Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@xraylarch-mcp Load fe_foil.xdi and show normalized XANES"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP (Model Context Protocol) server that wraps xraylarch for X-ray spectroscopy analysis. Load, process, analyze, and plot XAS/XAFS spectra through Claude Desktop or Claude Code with natural language tool calls. Supports XANES normalization, EXAFS extraction, Fourier transforms, linear combination fitting, PCA, FEFFIT shell fitting, and publication-quality plotting.
pip install xraylarch-mcpRelated MCP server: mhlabs-mcp-tools
Add to your Claude Desktop configuration (claude_desktop_config.json):
{
"mcpServers": {
"xraylarch": {
"command": "python",
"args": ["-m", "xraylarch_mcp"]
}
}
}claude mcp add xraylarch -- python -m xraylarch_mcpAsk Claude:
"Load the spectrum at ~/data/fe_foil.xdi and show me the normalized XANES"
Claude will:
Call larch_load_spectrum to read your data
Call larch_normalize to perform pre-edge subtraction and normalization
Call larch_plot with plot_type="norm" to generate a publication-quality plot
Tool | Description |
| Load a spectrum from file (.xdi, .dat, .csv, .prj, etc.) |
| Read/inspect Athena project files |
| List all loaded spectrum groups |
| Detailed view of a group's arrays and scalars |
| Remove a group to free memory |
Tool | Description |
| Pre-edge subtraction and normalization (wraps |
| EXAFS background removal (AUTOBK algorithm) |
| Forward Fourier transform: chi(k) -> chi(R) |
| Back Fourier transform: chi(R) -> chi(q) |
| Fluorescence self-absorption correction |
| MBACK normalization (alternative for problematic data) |
| Noise estimation in chi(k) and chi(R) |
| Cauchy wavelet transform for simultaneous k- and R-resolution |
| Rebin to standard 3-region XAFS energy grid |
Tool | Description |
| Publication-quality plots (mu, norm, flat, dmude, chi_k, chi_r, chi_q, cauchy_wavelet) |
Tool | Description |
| Smooth arrays with Lorentzian/Gaussian/Voigt kernel |
| Numerical derivative |
| Interpolate onto new energy grid |
| Merge/average multiple spectra |
| Remove glitch points |
Tool | Description |
| Linear combination fitting against standards |
| Principal Component Analysis |
| FEFFIT EXAFS shell fitting |
| Peak fitting (Gaussian, Voigt, etc.) |
Tool | Description |
| Open an interactive HTML page to tune normalization parameters |
| Apply normalization parameters from a saved JSON file |
Ask Claude to interactively normalize your spectrum
An HTML page opens in your browser with Plotly.js plots and sliders
Adjust E0, pre-edge range, post-edge range, and polynomial degree — plots update in real time
Click Save Parameters to download a JSON file, or Copy to Clipboard
Tell Claude to apply the saved parameters
"Load Pdfoil.prj and let me interactively choose the normalization parameters"
Tool | Description |
| Execute arbitrary Python code in the larch session |
The server exposes documentation resources that Claude can read on demand:
larch://docs/xafs — XAFS analysis reference
larch://docs/io — I/O functions reference
larch://docs/fitting — Fitting reference
larch://docs/feff — FEFF interface reference
larch://docs/interactive — Interactive tools reference
larch://docs/examples/xanes — XANES workflow example
larch://docs/examples/exafs — EXAFS workflow example
BSD-3-Clause (matching xraylarch)
This server cannot be deployed
MCP server for AI dialogue using various LLM models via AceDataCloud
Personal assistant MCP server with search, execute, packages, jobs, secrets, and integrations.
This MCP server enables users to perform scientific computations regarding linear algebra and vect…
MCP server for generating rough-draft project plans from natural-language prompts.
