Model Context Protocol Business Analyst (MCP-BA)—a governed reasoning framework that operationalizes the Model Context Protocol to connect user intent, organizational data, and analytical tools under identity-aware and policy-controlled execution. The architecture combines a crawler-vector layer for continuous context refresh with an audit-enforced reasoning loop that transforms LLMs into compliant analytical micro-services. A synthetic enterprise evaluation demonstrated substantial gains over RAG and Atlas baselines, improving context precision by 17 points, governance accuracy by 42%, and audit completeness to 100%, while reducing reasoning latency by 29%. The proposed framework establishes a repeatable design pattern for explainable, secure, and high-trust enterprise analytics, bridging the gap between intelligent automation and corporate accountability.