Thingadera MCP
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Thingadera MCP
The right words for UI patterns, inside your AI tool.
Most back-and-forth with an AI builder is fixing things nobody named. Ask for "a loading state" and you get a spinner. Ask for "a skeleton screen shaped like the result cards" and you get it right the first time. This server gives your AI the names, the rules for when each pattern fits, and a way to do that prep before it writes any UI.
It's the same library and logic as thingadera-f23e191e.base44.app: the full pattern library, the clashes between them, platform and audience rules, and the prep.
Tools
Tool | What it does |
| "panel that slides up from the bottom" → Bottom sheet, a prompt line to build it, what it's confused with, what it clashes with, when it's overused |
|
|
| A few answers (what, platform, setting, tone, big decisions) → one precise prompt, with what's still undecided |
| The valid answers for |
| "make it pop and modern" → why each phrase fails and specific words to use instead |
| The whole library by category |
No account, no API key, nothing sent anywhere. It runs on your machine.
Related MCP server: Better Design
Install
Requires Node 18 or newer.
Claude Code
claude mcp add thingadera -- npx -y thingadera-mcpClaude Desktop, Cursor, Windsurf, and others — add this to the MCP config:
{
"mcpServers": {
"thingadera": { "command": "npx", "args": ["-y", "thingadera-mcp"] }
}
}Get the most out of it
AI tools decide on their own when to call a tool. To make sure yours does the prep first, add one line to your project rules (CLAUDE.md, .cursorrules, or similar):
Before building or changing UI, use the thingadera tools: name each pattern with find_ui_pattern, check the combination, and build from build_ui_prompt.Does it help?
We tested it blind. Four one-line UI requests were each built twice by the same AI model, once with no tools and once with Thingadera plus the rules line above, and a separate AI judged the drafts without knowing which was which. With Thingadera, three of four drafts came out better: the right overlay for each platform, real buttons and accessible controls, fewer emoji standing in for icons, and data that added up. The one loss (content hidden until you scroll) led to a fix in the build notes, and the rebuilt draft passed the automated checks.
Without the rules line, the model never called the tools. Add it.
Small sample, and AI judging AI. Treat it as a signal, not proof.
Examples
"Add a filter panel to my recipe results page, on phone and desktop. Make it pop."
With Thingadera the AI can look up that a filter panel on phones is usually a bottom sheet and on desktop a drawer, check that a bottom sheet clashes with a floating action button, and replace "make it pop" with something specific, like one accent color used only on the main button.
License
MIT. Made by Paavan Patel.
This server cannot be deployed
Maintenance
Related MCP Connectors
Checks UI code for AI-default design patterns and gives the fix. By Precious Studio.
Live React design-system APIs, patterns, and code validation so AI agents build real UI, not slop.
UI design from prompts, screenshots, and URLs for AI coding agents and theme tokens.
Serves your design system and coding standards to coding agents, so they stop guessing.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceProvides design systems, UI prompts, and layout variation guidance to AI coding tools for generating better user interfaces.394 npm2,189MIT
- AlicenseAqualityBmaintenanceA design harness for AI coding agents. Better Design gives an agent design systems, UI and UX principles, icons and UI review: it finds or creates a design system that fits the product and installs its components, explains how sign-up, forms and onboarding should work, and reviews finished screens for readability, accessibility and unclear copy.48554MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI coding assistants to generate bespoke design systems by synthesizing OKLCH color palettes, chamfer highlights and spring physics, teaching layout composition grammar, and returning micro-interaction primitives and component blueprints. Also audits JSX/TSX/HTML through a senior design director's lens to score and critique UI quality.13 npm1MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI coding agents to query any DESIGN.md design system and receive short, targeted answers with exact design tokens, existing component classes, markup examples, and rules. It also catches drift by flagging made-up colors and pixel values and suggesting the nearest token.1Apache 2.0