Access
Free. No account, no API key, no authentication — paste the URL and it works.
Ask your AI assistant what any UI element is called.
CatchUI's curated pattern catalog speaks the Model Context Protocol. Add one URL to Claude, ChatGPT, Cursor, or any MCP client, and your assistant answers "what is this element called" from 50 curated UI patterns — in English and Chinese, citing canonical teaching cards.
https://catchui.com/api/mcp
At a glance
Transport
Streamable HTTP (stateless JSON-RPC). Works with MCP clients that support Streamable HTTP.
Data
Read-only lookups against the public curated catalog. No user data is touched.
Languages
Queries and answers work in English and Simplified Chinese, including real search phrasings.
Connect your client
Claude Code
Run once in your terminal:
claude mcp add --transport http catchui https://catchui.com/api/mcpclaude.ai / Claude Desktop
Settings → Connectors → Add custom connector → paste https://catchui.com/api/mcp. No authorization step appears because none is needed.
ChatGPT
Settings → Apps & Connectors → enable Developer mode → Create: server URL https://catchui.com/api/mcp, authentication "None".
Cursor and other clients
Any client accepting a Streamable HTTP URL works. Cursor's ~/.cursor/mcp.json:
{ "mcpServers": { "catchui": {
"url": "https://catchui.com/api/mcp" } } }Six tools, one job: naming UI
search_ui_patterns
Turn a plain-language description or question — "the bar at the bottom of an app", 「三条横线的图标叫什么」 — into pattern names, definitions, matching Q&A, and catalog links.
get_ui_pattern
The full bilingual teaching entry for one pattern id: definition, pronunciation, aliases in both languages, common questions, and related patterns.
list_ui_patterns
Browse all 50 patterns grouped by family — navigation, input, action, overlay, feedback, content, data and system.
compare_ui_patterns
How two to four look-alikes differ — modal vs popover vs bottom sheet, tabs vs segmented control, Dynamic Island vs notch — side by side, with the catalog's written comparison.
get_ui_component_names
What a pattern is called in SwiftUI, UIKit, Jetpack Compose, Android Views, Flutter and HTML — or from a component like UISegmentedControl back to its equivalents elsewhere.
get_implementation_prompt
Ready-to-use build instructions for one to six patterns — placement, states and accessibility — in English or Chinese, for Claude Code, Cursor or any AI coding tool.
Try asking
- "What is the bar at the bottom of an app called?"
- 「App 底部的导航栏叫什么？」
- "What's the difference between a toast and a modal?"
- "List every navigation pattern in the CatchUI catalog."
- "Modal, popover or bottom sheet — which should this share menu be?"
- "What is UISegmentedControl called in Flutter?"
- "Give me build instructions for a search field with filter chips and pagination."
What it deliberately does not do
Screenshot recognition is not exposed over MCP — it runs in the web app at catchui.com. Multimodal assistants can still look at your screenshot themselves, describe an element in words, and search the catalog for its proper name.
Frequently asked questions
What is the CatchUI MCP server?
A public Model Context Protocol endpoint at https://catchui.com/api/mcp. Once added to an MCP client such as Claude, ChatGPT, or Cursor, the assistant can search CatchUI's curated catalog of 50 UI patterns and answer what an interface element is called, with definitions and canonical links.
Is the CatchUI MCP server free?
Yes. The catalog tools are free, require no account, no API key, and no authentication. Screenshot scanning is a separate feature of the web app and is not part of the MCP server.
Which apps can connect to it?
Any Model Context Protocol client that supports the Streamable HTTP transport: Claude Code, claude.ai and Claude Desktop custom connectors, ChatGPT developer-mode connectors, Cursor, and others.
What tools does it expose?
Six read-only tools: search_ui_patterns finds pattern names from plain-language descriptions or questions in English or Chinese; get_ui_pattern returns the full bilingual entry for one pattern; list_ui_patterns browses the catalog by family; compare_ui_patterns explains how two to four patterns differ; get_ui_component_names gives a pattern's component names in SwiftUI, UIKit, Jetpack Compose, Android Views, Flutter and HTML, or works back from a component such as UISegmentedControl; get_implementation_prompt returns ready-to-use build instructions for an AI coding tool, in English or Chinese.
Can it analyze screenshots over MCP?
No. Screenshot recognition runs in the CatchUI web app at catchui.com. Multimodal assistants can still look at a screenshot themselves, describe an element in words, and use search_ui_patterns to find its proper name.
Does it access my data?
No. Every tool is a read-only lookup against the public curated catalog. The server requires no sign-in and touches no user accounts, libraries, or uploads.
Operator and contact
CatchUI is operated from Hong Kong. Questions about the MCP server can be sent to support@catchui.com.
Facts on this page last verified: 2026-08-24.