中国物理B ›› 2025, Vol. 34 ›› Issue (11): 117106-117106.doi: 10.1088/1674-1056/ae0681

• • 上一篇    下一篇

VASPilot: MCP-facilitated multi-agent intelligence for autonomous VASP simulations

Jiaxuan Liu(刘家轩)1,2, Tiannian Zhu(朱天念)1,2, Caiyuan Ye(叶财渊)1,2, Zhong Fang(方忠)1,2, Hongming Weng(翁红明)1,2†, and Quansheng Wu(吴泉生)1,2‡   

  1. 1 Beijing National Laboratory for Condensed Matter Physics and Institute of Physics, Chinese Academy of Sciences, Beijing 100190, China;
    2 University of Chinese Academy of Sciences, Beijing 100049, China
  • 收稿日期:2025-08-25 修回日期:2025-09-09 接受日期:2025-09-15 发布日期:2025-11-06
  • 基金资助:
    Project supported by the Science Center of the National Natural Science Foundation of China (Grant No. 12188101), the National Key R&D Program of China (Grant Nos. 2023YFA1607400 and 2022YFA1403800), the National Natural Science Foundation of China (Grant Nos. 12274436, 11925408, and 11921004), and the New Cornerstone Science Foundation through the XPLORER PRIZE. The AI-driven experiments, simulations and model training were performed on the robotic AI-Scientist platform of the Chinese Academy of Science.

VASPilot: MCP-facilitated multi-agent intelligence for autonomous VASP simulations

Jiaxuan Liu(刘家轩)1,2, Tiannian Zhu(朱天念)1,2, Caiyuan Ye(叶财渊)1,2, Zhong Fang(方忠)1,2, Hongming Weng(翁红明)1,2†, and Quansheng Wu(吴泉生)1,2‡   

  1. 1 Beijing National Laboratory for Condensed Matter Physics and Institute of Physics, Chinese Academy of Sciences, Beijing 100190, China;
    2 University of Chinese Academy of Sciences, Beijing 100049, China
  • Received:2025-08-25 Revised:2025-09-09 Accepted:2025-09-15 Published:2025-11-06
  • Contact: Hongming Weng, Quansheng Wu E-mail:hmweng@iphy.ac.cn;quansheng.wu@iphy.ac.cn
  • Supported by:
    Project supported by the Science Center of the National Natural Science Foundation of China (Grant No. 12188101), the National Key R&D Program of China (Grant Nos. 2023YFA1607400 and 2022YFA1403800), the National Natural Science Foundation of China (Grant Nos. 12274436, 11925408, and 11921004), and the New Cornerstone Science Foundation through the XPLORER PRIZE. The AI-driven experiments, simulations and model training were performed on the robotic AI-Scientist platform of the Chinese Academy of Science.

PDF (PC)

4

赞

摘要： Density-functional-theory (DFT) simulations with the Vienna Ab initio Simulation Package (VASP) are indispensable in computational materials science but often require extensive manual setup, monitoring, and postprocessing. Here, we introduce VASPilot, an open-source platform that fully automates VASP workflows via a multi-agent architecture built on the CrewAI framework and a standardized model context protocol (MCP). VASPilot’s agent suite handles every stage of a VASP study from retrieving crystal structures and generating input files to submitting Slurm jobs, parsing error messages, and dynamically adjusting parameters for seamless restarts. A lightweight Quart-based web interface provides intuitive task submission, real-time progress tracking, and drill-down access to execution logs, structure visualizations, and plots. We validated VASPilot on both routine and advanced benchmarks: automated band-structure and density-of-states calculations (including on-the-fly symmetry corrections), plane-wave cutoff convergence tests, lattice-constant optimizations with various van der Waals corrections, and cross-material band-gap comparisons for transition-metal dichalcogenides. In all cases, VASPilot completed the missions reliably and without manual intervention. Moreover, its modular design allows easy extension to other DFT codes simply by deploying the appropriate MCP server. By offloading technical overhead, VASPilot enables researchers to focus on scientific discovery and accelerates high-throughput computational materials research.

关键词: VASP, agent, model context protocol (MCP), VASPilot

Abstract: Density-functional-theory (DFT) simulations with the Vienna Ab initio Simulation Package (VASP) are indispensable in computational materials science but often require extensive manual setup, monitoring, and postprocessing. Here, we introduce VASPilot, an open-source platform that fully automates VASP workflows via a multi-agent architecture built on the CrewAI framework and a standardized model context protocol (MCP). VASPilot’s agent suite handles every stage of a VASP study from retrieving crystal structures and generating input files to submitting Slurm jobs, parsing error messages, and dynamically adjusting parameters for seamless restarts. A lightweight Quart-based web interface provides intuitive task submission, real-time progress tracking, and drill-down access to execution logs, structure visualizations, and plots. We validated VASPilot on both routine and advanced benchmarks: automated band-structure and density-of-states calculations (including on-the-fly symmetry corrections), plane-wave cutoff convergence tests, lattice-constant optimizations with various van der Waals corrections, and cross-material band-gap comparisons for transition-metal dichalcogenides. In all cases, VASPilot completed the missions reliably and without manual intervention. Moreover, its modular design allows easy extension to other DFT codes simply by deploying the appropriate MCP server. By offloading technical overhead, VASPilot enables researchers to focus on scientific discovery and accelerates high-throughput computational materials research.

Key words: VASP, agent, model context protocol (MCP), VASPilot

中图分类号:  (Density functional theory, local density approximation, gradient and other corrections)

  • 71.15.Mb