Abstract
Large language models (LLMs) and agents have lately propelled advances in artificial intelligence for science (AI4S). In this work, we propose a toolset-first paradigm for intelligent computation that decouples the tools from the agents via the model context protocol (MCP). We construct four MCP servers, HEA-MCP, VASP-MCP, LAMMPS-MCP, and OpenClaw-MCP. HEA-MCP provides theoretical calculations for high-entropy alloys (HEA). VASP-MCP and LAMMPS-MCP provide first-principles calculations and molecular dynamics simulations, respectively. OpenClaw-MCP contains an autonomous agent, OpenClaw, which renders the autonomous agent a callable tool. OpenClaw itself also supports the MCP to form a recursive agent architecture. By packaging the tools as MCP servers and connecting them to a general MCP-compatible agent, domain-specific capabilities can be obtained without building dedicated agents and can be reused across agentic frameworks.
Funding Information
  • Natural Science Foundation of Shanghai Municipality (23ZR1418200)
  • National Natural Science Foundation of China (21703158)
  • National Natural Science Foundation of China (21873073)
  • National Natural Science Foundation of China (22273023)
  • National Natural Science Foundation of China (92477103)
  • Science and Technology Commission of Shanghai Municipality (25511102400)
  • Natural Science Foundation of Zhejiang Province (LMS26B030003)
  • Natural Science Foundation of Chongqing Municipality (CSTB2023NSCQ-MSX0616)

This publication has 40 references indexed in Scilit: