PyLumerical MCP Server
PyLumerical MCP Server provides a Model Context Protocol (MCP) server that enables AI assistants to interact with Ansys Lumerical (FDTD, MODE, DEVICE, INTERCONNECT) through PyLumerical. This server enables natural language interaction with Lumerical for photonics and electromagnetic simulation workflows.
Overview
Key features:
- Multi-session management: Open, list, and close multiple concurrent Lumerical sessions (FDTD, MODE, DEVICE, INTERCONNECT) under user-chosen names.
- Persistent Python execution: Run arbitrary Python and PyLumerical code against live Lumerical handles, with state preserved across tool calls.
- Workflow guidance: Access context and best practices for Lumerical simulations.
- Cross platform support: Enable Windows and Linux support with headless CAD.
Prerequisites
- Python 3.11, 3.12, 3.13, or 3.14
- Ansys Lumerical installation
- Ansys Lumerical license
Installation
For users
Install the latest release with:
pip install ansys-lumerical-mcp
Or run directly without installing using uvx:
uvx --from git+https://github.com/ansys/pylumerical-mcp ansys-lumerical-mcp
For developers
Install
# Clone the repository
git clone https://github.com/ansys/pylumerical-mcp.git
cd pylumerical-mcp
# Create virtual environment
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate or .venv\Scripts\Activate.ps1
pip install uv
# Install dependencies
uv sync
# Run
uv run ansys-lumerical-mcp
Quick start with VS Code or Cursor
If you're using the devopment container:
{
"servers": {
"pylumerical-mcp": {
"type": "stdio",
"command": "/workspaces/pylumerical-mcp/.venv/bin/ansys-lumerical-mcp",
"args": []
}
},
"inputs": []
}
Usage
For step-by-step setup instructions for VS Code, Claude Code, Claude Desktop, Cursor, and other MCP-compatible clients, follow your client's documentation.
License
This project is licensed under the Apache 2.0 license agreement. See the LICENSE file for details.
Resources
- PyLumerical-MCP documentation
- PyLumerical documentation
- Model Context Protocol
- FastMCP documentation
- Ansys Lumerical
- Repository's Issues page
- Repository's Discussions page
For general PyAnsys questions, email pyansys.core@ansys.com.
Metadata
Release files for ansys-lumerical-mcp 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| ansys_lumerical_mcp-0.1.0.tar.gz | 88.8 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| ansys_lumerical_mcp-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 196.9 kB
Release files / ansys_lumerical_mcp-0.1.0.tar.gz
| Download URL | ansys_lumerical_mcp-0.1.0.tar.gz |
|---|---|
| Size | 88.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
5350deea880c8ee130b9e89697989c63240bf3cd007796497e1969fe14bbb71c
|
|
BLAKE2b-256 checksum How to use checksums |
34a0bb5a455da88473360b26a13123483a7fb65b03f4c8b7dfbf04bde9e9e254
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.13
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 1, 2026.
Transparency logRelease files / ansys_lumerical_mcp-0.1.0-py3-none-any.whl
| Download URL | ansys_lumerical_mcp-0.1.0-py3-none-any.whl |
|---|---|
| Size | 108.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
33a95d7d0952541c3f020e30ac2df26033029de784c86698b365f65b95c7c782
|
|
BLAKE2b-256 checksum How to use checksums |
03c5bbc6d32fe03e96e0b82d5250c698a47e3feffb82aead510fe1209ef9c2be
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.13
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 1, 2026.
Transparency log