Automatic generation of technical drawings using Model Context Protocol
Abstract
With the current omnipresence of Large Language Models (LLM) there is a high interest in how to apply them also in Computer Aided Design (CAD). This paper presents an agent-based approach for the automated generation of technical drawings from existing 3D CAD models using direct integration via the Model Context Protocol (MCP). Instead of relying on intermediary representations or scripting languages, the proposed system connects a multimodal large language model directly to the native CAD environment via an integrated MCP server. The approach supports iterative refinement through visual feedback and native geometric constraints, allowing the agent to select, place, and revise drawing views in a closed loop. A modular FreeCAD addon implementing this concept is introduced and released as a testbed for agentic CAD research. The system is evaluated by comparing automatically generated drawings with human-created references using defined metrics for view selection and layout quality. Experiments with two multimodal language models demonstrate that LLM-based agentic drawing generation still has difficulties matching human drafting decisions, due to current limitations in visual understanding. The results highlight the potential of direct CAD–agent integration and motivate further specialization of smaller models for technical drawing tasks.
Read the paper
Related studies
- Learning from First-Generation Qualitative Approaches in the IS Discipline: An Evolutionary View and Some Implications for Authors and Evaluators (PART 1/2)
- Commentary on the clinical and preclinical dosage limits of interstitially administered magnetic fluids for therapeutic hyperthermia based on current practice and efficacy models
- Prosthesis: New Technological Opportunities and Innovative Biomedical Devices
- The history and future of neural modeling for cochlear implants
- Ryanodine receptors: waking up from refractoriness
- Novel Transgenic Rabbit Model Sheds Light on the Puzzling Role of Matrix Metalloproteinase-12 in Atherosclerosis
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.