mcpField
W
WunderUI

WunderUI

Local
wunderui.comDeveloper Tools1Updated 4d ago

About WunderUI

WunderUI MCP supplies coding agents with design-system data for building interfaces with the WunderUI library. It provides component signatures, tokens, templates, starter code, and agent instructions through tools and read-only resources.

Key features

  1. 01Browse components by category or plan
  2. 02Get TypeScript props and usage examples
  3. 03Retrieve light and dark design tokens
  4. 04Read design rules and page templates
  5. 05Fetch TSX starters and agent skills
  6. 06Access data through tools or resources

Use cases

  1. 01Build pages using WunderUI components
  2. 02Check component props and import paths
  3. 03Apply the library's tokens and design rules
  4. 04Give an agent task-specific skill instructions

MCP support

The server exposes WunderUI design data through MCP tools and read-only resources. It supports clients using MCP over stdio.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"kl-webmedia-wunderui": {
"command": "npx",
"args": [
"-y",
"wunderui-mcp"
]
}
}
}
Run commandnpx -y wunderui-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmwunderui-mcp1.1.0

Tools

11

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
planenumNoOnly components of this plan. Free = open source under MIT (github.com/wunder-ui/wunderui); pro needs WunderUI Core or Pro.free | pro
querystringNoFree text, matched against name, description and category
categorystringNoOne of: Primitives, Overlays, Charts, Data Display, KPI, Navigation, Forms, AI, Agents, Feedback, Layout, Block Parts

Details

From the project README

WunderUI MCP

An MCP server that gives an AI coding agent the WunderUI design system: design tokens, the component inventory with real prop signatures, page templates and starter snippets. The agent builds with the library instead of reinventing a data grid out of raw divs.

claude mcp add wunderui -- npx -y wunderui-mcp

Works with Claude Code, Cursor, Windsurf, Cline, Codex, VS Code and any other client that speaks MCP over stdio. No key and no account needed.

Tools

ToolWhat the agent gets
list_componentsThe inventory, filterable by category, plan (free or pro) or free text
get_componentExports, the TypeScript prop signature, the import line, an example, the docs URL
get_tokensLight and dark tokens as JSON, a CSS block, or Tailwind @theme mappings
get_design_mdThe full DESIGN.md, or one section (rules, donts, tasks, tokens, inventory, reference, templates, starters)
list_templatesThe full-page templates and what each is built from
get_starterCopy-paste TSX: app shell, dashboard, data grid, AI chat, theming
get_library_infoPackage name, version, install commands, stack, counts, data source
get_instructionsThe short, always-on rules (components, tokens, motion, copy) for CLAUDE.md / AGENTS.md
list_skillsThe WunderUI agent skills, free and Pro
get_skillOne skill's instructions (SKILL.md), so the agent can follow it without installing — Pro skills need WUNDERUI_LICENSE_KEY
get_block_sourceThe React source of a UI block and its shared helpers — needs a Pro key in WUNDERUI_LICENSE_KEY

Every component carries its plan. On the Free plan, an agent should only use components marked free; the others need WunderUI Core or Pro.

Resources

Clients that support MCP resources can attach the design context without a tool call. Read-only, and the same data as the tools above:

Resource URIWhat it holds
wunderui://design-mdThe full DESIGN.md (markdown)
wunderui://design-jsonThe machine-readable design data (tokens, inventory, templates, skills)
wunderui://tokensLight and dark token values
wunderui://instructionsThe short rules for CLAUDE.md / AGENTS.md
wunderui://componentsThe component inventory: name, category, plan, description
wunderui://components/{slug}One component in full (one resource per component, listed by the server)

The tools stay for clients without resource support.

Install

Claude Code

claude mcp add wunderui -- npx -y wunderui-mcp

Cursor: .cursor/mcp.json

{
  "mcpServers": {
    "wunderui": { "command": "npx", "args": ["-y", "wunderui-mcp"] }
  }
}

Windsurf, Cline, Codex, VS Code: the same shape, in that editor's MCP config.

Installing WunderUI itself

The server describes the library; it does not ship it. @wunderui/react on npm is WunderUI Free (the free components only). Core and Pro licence holders install the full library from the wunderui-core download (the wunderui-setup agent skill does it for you), and the server tells agents exactly that.

Where the data comes from

data/design.json and data/DESIGN.md are generated from the WunderUI source with every release: tokens from the stylesheet, props from the built type definitions, names and descriptions from the docs.

The server starts with the bundled copy and answers immediately. In the background it fetches the current design.json and DESIGN.md from wunderui.com and switches to them when they are at least as new, so agents see new components without a package update. get_library_info reports which source is in use.

VariableEffect
WUNDERUI_OFFLINE=1never touch the network, use the bundled copy
WUNDERUI_SITE=<url>fetch the live data from another origin
WUNDERUI_LICENSE_KEY=<key>your WunderUI Pro key — unlocks Pro skills (get_skill) and block source (get_block_source); sent only to wunderui.com

Without MCP

The same data is served as static files for agents and editors that don't speak MCP:

  • https://wunderui.com/DESIGN.md: paste at the top of a prompt
  • https://wunderui.com/llms.txt: the llms.txt convention
  • https://wunderui.com/design.json: the same structured index

Verify

npm install
npm run smoke

Starts the server with a real MCP client and calls every tool once.

Licence

The server code is MIT. The WunderUI components it describes are licensed per plan, see wunderui.com/pricing.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.