# Jpisnice/shadcn-ui-mcp-server

A mcp server to allow LLMS gain context about shadcn ui component structure,usage and installation,compaitable with react,svelte 5,vue & React Native

Repository: https://github.com/Jpisnice/shadcn-ui-mcp-server
Canonical: https://ross.abutalabs.com/products/shadcn-ui-mcp-server
Language: TypeScript
License: MIT
License Family: permissive
Topics: ai, mcp, modelcontextprotocol, ts, typescript, shadcn-ui, ui, webdev, nextjs, npm, npm-package, npx, react, svelte, sveltekit, vue, vuejs, expo, react-native
Last push: 2026-05-16T13:09:07+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 82, release rhythm 44, longevity 36
- inputs: {"age_days": 513, "days_push": 109, "days_rel": 215, "gap_med": 99, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2960, forks 304 (observed 2026-08-28T04:07:32.261675+00:00)

## What it is
A Model Context Protocol (MCP) server that gives AI assistants access to shadcn/ui component source code, demos, blocks, and metadata across React, Svelte 5, Vue, and React Native. It runs via npx or Docker and supports stdio and SSE transports with GitHub API caching.

## Use cases
- let claude or cursor generate code using shadcn/ui components
- give my llm context about shadcn ui component usage and installation
- fetch shadcn/ui component source for svelte or vue in an ai workflow
- build ai-powered scaffolding for dashboards and forms with shadcn blocks
- run an mcp server that serves ui component metadata to coding agents

## When to choose
- you use shadcn/ui and want AI coding assistants to write correct component code
- you work across React, Svelte, Vue, or React Native with shadcn patterns
- you want a ready-made MCP server installable in Claude Desktop via .mcpb

## When to avoid
- you don't use shadcn/ui or an MCP-compatible AI client
- you need a general-purpose component registry rather than shadcn-specific data
- you cannot provide a GitHub token and need high request volumes

## Facets
- artifact type: service
- maturity: active
- function: mcp, ui-components, developer-tools, llm-inference
- domain: developer-tools, frontend, web-development, large-language-models
- platform: cli, cross-platform
- tags: shadcn-ui, model-context-protocol, ai-assistants, react, svelte, vue, react-native, component-library, ai-agents, nodejs, docker

## Member repositories
- Jpisnice/shadcn-ui-mcp-server (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:32.261675+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:32:10.079957+00:00, confidence not recorded.
  - readme: https://github.com/Jpisnice/shadcn-ui-mcp-server (fetched 2026-08-28T04:07:32.261675+00:00, sha 0daf35f33725)
- Data as of 2026-08-30T08:39:29.467469+00:00.