MCP Atomictoolkit MCP Server

A FastMCP server for **atomistic modeling workflows** powered by ASE, pymatgen, and modern ML interatomic potentials.

Local serverstdioPython

What is the MCP Atomictoolkit MCP server?

A FastMCP server for atomistic modeling workflows powered by ASE, pymatgen, and modern ML interatomic potentials. Exposed over MCP by the mcp atomictoolkit mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

Its toolset

Everything the assistant can do here goes through one of these:

  • ready-to — call MCP tools** for common simulation tasks,
  • file — first outputs** that are easy to inspect/reuse,
  • deployment — ready HTTP app** with health and server-card endpoints
  • MCP — native workflows** via FastMCP tools
  • Registry — friendly endpoints** (/healthz, server card, Streamable HTTP root)
  • build_structure_workflow — analyze_structure_workflow
  • write_structure_workflow — optimize_structure_workflow
  • single_point_workflow — run_md_workflow
  • analyze_trajectory_workflow — autocorrelation_workflow
  • surface — indices, layers, vacuum
  • supercell — size, base_structure_type, base_crystal_system, base_lattice_constant, base_kwargs
  • bicrystal — grain_size, interface_axis, rotation_angle, rotation_axis, interface_gap

Adding it to your client

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

When to reach for it

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. MCP Atomictoolkit's toolset — ready-to, file, deployment and 11 more — is a fair guide to whether it matches your workflow. It is maintained by xirtamesrevni; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against MCP Atomictoolkit's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch MCP Atomictoolkit.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the mcp atomictoolkit mcp server does with a few real requests.

Available tools

ToolWhat it does
ready-tocall MCP tools** for common simulation tasks,
filefirst outputs** that are easy to inspect/reuse,
deploymentready HTTP app** with health and server-card endpoints.
MCPnative workflows** via FastMCP tools
Registryfriendly endpoints** (/healthz, server card, Streamable HTTP root)
build_structure_workflowanalyze_structure_workflow
write_structure_workflowoptimize_structure_workflow
single_point_workflowrun_md_workflow
analyze_trajectory_workflowautocorrelation_workflow
surfaceindices, layers, vacuum
supercellsize, base_structure_type, base_crystal_system, base_lattice_constant, base_kwargs
bicrystalgrain_size, interface_axis, rotation_angle, rotation_axis, interface_gap
polycrystalnum_grains, grain_size, rotation_angle
mcp_server.pyPreserve http_app.py compatibility behavior unless intentionally changing deployment contracts.

Example prompts to try

  • Use MCP Atomictoolkit to ready-to.
  • Use MCP Atomictoolkit to file.
  • Use MCP Atomictoolkit to deployment.

Frequently asked questions

It connects MCP Atomictoolkit to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (ready-to, file, deployment, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with MCP Atomictoolkit directly.