mcpField
M
molecular-mcp

molecular-mcp

Local
andylbrummer.github.ioScience & Education2Updated 26w ago
RepositoryVisit website

About molecular-mcp

molecular-mcp is an MCP server for classical molecular dynamics, suited to studying particle systems and their thermodynamic behavior. It offers multiple ensembles, interaction potentials, analysis, and visualization, with optional CUDA acceleration.

Key features

  1. 01Create particle systems
  2. 02Lennard-Jones and Coulomb potentials
  3. 03NVE, NVT, and NPT simulations
  4. 04Radial distribution and mean squared displacement analysis
  5. 05Trajectory rendering and density-field visualization
  6. 06Optional CUDA acceleration

Use cases

  1. 01Simulating Lennard-Jones liquids
  2. 02Analyzing diffusion and mean squared displacement
  3. 03Studying temperature and pressure control
  4. 04Detecting phase transitions and viewing particle trajectories

MCP support

As an MCP server, it exposes tools for particle setup, molecular dynamics simulations, trajectory retrieval, analysis, and visualization to MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "andylbrummer-molecular": {
      "command": "uvx",
      "args": [
        "scicomp-molecular-mcp"
      ]
    }
  }
}
Run commanduvx scicomp-molecular-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypiscicomp-molecular-mcp0.1.6

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

scicomp-molecular-mcp

mcp-name: io.github.andylbrummer/molecular-mcp

MCP server for classical molecular dynamics simulations.

Overview

This server provides tools for molecular dynamics simulations with support for various ensembles and interaction potentials:

  • Particle systems - Create and manage systems of interacting particles
  • Interaction potentials - Lennard-Jones and Coulomb interactions
  • Ensembles - NVE (microcanonical), NVT (canonical), NPT (isothermal-isobaric)
  • Analysis tools - Radial distribution functions, mean squared displacement, phase transitions
  • Visualization - Trajectory rendering and density field visualization
  • GPU acceleration - Optional CUDA acceleration for large systems

Installation & Usage

# Run directly with uvx (no installation required)
uvx scicomp-molecular-mcp

# Or install with pip
pip install scicomp-molecular-mcp

# With GPU support
pip install scicomp-molecular-mcp[gpu]

# Run as command
scicomp-molecular-mcp

Available Tools

System Setup
  • create_particles - Initialize particle system with temperature
  • add_potential - Add Lennard-Jones or Coulomb interactions
Simulation
  • run_md - NVE ensemble (constant energy, volume)
  • run_nvt - NVT ensemble (constant temperature, volume)
  • run_npt - NPT ensemble (constant temperature, pressure)
  • get_trajectory - Retrieve simulation trajectory data
Analysis
  • compute_rdf - Radial distribution function analysis
  • compute_msd - Mean squared displacement
  • analyze_temperature - Thermodynamic properties
  • detect_phase_transition - Identify phase transitions
  • density_field - Compute density field visualization
Visualization
  • render_trajectory - Animate particle trajectories

Configuration

Enable GPU acceleration with environment variable:

MCP_USE_GPU=1 scicomp-molecular-mcp

Examples

🎬 Visual Demos

Spectacular animated demonstrations:

Run demos with Claude:

claude -p "Simulate two galaxies colliding" \
  --allowedTools "mcp__molecular-mcp__*"
📖 Code Examples

Practical tutorials in EXAMPLES.md:

  • Simple liquid simulation with Lennard-Jones
  • Temperature & pressure control
  • Diffusion coefficient calculation
  • Ionic systems with Coulomb interactions
📚 Full Documentation

See the API documentation for complete reference.

Part of Math-Physics-ML MCP System

Part of a comprehensive system for scientific computing. See the documentation for the complete ecosystem.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.