Skip to main content

MCP Server

Point any MCP client at the NachUI server and your agent can list the catalog, read the real source of a component and search the docs before it writes a line.

An assistant that guesses what a component looks like will invent one that does not exist. The MCP server closes that gap: it exposes the same registry the docs and the CLI use, so the agent reads the actual file before it writes anything.
Nothing is installed and nothing runs in the background. It is four read-only tools over the registry.

Setup

Add the server to your MCP client. For Claude Code, Cursor and most others, that is an entry in the client's mcp.json:
mcp.json
1{
2 "mcpServers": {
3 "nachui": {
4 "command": "npx",
5 "args": ["-y", "nachui-mcp"]
6 }
7 }
8}
The package is fetched on first use and cached by npx. Restart the client and the tools show up.

Tools

ToolWhat it returns
list_componentsEvery component in the registry, with the npm packages it needs.
get_componentThe source of one component, the same file you would copy by hand.
search_docsSemantic search across the documentation, in English or Spanish.
get_docA full docs page as markdown, for when a snippet is not enough.
A typical turn: the agent calls list_components to see what exists, search_docs to find how a pattern is meant to be used, and get_component to pull the file it is about to adapt. You get the same copy and paste as always, done by the agent, from the real source.

Slugs

Components are addressed by family and name, the same slugs the CLI takes: ui/button, layout/stack, ai/prompt-input, hybrids/chat, icons/search. A bare name like button works when it is unique across families.
Three ways to hand an agent the library
llms.txt is the documentation as plain text, for any model that can fetch a URL. Skills are the conventions, installed into your repo. The MCP server is the live registry, for agents that can call tools. They stack.
  • CLI for the commands the tools mirror.
  • llms.txt for the documentation feed.
  • Skills for the conventions an assistant should follow.
Found something to improve?

Notice a bug, typo, or missing detail on this page? Help us make the documentation better by opening a GitHub issue.

Create an Issue