Design Checklists MCP
Provides read-only access to over 100 UX/UI design checklists from Checklist.design, enabling users to search and retrieve design guidance for specific flows and screens. Runs locally without an API key.
README
Checklist.design MCP for Codex
An unofficial, read-only Model Context Protocol server that puts the public Checklist.design catalogue inside Codex and other MCP clients.
I kept opening Checklist.design while building interfaces. It is a useful reference for the small UX details that are easy to miss, so I made the checklists searchable from the place where I was already working.
Ask for a mobile checkout checklist, a subscription-cancellation flow, or guidance for an admin billing screen. The MCP searches 110 UX and UI design checklists and returns the relevant source material with attribution.
The server runs locally. It does not need an API key, call the paid Checklist.design AI checker, upload your designs, or write to any external service.
This repository contains code and synthetic test fixtures only. Checklist.design content is fetched into each user's local cache and remains owned by Checklist Design Pty Ltd. See Third-party content.
Add it to Codex
Run:
codex mcp add design_checklists -- npx -y github:patelchanakya/design-checklists-mcp
Start a new Codex task, then check the connection:
codex mcp list
The first launch downloads the public catalogue to a local cache. Later launches read that cache and start without another network request.
Try asking Codex:
Use design_checklists to find everything relevant to a mobile checkout.
Get the complete flows/canceling-subscription checklist.
Build a review checklist for an admin billing screen with 2FA.
For another MCP client, use npx as the command and these arguments:
{
"command": "npx",
"args": ["-y", "github:patelchanakya/design-checklists-mcp"]
}
What you get
| Tool | What it does |
|---|---|
get_catalog_summary |
Returns source metadata plus checklist, entry, and category totals. |
list_checklists |
Browses and filters checklist summaries. |
search_checklists |
Searches checklist names, descriptions, suggestions, and step text. |
get_checklist |
Returns one complete checklist by category/slug, slug, or UUID. |
build_review_checklist |
Selects a focused set of checklists for a screen, component, or flow. |
All five tools are read-only, idempotent, and non-destructive. Search and review selection are deterministic local keyword matching, not an AI design review.
Run it from source
git clone https://github.com/patelchanakya/design-checklists-mcp.git
cd design-checklists-mcp
npm ci
npm test
codex mcp add design_checklists -- node "$PWD/src/server.mjs"
The repository also includes a project-scoped .codex/config.toml for development.
Local cache
- First launch fetches the public catalogue and validates every checklist before saving it.
- Later launches use the saved cache.
npx -y github:patelchanakya/design-checklists-mcp --syncrefreshes it manually.CHECKLIST_DESIGN_DATA_PATH=/absolute/path/checklists.jsonchanges the cache location.npm run syncwrites an ignored development snapshot todata/checklists.json.
The importer uses bounded concurrency and replaces the cache only after the complete download passes validation. MCP diagnostics go to stderr so stdout stays reserved for protocol messages.
Scope
These checklists are reference material. A returned checklist does not prove accessibility, platform compliance, user validation, or production correctness. The public Checklist.design endpoints can also change; run --sync when you want a fresh local copy.
The MCP does not access the paid Figma or AI analysis service.
Third-party content
The MIT licence covers this project's code, documentation, and synthetic tests. It does not cover Checklist.design names, descriptions, checklist entries, suggestions, images, branding, plugin, or paid services.
Checklist content is retrieved for local use and returned with attribution to Checklist Design. Use remains subject to the Checklist.design Terms of Service.
This project is independent and unofficial. Do not publish generated cache files or represent the project as an official Checklist.design product without explicit written permission.
Contributing
Issues and small pull requests are welcome. See CONTRIBUTING.md for the test and content rules. Security reports belong in a private GitHub security advisory; see SECURITY.md.
The source code is available under the MIT Licence.
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.