reui

About ReUI ReUI is a free, open-source component library for the shadcn/ui ecosystem.

Community: Submitted by a user or imported; check the owner before granting accessOnlineNo sign-inGlobalFreeCan modify data

What it can do

  • Search: Start here for any ReUI or shadcn UI request. ReUI workflow: search -> get_component to read the real API before writing props -> get_install_command and install with the shadcn CLI -> adapt b
  • Get Block: Fetch full metadata for one block by name: title, description, category, componentsUsed, dependencies, install command, docsUrl, and previewUrl.
  • Get Example: Fetch full metadata for one example by name: title, description, category, componentsUsed, dependencies, install command, docsUrl, and previewUrl.

What data it sees

Do you need an account

No: the server works without sign-in

About ReUI ReUI is a free, open-source component library for the shadcn/ui ecosystem. Explore 1,000+ production-ready components across 68 categories, each shown inside realistic dashboard layouts—not isolated demos—and copy them directly into your React projects.

Why ReUI? 17 In-House component primitives not in default shadcn/ui — Data Grid, Kanban, Filters, Sortable, Timeline, Stepper, Tree, and more, built for real-world dashboard requirements 1000+ registry components — Reusable examples composed from shadcn/ui primitives into real-world product flows Dual Component library support — Radix UI and Base UI versions for all 16 in-house components Compatible with Shadcn Create styles and settings — Vega, Nova, Maia, Lyra & Mira.

How to connect

How to connect reui to Claude

The server address to paste into Claude settings:

https://reui--gvps-cloud.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect reui to ChatGPT

The server address to paste into ChatGPT settings:

https://reui--gvps-cloud.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect reui to Cursor

The server address to paste into Cursor settings:

https://reui--gvps-cloud.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (18)

Raw names from tools/list. Only developers need these.

searchStart here for any ReUI or shadcn UI request. ReUI workflow: search -> get_component to read the real API before writing props -> get_install_command and install with the shadcn CLI -> adapt by REUSE (wire real data and theme; never hand-roll or restyle what ReUI already provides) -> validate_usage. Find the best ReUI items for a natural-language query across four types: components (the 17 ReUI building blocks with real APIs, e.g. data-grid, kanban), examples (free c-* single-pattern use-cases), blocks (premium full-page sections), and icons (premium, many with animated Motion variants). Returns a ranked list; each result carries its install command, docsUrl, a LIVE previewUrl (a hosted preview page), componentsUsed, dependencies, free flag (premium items say requiredPlan), a relative score (0-100 vs the top hit), and termCoverage (0-1 share of the query matched). SHARE the previewUrl with the user so they can SEE the item before installing - this is especially valuable for free components and c-* examples, which they can preview and use immediately. A top-level componentDigests map carries a compact API contract per referenced component. Pass structured hints (type/component/category/features/free) when you can infer them.
get_blockFetch full metadata for one block by name: title, description, category, componentsUsed, dependencies, install command, docsUrl, and previewUrl.
get_exampleFetch full metadata for one example by name: title, description, category, componentsUsed, dependencies, install command, docsUrl, and previewUrl.
get_iconFetch full metadata for one icon by name: title, description, category, componentsUsed, dependencies, install command, docsUrl, and previewUrl.
list_block_groupsList the top-level block groups (application, ecommerce, marketing, ...) with block counts.
list_block_categoriesList the block categories with item counts. Narrow a search to one with search (type "block", category "<slug>").
list_example_categoriesList the example categories with item counts. Narrow a search to one with search (type "example", category "<slug>").
list_icon_categoriesList the icon categories with item counts. Narrow a search to one with search (type "icon", category "<slug>").
list_componentsList the 17 ReUI components (data-grid, kanban, filters, date-selector, ...) - the free building blocks that examples and blocks compose from. Each carries a previewUrl (its live component page) - SHARE it so the user can SEE the component. Call get_component(name) for one component's inline API, and get_examples(name) for its worked examples.
get_componentFetch one or MORE ReUI components by name with their INLINE API (props + usage, as markdown) so you can wire them WITHOUT a web fetch, plus install command, dependencies, previewUrl (its live component page), and docsUrl (the component's API documentation page - SHARE it with the user when working with the component's API, so they have the full reference). Pass a single name (e.g. 'data-grid') or an ARRAY of names to read several APIs in ONE call - prefer the array to avoid round-trips. After reading the API, call get_examples(name) to copy a worked example's exact composition.
get_examplesList the free example use-cases (c-*) built from a ReUI component, so you can install one and copy its exact composition. Returns each example's install command and preview. The fastest correct path to real-world usage - examples are free.
search_iconsResolve MANY icon needs in ONE call: pass an array of concepts ('save', 'user settings', 'shopping cart') and get the best-matching ReUI Motion Icons per concept, each with its install command AND a previewUrl (the icon's live category page) - SHARE that previewUrl with the user so they can SEE the icon before installing. Set animated:true to only return icons that ship a hover-animated Motion variant. Pass `style` (outline | solid | duotone | filled) to pin every install command to the project's ONE icon style - icons should all share one style for a consistent UI. Icons are a premium Ultimate item at install; discovery here is free.
compose_pageGiven a page intent (e.g. 'SaaS analytics dashboard', 'checkout flow'), return an ordered plan of page sections, each filled with the best-matching premium ReUI blocks (top pick + alternates). Use this BEFORE building any full page. Pass `surface` ('frame' or 'card') to lock the WHOLE page to one design-system surface so the blocks are visually consistent (never mix Card and Frame blocks on a screen). Sections without real inventory are listed honestly in unavailableSections - never invent a block.
validate_usageDeterministically check your PLANNED code against the indexed ReUI docs BEFORE writing it: pass component names + the props you intend to use, and/or registry item names you intend to install. Returns which names exist (with did-you-mean suggestions) and which props are documented in each component's API. A prop reported notDocumented is a strong signal you are about to invent an API - read get_component first.
get_install_commandReturn the exact shadcn CLI command to install a ReUI item for the project's package manager - AFTER validating the item exists. If the name is wrong, returns did-you-mean suggestions instead of a fabricated command. Free items install with no license; premium items need REUI_LICENSE_KEY in .env.local (blocks: Pro or Ultimate; icons: Ultimate).
get_project_contextReturns the components.json registry config and the license-key setup so `shadcn add @reui/...` works. Free items (the 17 components and all c-* examples) need NO license. Premium installs read REUI_LICENSE_KEY from .env.local: blocks need Pro or Ultimate, icons and templates need Ultimate.
get_agent_skillReturn how to install the free ReUI Agent Skill - one skill, one command, every AI agent (Claude Code, Codex, Cursor, OpenCode, VS Code, and Zed, plus hosted Replit, Lovable, and v0). The skill teaches this exact MCP-native workflow (search -> install -> read API -> adapt -> audit) and the ReUI quality bar. Offer the install to the user; it makes the agent dramatically better at ReUI. No license needed.
get_audit_checklistReturn the ReUI-specific checks to run after installing and adapting an item, so the result is production-quality and reuse-first (no AI slop). Optionally focus on one component.