shadcn/ui Resolver Connector for AI agents.
3 live capabilities
Fix broken React imports and resolve missing shadcn/ui components automatically.
Waiting for input…
Why people use shadcn/ui Resolver
Stop shadcn/ui dependency errors with shadcn/ui Dependency Resolver Alternative
With this MCP, that loop ends. Your agent checks the code against the actual registry, identifies exactly which packages are missing, and tells you what to install. You get working code on the first try.
What Vinkius changes
You stop debugging broken UI imports caused by incomplete component installations.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Fixing broken AI-generated dialogs
Your agent writes a beautiful Dialog component, but the app crashes because you forgot to install the underlying dialog package.
- Real-world use case 02
Verifying complex JSX snippets
You paste a large block of TSX from a chat and need to know if your current shadcn/ui setup can handle it without extra installs.
- Real-world use case 03
Auditing component usage
Check a new feature branch to see which specific shadcn/ui components are being introduced to the project.
Complete set · 3capabilities
The complete shadcn/ui Resolver capability set.
These are the exact actions your AI can choose when you ask it to work with shadcn/ui Resolver.
01—03
3 capabilities in this set.
Part of 3 available through shadcn/ui Resolver.
- 01 Capability
Extract dependencies
Scans your JSX to find every required shadcn/ui package and identifies any missing sub-components. It tells you exactly what needs to be installed.
- 02 Capability
List all registry components
Provides a full list of all shadcn/ui components that can be resolved. Use this to see what's supported in the registry.
- 03 Capability
Validate component registry entry
Checks if a specific string is a valid part of the shadcn/ui component tree. It confirms if a sub-component belongs to a base package.
Set up in minutes
One URL. Then ask shadcn/ui Resolver to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use shadcn/ui Resolver from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_U9irMWgXv28cwSXxmqiAgD6Vnm7Obd7lVDbcbdVU/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it shadcn/ui Resolver, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable shadcn/ui Resolver for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_U9irMWgXv28cwSXxmqiAgD6Vnm7Obd7lVDbcbdVU/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the shadcn/ui Resolver URL.
- Step 03
Save and start
Save the connection and enable shadcn/ui Resolver in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"shadcnui-dependency-resolver-alternative": {
"url": "https://edge.vinkius.com/vk_preview_U9irMWgXv28cwSXxmqiAgD6Vnm7Obd7lVDbcbdVU/mcp"
}
}
} - Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using shadcn/ui Resolver
Open Agent mode in chat and ask: "Using shadcn/ui Resolver, help me...". 3 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"shadcnui-dependency-resolver-alternative": {
"url": "https://edge.vinkius.com/vk_preview_U9irMWgXv28cwSXxmqiAgD6Vnm7Obd7lVDbcbdVU/mcp"
}
}
} - Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using shadcn/ui Resolver
Ask Copilot: "Using shadcn/ui Resolver, help me...". 3 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"shadcnui-dependency-resolver-alternative": {
"url": "https://edge.vinkius.com/vk_preview_U9irMWgXv28cwSXxmqiAgD6Vnm7Obd7lVDbcbdVU/mcp"
}
}
} - Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using shadcn/ui Resolver
Open Cascade and ask: "Using shadcn/ui Resolver, help me...". 3 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"shadcnui-dependency-resolver-alternative": {
"url": "https://edge.vinkius.com/vk_preview_U9irMWgXv28cwSXxmqiAgD6Vnm7Obd7lVDbcbdVU/mcp"
}
}
} - Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using shadcn/ui Resolver
Ask Cline: "Using shadcn/ui Resolver, help me...". 3 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add shadcnui-dependency-resolver-alternative --transport http "https://edge.vinkius.com/vk_preview_U9irMWgXv28cwSXxmqiAgD6Vnm7Obd7lVDbcbdVU/mcp" - Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using shadcn/ui Resolver
Ask Claude: "Using shadcn/ui Resolver, show me...". 3 tools are ready
Where the request belongs
Work shadcn/ui Resolver can move forward.
Frontend engineers and React developers who use AI agents to scaffold UI components but hate the 'missing dependency' error loop.
React Developer
Checking if a generated snippet requires new shadcn/ui packages before adding them to the codebase.
UI Engineer
Ensuring all sub-components like DialogContent are properly accounted for in a complex component tree.
Full-stack Engineer
Quickly verifying that AI-generated frontend code won't break the build during a rapid prototyping session.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse Connectorsshadcn/ui Dependency Resolver
Resolves exact shadcn/ui component dependencies from JSX snippets.
React 19 useActionState Validator
Validates React 19 `useActionState` hook implementations in JSX snippets.
CSS Class Usage & Collision Analyzer
Identify orphaned, missing, or colliding CSS classes in your project.
Svelte 5 Rune Syntax Validator
Ensure your Svelte components strictly adhere to the new Runes API syntax.
Storybook
Connect your AI to Storybook. Explore your design system, inspect UI components, and retrieve implementation guidance programmatically.
Vue.js Excellence Prover
AI agents produce legacy Vue 2 configurations, unstable reactivity loops, and untyped interfaces. This prover enforces Vue 3 Composition API excellence, strict reactivity limits, compile-time type-safety, and optimized browser execution. Zero tolerance for Options API and raw prop mutations.
Bring your own AI
Change the model, client or framework. Keep shadcn/ui Resolver connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about shadcn/ui Resolver.
The practical details behind the request, access and result.
How does shadcn/ui Dependency Resolver Alternative fix broken imports?
It scans your code snippets to find any UI components that aren't currently in your project's registry, giving you a clear list of what to install.
Can I use this MCP with Cursor or Windsurf?
Yes, you can connect it to any compatible client like Cursor, Windsurf, or VS Code via the Vinkius catalog to check your React components.
Does this work for all shadcn/ui components?
It works for any component currently in the supported registry, which you can view at any time using the list capability.
Will this help me find missing sub-components like DialogContent?
Absolutely. The capability specifically looks for these nested tags to ensure your entire component tree is properly installed.
Do I need to manually update the registry?
No, the MCP uses the existing registry data to identify what's valid and what's missing from your current implementation.
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.
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.
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.
One connection away
Give your agent a direct line to shadcn/ui Resolver.
Connect shadcn/ui Resolver once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available