Official description7 sourcesMCP servers8d ago

vince-gonzalez/opticquiz-mcp

Two MCP servers for color-vision accessibility: check whether a palette or image is colorblind-safe, and see it recolored as protan/deutan/tritan. Machado 2009 + CIEDE2000, published method. Local stdio.

View on GitHub ↗Direct link · no redirect page

Config template (adjust for your client)

claude mcp add opticquiz-mcp -- npx -y opticquiz-mcp

A pasteable skeleton generated from the repository name. Check the project README for the exact package and arguments.

Star count: 0 ★ · vince-gonzalez/opticquiz-mcp · read from the repository page · (checked 2026-10-16 20:00:20)
Source: collected from the punkpeye/awesome-mcp-servers list · type: MCP server
Harvest history: first seen 2026-10-09 · last seen 2026-10-16 · seen 32× · listed by 7 sources
Score: score 703 · 7 sources · mcp

FAQ (answers come from our records)

How do I install it?

We did not find an install command for this repository (our install coverage is only about 4%). Check its README or releases page.

Who is it for?

We filed it under these tags: MCP 服务. The tags come from the entry itself, not a taxonomy we imposed.

Who maintains it?

repository vince-gonzalez/opticquiz-mcp；first catalogued 2026-10-09；last seen 2026-10-16。There is no official certification or quality rating here — we record sources and dates only.

Third-party quality signals

OpticQuiz MCP servers

以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →

**Two MCP servers that let an assistant check and see color the way a colorblind person does** —
built on a published, open-access color-vision method rather than a rule of thumb.
Both are listed in the official Model Context Protocol registry.
cvdsafe-mcp — check it
| tool | what it does |
| --- | --- |
| checkPalette | Whether a set of colors stays distinguishable under protanopia, deuteranopia and tritanopia — with the conflicting pairs named |
| checkImage | Extracts an image's dominant colors and flags the pairs that collapse, each weighted by how much of the image they cover. PNG + JPEG |
| generateSafePalette | N colorblind-safe colors, seeded with Okabe–Ito. Never returns an unsafe one |
| fixPalette | Repairs a failing palette, staying close to the originals |
| checkContrast | WCAG contrast ratio, AA/AAA |
| simulateColor | One color under a chosen deficiency |
colorblind-mcp — see it
| tool | what it does |
| --- | --- |
| simulateImage | Recolors a PNG/JPEG the way a deficiency renders it, and **returns the image** |
| plate | Generates an Ishihara-style pseudoisochromatic test plate and returns it |
| compareVision | One color under all three deficiencies at once |
| simulateColor | A single color under one deficiency, with severity |
Install
Add to claude_desktop_config.json (Settings → Developer → Edit Config):
Restart, then ask: *"Is this palette colorblind-safe: #d7191c, #1a9641, #2166ac?"* or *"Show me
./dashboard.png the way a deuteranope sees it."* Same config shape works in Cursor and other MCP
clients.
The method
Colors are simulated with the **Machado, Oliveira & Fernandes (2009)** deficiency matrices and
compared with **CIEDE2000**. The method is published open access —
doi.org/10.5281/zenodo.21310578 — and the same engine
ships as installable packages (cvdsafe, cvdsim on PyPI and npm), so any answer these servers
give can be reproduced outside them.
Everything runs locally over stdio. Nothing leaves your machine; images are read from your disk and