MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Blender add-on to design, simulate, align & render optical setups — live beam tracing, kinematic-mount auto-alignment, polarization (Jones/Stokes), interference fringes, Gaussian beams, wavelength optics, and a real-vendor component library. Driveable from the UI or a headless optics_api (AI/MCP-friendly).
pypi GPL-3.0 ★ 37 -
MCP Server for Optics Design System
npm MIT ★ 1 -
OptiForge (光匠) — AI-native optical design & lens engineering platform over the Zemax/OpticStudio ZOS-API. MCP server: 5-stage design workflow, executable quality gates, aberration & tolerance analysis, CAD/ISO 10110 deliverables.
MIT ★ 5 -
MCP-CodeVgithub.com/eddie-rembrandt/MCP-CodeVupdated this year
MCP Server for Code V scripts -- Best for Optical Lens Design
MIT ★ 6 -
MCP server that lets Claude design and optimize optical thin-film coatings with OpenFilters
pypi GPL-2.0 -
Talk to Zemax OpticStudio in plain English — a non-invasive MCP bridge that lets Claude Code drive your optical designs from intent to result.
★ 19 -
Experimental MCP server for driving Zemax OpticStudio from a coding agent (code-only; vendor data built locally)
pypi Apache-2.0 ★ 19 -
Pixel-perfect optical centering for icons, symbols, and UI glyphs. Deterministic MCP server, Codex AI skill, PNG analysis, and 435 precision tests.
MIT -
An agentic AI workflow for SiN waveguide design that bridges modesolverpy, SAX+JAX, and gdsfactory via FastMCP. It handles eigenmode solving and inverse design for GDSII mask output, powered by AWS Bedrock AgentCore, Strands SDK, and hybrid S3/DynamoDB storage
MIT ★ 4 -
The open photonics suite: Mie, T-matrix, DDA, FDTD, TMM, RCWA, mode, EME, FDFD, PWE and circuit solvers on CPU and GPU, differentiable, with JSON, CLI and MCP interfaces for AI agents.
MIT ★ 2