openmm-mcp-server

openmm-mcp-server

3.5

If you are the rightful owner of openmm-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

OpenMM MCP Server is a comprehensive server for molecular dynamics simulations using OpenMM and DFT calculations with Abacus, providing a natural language interface for complex molecular simulations.

OpenMM MCP Server

|


🧬 OpenMM & Abacus MCP Server

A comprehensive Model Context Protocol (MCP) server for molecular dynamics simulations using OpenMM and DFT calculations with Abacus. This server provides a natural language interface for complex molecular simulations through LLM integration.

✨ Features
  • Complete OpenMM Integration: Support for all OpenMM features including advanced integrators, barostats, and constraints
  • DFT Calculations: Abacus DFT engine integration for quantum mechanical calculations
  • Pre-configured Templates: Ready-to-use setups for protein simulations, membrane systems, and more
  • Advanced Sampling: Metadynamics, free energy calculations, and enhanced sampling methods
  • GPU Acceleration: CUDA and OpenCL platform support for high-performance computing
  • Task Management: Asynchronous task execution with persistence and monitoring
  • Natural Language Interface: Interact with complex simulations using simple English commands
šŸš€ Quick Start
Installation
# Clone the repository
git clone <repository_url>
cd openmm-mcp-server

# Install dependencies
pip install -r requirements.txt

# Optional: Install OpenMM for actual simulations
conda install -c conda-forge openmm

# Test installation
python test_mcp_server.py
Roo Code Integration

Add to your Code/Cline/Claude MCP settings:

{
  "mcpServers": {
    "openmm-server": {
      "command": "python",
      "args": ["run_openmm_server.py"],
      "cwd": "path-to\\openmm-mcp-server",
      "alwaysAllow": [
        "create_md_simulation",
        "create_advanced_md_simulation",
        "setup_protein_simulation",
        "setup_membrane_simulation",
        "create_dft_calculation",
        "control_simulation",
        "get_task_status",
        "list_all_tasks",
        "analyze_results"
      ]
    }
  }
}

Important: Replace the path with your actual project path!

šŸ› ļø Available Tools
Basic Tools
  • create_md_simulation - Create simple MD simulations
  • create_dft_calculation - Create DFT calculations
  • control_simulation - Control simulation execution (start/stop/pause)
  • get_task_status - Check task status
  • list_all_tasks - List all tasks
  • analyze_results - Analyze simulation results
Advanced Tools
  • create_advanced_md_simulation - Full OpenMM feature support (50+ parameters)
  • setup_protein_simulation - Pre-configured protein simulation templates
  • setup_membrane_simulation - Membrane protein simulation setup
šŸ’¬ Usage Examples
Simple Water Simulation
"Run a molecular dynamics simulation of a water molecule at 300K for 10000 steps"
Advanced Protein Simulation
"Set up a protein production simulation for 100 nanoseconds at physiological temperature 310K, using Amber19 force field with TIP3P-FB water model, 0.15M salt concentration, and GPU acceleration"
Membrane Protein Simulation
"Create a POPC membrane protein simulation for 50 nanoseconds with surface tension control"
šŸ“Š OpenMM Parameters Reference
Integrators
  • LangevinMiddle - Langevin middle integrator (recommended)
  • Verlet - Verlet integrator (NVE ensemble)
  • Brownian - Brownian dynamics
  • VariableLangevin - Variable step size Langevin
  • VariableVerlet - Variable step size Verlet
  • NoseHoover - Nose-Hoover thermostat
Force Fields
  • Amber14: ["amber14-all.xml", "amber14/tip3pfb.xml"]
  • Amber19: ["amber19-all.xml", "amber19/tip3pfb.xml"]
  • CHARMM36: ["charmm36_2024.xml", "charmm36/water.xml"]
Water Models
  • tip3p - TIP3P water model
  • tip3pfb - TIP3P-FB water model (recommended)
  • tip4pew - TIP4P-Ew water model
  • spce - SPC/E water model
Platforms
  • CUDA - NVIDIA GPU (fastest)
  • OpenCL - General GPU
  • CPU - CPU computation
  • Reference - Reference implementation
Nonbonded Methods
  • PME - Particle Mesh Ewald (recommended for periodic systems)
  • NoCutoff - No cutoff (small systems)
  • CutoffNonPeriodic - Non-periodic cutoff
  • CutoffPeriodic - Periodic cutoff
  • Ewald - Traditional Ewald summation
Constraints
  • None - No constraints
  • HBonds - Hydrogen bond constraints (recommended)
  • AllBonds - All bond constraints
  • HAngles - Hydrogen angle constraints
Barostats
  • MonteCarloBarostat - Isotropic pressure control
  • MonteCarloAnisotropicBarostat - Anisotropic pressure control
  • MonteCarloMembraneBarostat - Membrane system pressure control
Precision
  • mixed - Mixed precision (recommended)
  • single - Single precision
  • double - Double precision
šŸ”§ Configuration

Environment variables:

export TASK_DATA_DIR="./simulation_data"
export MAX_CONCURRENT_TASKS=4
export DEFAULT_OPENMM_PLATFORM="CUDA"
export LOG_LEVEL="INFO"
export LOG_FILE="./mcp_server.log"
šŸ“ Project Structure
openmm-mcp-server/
ā”œā”€ā”€ run_openmm_server.py      # Startup script
ā”œā”€ā”€ test_mcp_server.py        # Test script
ā”œā”€ā”€ requirements.txt          # Dependencies
ā”œā”€ā”€ README.md                 # English documentation
ā”œā”€ā”€ README_CN.md              # Chinese documentation
ā”œā”€ā”€ src/
│   ā”œā”€ā”€ server_new.py         # Main server
│   ā”œā”€ā”€ advanced_md_tools.py  # Advanced MD tools
│   ā”œā”€ā”€ task_manager.py       # Task management
│   ā”œā”€ā”€ openmm_engine.py      # OpenMM engine
│   ā”œā”€ā”€ abacus_engine.py      # Abacus DFT engine
│   ā”œā”€ā”€ config.py             # Configuration management
│   ā”œā”€ā”€ tools/                # MCP tool implementations
│   ā”œā”€ā”€ resources/            # MCP resource implementations
│   └── utils/                # Utility functions
ā”œā”€ā”€ tests/                    # Test files
ā”œā”€ā”€ examples/                 # Example code
ā”œā”€ā”€ docs/                     # Documentation
└── task_data/                # Task data directory (auto-created)
šŸ“š Additional Documentation
  • - Detailed installation instructions
  • - Comprehensive usage examples
  • - Detailed integration guide
  • - Complete parameter reference
  • - Technical analysis and improvements
šŸ” Troubleshooting
Common Issues
  1. "OpenMM not found" warning

    • This is normal, server will run in mock mode
    • For actual simulations, install OpenMM: conda install -c conda-forge openmm
  2. "command not found" error

    • Check if Python is in PATH
    • Verify project path is correct
    • Try using absolute paths
  3. Permission errors

    • Ensure read/write permissions for project directory
    • Check if task_data directory is writable
Verify Configuration
# Test server startup
python run_openmm_server.py

# Test MCP functionality
python test_mcp_server.py
šŸ¤ Contributing
  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Add tests
  5. Submit a pull request
šŸ†˜ Support

If you encounter any issues:

  1. Run the test script: python test_mcp_server.py
  2. Review the documentation
  3. Check log files (if configured)
  4. Submit an issue on GitHub
šŸ“„ License

This project is licensed under the GNU General Public License v3.0.


Happy simulating! šŸŽ‰