Lumerical MCP Server

Lumerical MCP Server

Enables natural-language-driven automation of Ansys Lumerical photonic simulations (FDTD, MODE, DEVICE, INTERCONNECT) with 40+ tools for geometry, materials, sources, monitors, solvers, results, optimization, and documentation.

Category
Visit Server

README

Lumerical MCP Server & Skill

Complete MCP (Model Context Protocol) server and Claude Code Skill for Ansys Lumerical photonic simulation tools — FDTD, MODE, DEVICE, and INTERCONNECT.

What This Provides

  • MCP Server with 40+ structured tools covering the full Lumerical workflow
  • 480+ script commands accessible via lumerical_eval and lumerical_call
  • Claude Code Skill for natural-language-driven simulation automation
  • Documentation search across all Lumerical scripting commands

Capabilities

Domain Coverage
Session Management Open/close/list sessions for FDTD, MODE, DEVICE, INTERCONNECT
Script Execution Execute arbitrary LSF, get/set variables, call any command
Simulation Control Run, load, save, reset, layout mode
Geometry Add rect/sphere/circle/polygon/waveguide + select/copy/move/rotate/delete
Materials Add/modify/get materials, import nk data, query refractive index, thin-film T/R
Sources Dipole, mode, gaussian, plane wave, TFSF, imported
Monitors Power, profile, index, time, movie, field, absorption, mode expansion, bandstructure
Solvers FDTD, FDE, EME, varFDTD, DGTD, Charge, Heat, FEEM
Boundaries PML, Periodic, PEC, PMC, Absorbing
Results Get result/data, field extraction, far-field projection, transmission spectra, CSV export
Optimization Parameter sweeps, adjoint inverse design, parallel job execution
Documentation List/search/help for 480+ commands, categorized browsing, example discovery

Quick Install

cd D:\ENV\claude\Lumerical_MCP

# Check your Lumerical installation
python install.py --check

# Install both MCP server config and Skill
python install.py

Manual MCP Configuration

Add to ~/.claude/mcp.json:

{
  "mcpServers": {
    "lumerical": {
      "command": "python",
      "args": ["-m", "mcp_server.server"],
      "cwd": "D:\\ENV\\claude\\Lumerical_MCP",
      "description": "Lumerical MCP - FDTD, MODE, DEVICE, INTERCONNECT"
    }
  }
}

Environment Setup

# Required: Point to your Lumerical installation
set LUMERICAL_HOME=D:\ENV\Lumerical\v202

# Install Python dependencies
pip install mcp numpy

Usage

In Claude Code, type /lumerical to invoke the Skill, or use MCP tools directly:

lumerical_open("fdtd")  →  {"session_id": "lum_1", "product": "fdtd"}
lumerical_eval("lum_1", "addfdtd;\nset('dimension',2);\nset('x span',2e-6);\nrun;")
lumerical_close("lum_1")

Project Structure

Lumerical_MCP/
├── mcp_server/
│   ├── server.py              # Main MCP server entry point (FastMCP)
│   ├── session_manager.py     # Session lifecycle (open/close/eval/var)
│   ├── command_docs.py        # Load & query 480+ command docs
│   └── tools/
│       ├── session.py         # Session management (5 tools)
│       ├── script.py          # Script execution (4 tools)
│       ├── simulation.py      # Simulation lifecycle (6 tools)
│       ├── geometry.py        # Geometry & objects (10 tools)
│       ├── material.py        # Materials (6 tools)
│       ├── source_monitor.py  # Sources & monitors (4 tools)
│       ├── solver.py          # Solver config (4 tools)
│       ├── results.py         # Results & analysis (6 tools)
│       ├── optimization.py    # Sweeps & optimization (6 tools)
│       └── docs.py            # Documentation & discovery (7 tools)
├── skill/
│   └── lumerical.md           # Claude Code Skill definition
├── lumerical-docs/            # Local documentation repository (727 cmd docs)
├── install.py                 # One-step installer
├── pyproject.toml
├── README.md
└── DESIGN.md                  # Architecture design document

Requirements

  • Python 3.10+ with mcp and numpy
  • Ansys Lumerical v202 (or later) installed locally
  • Lumerical GUI license
  • Windows (primary; Linux/macOS supported via lumapi)

License

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured