From Prompt to Plot: An MCP Framework for LLM-Driven Engineering Automation

Abstract

The wellbore schematic is one of the most critical diagrams in drilling engineering design. Currently, these schematics are predominantly generated manually, a process that is tedious, inefficient, and lacks standardization, leading to significant inconsistencies among diagrams produced by different engineers. To address these challenges and enable the intelligent generation of wellbore schematics, we first developed an efficient drawing algorithm featuring unified depth mapping, piecewise geometric analysis of the well trajectory, and wellbore profile visualization based on direction vectors. Subsequently, we employed a Large Language Model (LLM) as the central reasoning hub, integrating domain-specific knowledge through a Knowledge Base (KB). Furthermore, we utilized the Model Context Protocol (MCP) as a standardized interface for tool invocation, enabling efficient bidirectional interaction between the LLM and external engineering computation and drawing programs. This culminated in the development of an intelligent wellbore schematic generation system based on the "LLM+KB+MCP" architecture. The results demonstrate that the system achieves a tool-calling success rate of over 95% across eight mainstream LLMs, showcasing its excellent compatibility, efficiency, and stability. The system can intelligently generate schematics for various well types and can be applied to scenarios such as wellbore structure optimization, knowledge-driven drafting, and the intelligent redrawing and enhancement of wellbore schematics from fuzzy images. This work provides robust support for the intelligent transformation of drilling engineering design.