build_structure_workflowLABSCO SUMMARY
Simulation workflows an agent can call, without a scripts directory.
Every result is a file with a download URL rather than a blob in the chat, which is what makes a trajectory usable at all. For interfaces, doped structures or custom slabs the builder stops short — generate those with ASE or pymatgen yourself and hand them back through write_structure_workflow.
What it is
A FastMCP server over ASE, pymatgen and machine-learned interatomic potentials. Results are written as files and returned as download URLs, so binary output never lands in the conversation.
What you get
- Structures built as bulk, surface, molecule, supercell, amorphous, liquid, bicrystal or polycrystal — build_structure_workflow
- Geometry optimisation with convergence, step and constraint controls — optimize_structure_workflow
- Energy, forces and stress at a fixed geometry, without modifying the structure — single_point_workflow
- Molecular dynamics under Velocity Verlet, Langevin or Berendsen thermostats — run_md_workflow
- Analysis: RDF and coordination statistics, MSD and thermodynamic trends, VACF and Green-Kubo diffusion — analyze_structure_workflow, analyze_trajectory_workflow, autocorrelation_workflow
- A geometry persisted for a later step, including structures built elsewhere — write_structure_workflow
- Artifacts downloadable as xyz, extxyz, cif, traj, png, svg, csv and dat
Requirements
Python 3.11 or newer. Install with pip install -r requirements.txt, then serve Streamable HTTP with uvicorn mcp_atomictoolkit.http_app:app, or run python -m mcp_atomictoolkit.mcp_server for stdio. The default potential is kim; nequix and orb are also supported. A Dockerfile and a render.yaml are included.
Setup effort
Build from source
USE CASES
01
Relaxing a structure you just built
Build the bulk or surface, then optimise it with your own fmax and step limits, and keep the relaxed geometry as a file for whatever comes next.
02
Running MD and reading the trajectory back
Pick the ensemble and thermostat, tune temperature and friction, then get MSD and thermodynamic trends out of the trajectory rather than the raw frames.
03
Getting a diffusion coefficient
The autocorrelation workflow computes VACF and the Green-Kubo diffusion estimate from a trajectory, and returns the plot alongside the numbers.
04
Checking energy and forces without changing anything
A single-point calculation returns energy, forces and — for periodic systems — stress, leaving the structure exactly as it was.
8 tools
Listed in project docs. Your client may show a different list.
analyze_structure_workflowwrite_structure_workflowoptimize_structure_workflowsingle_point_workflowrun_md_workflowanalyze_trajectory_workflowautocorrelation_workflowBEFORE YOU INSTALL
What to know first
Tools you get
8 tools named in the project's documentation. Legacy aliases also answer, so a live server responds to more names than these 8.
Requires
Python 3.11+
INSTALLATION
Connect your client
Server setup
TERMINAL
git clone https://github.com/XirtamEsrevni/mcp-atomictoolkit
cd mcp-atomictoolkitInstall
TERMINAL
pip install -r requirements.txtSTDIO mode (for desktop MCP clients)
TERMINAL
python -m mcp_atomictoolkit.mcp_serverThe README prints no client configuration. For a desktop MCP client it names STDIO mode, python -m mcp_atomictoolkit.mcp_server run from the cloned folder — add that as the server's launch command in your client's own format. The HTTP alternative, uvicorn mcp_atomictoolkit.http_app:app --host 0.0.0.0 --port 10000, serves MCP at http://localhost:10000/.
