Prototype · Preview: every server in the official registry, synced every 30 minutes. Reviews and accounts come in a later step.
PopNx MCPMCP servers for people who use AI · explained in plain words

labsUI

by kznlabsversion 0.2.0i★ –iRuns on your computer
Registry nameio.github.kznlabs/labsui

Install

Overview

Description from the maker (original English)

Search, add, diff and update labsUI React components in your project.

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

  • Connection: Runs on your computer
  • Transport: stdio
  • Category: Search & AI memory

Install

Pick the AI app you use, then copy the settings.

Before you install

  • Basic checks: 1 of 1 passed
  • Runs on your computer with your user’s permissions (files, network, apps).
  • The registry lists no key to fill in.

You need

  • npmNode.js installed (for the npx command)

Which app do you use?

Pick your app above. We remember it, so next time the button says “Install in …”.

Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json

{
  "mcpServers": {
    "labsui": {
      "command": "npx",
      "args": [
        "-y",
        "@kznlabs/labsui",
        "mcp"
      ]
    }
  }
}

Run this in your terminal

claude mcp add labsui -- npx -y @kznlabs/labsui mcp

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "labsui": {
      "command": "npx",
      "args": [
        "-y",
        "@kznlabs/labsui",
        "mcp"
      ]
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "labsui": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@kznlabs/labsui",
        "mcp"
      ]
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.

Your choice stays on this device in a cookie; no account needed.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026

  • ✓ Pass

    Maker matches the repo

    The registry name was verified with the GitHub account kznlabs, which owns the repo

  • … Not checked yet

    Still maintained

    We have not read this repo from GitHub yet

  • … Not checked yet

    Has a licence

    We have not read this repo from GitHub yet

  • – Not applicable

    Endpoint responds

    This one runs on your computer; there is no internet endpoint

  • – Not applicable

    Sign-in with OAuth

    Runs on your computer and uses local settings instead

  • … Not checked yet

    No hidden instructions in tool descriptions

    Runs on your computer; we can only read tool lists from internet endpoints

Compared with others in Search & AI memoryi

  • More stars than 0% of the other 7275 servers in this category
  • Published to the registry more recently than 95% of the other 7275 servers in this category
  • Basic checks equal to or better than 100% of the other 7275 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is labsUI safe?

It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

The registry does not list a required key, though some servers ask you to sign in on first use.

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed –, and the latest version (0.2.0) reached the registry 2 days ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.

What can I use instead?

In the same category: Context7, Codebase Memory, Exa

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Context7

by upstash

Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.

Computer or cloud★ 64,224MITUpdated yesterday
Install

Codebase Memory

by DeusData

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

Runs on your computer★ 48,148MITUpdated 21 days ago
Install

Exa

by exa-labs

Connect AI agents to Exa for web search, content fetching, and multi-step research.

Runs in the cloud★ 5,213MITUpdated last month
Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

labsui

Add labsUI components to your project: clean React primitives with one smooth spring for every motion. Components are copied into your codebase, so you own and edit them.

Requires React 19, Tailwind CSS v4 and a path alias ("paths": { "@/*": ["./src/*"] } in tsconfig.json). The CLI runs on Node.js 22 or newer, or Deno. It has no dependencies and works offline.

Usage

npx @kznlabs/labsui init                # once: styles, theme, utils, motion provider

npx @kznlabs/labsui add button tabs # components plus everything they import npx @kznlabs/labsui search date range # find by name, export or intent npx @kznlabs/labsui view dialog # props, examples, what it installs npx @kznlabs/labsui update # newer components, keeping your edits npx @kznlabs/labsui doctor # check the setup

Any runner works: bunx @kznlabs/labsui add button, pnpm dlx @kznlabs/labsui …, yarn dlx @kznlabs/labsui …, or from JSR with deno run -A jsr:@kznlabs/labsui add button. npm dependencies install with whatever package manager your lockfile shows.

The component registry ships inside the package: no network needed beyond installing npm dependencies, and each labsui version installs the same component code. npx @kznlabs/labsui@latest add … gets the newest components.

Global install

To type labsui instead of npx @kznlabs/labsui in every project:

npm install -g @kznlabs/labsui    # or: bun add -g @kznlabs/labsui

deno install -gA -n labsui jsr:@kznlabs/labsui

A global install pins its components to that version, the same way the registry ships inside each release. Update it when you want newer ones (npm install -g @kznlabs/labsui@latest); npx @kznlabs/labsui@latest always gets them.

Commands

init
  • Writes styles/labsui.css (tokens, accent presets, animations) and imports it right after @import "tailwindcss" in your stylesheet.
  • Adds lib/utils, lib/theme and components/motion-provider, and installs motion, clsx and tailwind-merge.
  • Saves labsui.json with the registry URL, your alias and its folder.
  • Prints the lines your root layout needs (theme script, MotionProvider).

Run it again any time: existing files are kept.

add

Resolves dependencies through the registry (data-table brings table, checkbox, pagination, …), writes each file under your alias folder and installs the npm packages it imports. Existing files are kept unless you pass --overwrite; a kept dependency whose code differs from this version is named, with the labsui update that brings it level, since the new item may need it. If your alias isn't @/, imports are rewritten to match. Components that live once in the root layout (toast, confirm) print the line to add there. A mistyped name gets a suggestion: buton suggests button.

list and search

list shows everything: components, blocks, hooks (use-disclosure, use-hotkey, …) and helpers (utils, theme, …). Hooks and helpers come along with the components that import them; add one by name to use it on its own.

search ranks by name first, then by what an item exports, then by its description, and every word must match:

labsui search useModal         # finds dialog

labsui search toast promise # finds toast labsui search --kind hook # every hook

view

Everything you need before writing code with an item, without leaving the terminal:

  • Exact props and types of each export, read from the component source.
  • A usage line and the full examples from the docs.
  • What it brings along and which npm packages it installs.
  • What to mount in the root layout, if anything.

Imports in the examples use your alias. --source adds the files themselves.

update and diff

Components are yours to edit, so an update must not silently undo your changes. labsui.json records which labsui version wrote each item, and labsui update (or labsui update dialog) uses that version as the base:

  • Files you never edited are replaced.
  • Edited files are merged three ways: your changes and this version's changes both land.
  • Where both changed the same lines, the file gets <<<<<<< yours / >>>>>>> labsui markers and update lists it. labsui doctor fails until they are resolved.
  • New dependencies of updated items are added.

The base comes from JSR, which keeps every release's files. Offline, with a hosted registry, or for items installed before versions were recorded, edited files are left as they are. labsui diff lists installed items that differ from this version and, from the same base, whose change each file is: only labsUI's (update replaces it), only yours (update keeps it) or both (update merges). It also marks files that differ only in blank lines or indentation. labsui diff dialog prints the patch from this version's file to yours, or says dialog isn't installed.

doctor

Checks the setup and prints a fix for each problem: React 19 and Tailwind v4, the path alias and labsui.json, the stylesheet import, MotionProvider and the theme script, and mounted when installed, missing npm packages, and files your installed components import but the project lacks. It also lists installed items that differ from this version, your edits or an older install. Exits with 1 when something is broken, so it can run in CI.

It reads your code, not a framework's conventions: it works the same in any React app.

Coding agents

MCP server

labsui mcp serves the same commands to any agent that speaks the Model Context Protocol, over stdio. Register it with your agent:

{

"mcpServers": { "labsui": { "command": "npx", "args": ["-y", "@kznlabs/labsui", "mcp"] } } }

It works in the folder your agent shares as its workspace (MCP roots), or the one it starts the server in. If your agent starts servers elsewhere and shares no workspace, add "--cwd", "/path/to/app" after "mcp"; --cwd always wins. Claude Desktop is one of those: it shares no workspace, so give it --cwd. On Windows, Desktop starts npx through cmd:

{

"mcpServers": { "labsui": { "command": "cmd", "args": ["/c", "npx", "-y", "@kznlabs/labsui", "mcp", "--cwd", "C:\\path\\to\\app"] } } }

ToolDoes
searchfind items by name, export or intent
viewexact props, examples, dependencies, optional source
addinstall items into the project (never overwrites a file)
initone-time setup; returns the root layout code
diffpatches from this version to your edited files
updateupdate items, merging your edits three ways
doctorthe setup checks, each problem with its fix

On connect, the server also sends the labsUI coding rules (imports, tokens, motion, mounting), so the agent writes code the way the library expects. It runs in the folder the agent starts it in and writes only inside that project.

Without MCP
  • labsui rules prints the same coding rules as Markdown. Append them to the file your agent reads: labsui rules >> AGENTS.md.
  • --json on any command prints one JSON document on stdout; npm output goes to stderr. Errors are { "error": "…" } with exit code 1.

Options

FlagMeaning
--jsonmachine-readable output on stdout
--kind search only: component, block, hook, helper or setup
--sourceview only: include the source files
--overwritereplace files that already exist
--dry-runshow what would change, write nothing
--no-installprint the install command instead of running it
--registry another registry (also LABSUI_REGISTRY, or registry in config)
--cwd run against another project folder

License

MIT. Every component is original, hand-made labsUI code.

Ask PopNx