An astronaut overseeing a futuristic data hub

Connect Shadcnui Dependency Resolver to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Stop your AI from writing broken JSX code.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 3 capabilities

We ship only the actions that matter.

Capability set01 / 01

01-03

3 capabilities in this set.

Part of 3 available through shadcn/ui Resolver.

  1. 01

    Extract dependencies

    This capability analyzes JSX snippets to find required shadcn/ui components. It returns a list of necessary packages and flags any missing sub-components.

  2. 02

    List all registry components

    This capability provides a full list of every shadcn/ui component available in the registry. Use it to see what your agent is capable of resolving.

  3. 03

    Validate component registry entry

    This capability checks if a specific string is a valid shadcn/ui component or sub-component. It identifies the base package for any given tag.

Real work

What teams actually run

01

Rapid Prototyping

Your agent generates a complex form, and this MCP tells you exactly which shadcn components to install to make it work.

02

Code Auditing

You pass existing JSX files to the agent to find out which shadcn/ui dependencies are currently active in the codebase.

03

Component Verification

You check if a specific component name is a valid part of the shadcn registry before asking your agent to write it.

04

Fixing Broken Snippets

When an agent provides code that throws import errors, you use this capability to identify the missing pieces.

One connector, every AI

shadcn/ui Resolver works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put shadcn/ui Resolver to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

539ms average. Fast in production.

shadcn/ui Resolver is checked daily against the live service.

Daily averagePeak 623ms
Oct 3Today
Fastest day
474ms
Slowest day
623ms
14-day trend
Slowing+5%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 3 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of shadcn/ui Resolver, so you can see the experience inside your AI.

It does not authenticate your account with shadcn/ui Resolver. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

shadcn/ui Resolver Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_U9irMWgXv28cwSXxmqiAgD6Vnm7Obd7lVDbcbdVU/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — shadcn/ui Resolver capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "shadcnui-dependency-resolver-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_U9irMWgXv28cwSXxmqiAgD6Vnm7Obd7lVDbcbdVU/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up shadcn/ui Resolver in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work shadcn/ui Resolver owners hand off.

Frontend developers using AI agents to scaffold UI components.

  • 01

    React Developers

    You hand off UI layout tasks to an agent and use this MCP to verify the generated code is installable.

  • 02

    AI Engineers

    You use this to build more reliable coding agents that don't hallucinate missing dependencies.

  • 03

    Full Stack Developers

    You use this to quickly bridge the gap between AI-generated snippets and your local project environment.

FAQ

Questions shadcn/ui Resolver owners ask.

  • 01

    What does this MCP actually do?

    It identifies the specific shadcn/ui components and packages required by any JSX or TSX code snippet you provide to your AI client.

  • 02

    How does it help with shadcn/ui components?

    It solves the problem where an AI agent writes code for a component but forgets that the project needs specific sub-components or base packages installed.

  • 03

    Which AI clients can use this?

    You can use this with any MCP-compatible client, including Claude, Cursor, and Windsurf.

  • 04

    Does it install the packages for me?

    No, it identifies what needs to be installed so you can run the installation commands yourself.

  • 05

    Can it verify if a component name is correct?

    Yes, the validate_component_registry_entry capability checks if a string matches a known shadcn/ui component or sub-component.

  • 06

    What does the extract_dependencies capability return?

    It returns a unique list of required components, the total count of detected components, and a list of any missing sub-components found in your snippet.

  • 07

    How does it identify components?

    The capability scans your JSX for tags starting with an uppercase letter and matches them against a strict registry of shadcn/ui component families.

  • 08

    Can I verify a specific tag name?

    Yes, you can use the validate_component_registry_entry capability to check if a specific string like 'AccordionItem' is recognized as a valid shadcn/ui component.

Connect shadcn/ui Resolver to Claude, Cursor, ChatGPT & more