Component Library MCP Server
Provides AI assistants with access to private React component library documentation, props, and code examples through type-safe TypeScript integration.
README
Component Library MCP Server (TypeScript)
A type-safe MCP (Model Context Protocol) server built with TypeScript that provides AI assistants with access to your private React component library documentation and examples.
Features
- 🎯 Type-safe implementation using TypeScript
- 🛠️ Modern MCP SDK with
McpServerand.tool()methods - 📦 Three core tools:
list_components- Lists all components with optional category filteringget_component- Retrieves detailed documentation, props, and usageget_example- Provides code examples for components
- 🔍 Smart parsing:
- Markdown files with frontmatter metadata
- TypeScript prop extraction from source files
- Inline code block extraction from docs
- ⚡ Performance optimized with component caching
Quick Start
1. Install
# Clone or download the server
cd component-library-mcp-ts
# Install dependencies
npm install
# Build TypeScript
npm run build
2. Configure
Set environment variables for your paths:
export COMPONENTS_PATH="/path/to/your/component-library/src/components"
export DOCS_PATH="/path/to/your/documentation-site/content"
export EXAMPLES_PATH="/path/to/your/documentation-site/examples"
Or create a .env file:
COMPONENTS_PATH=/path/to/your/components
DOCS_PATH=/path/to/your/docs
EXAMPLES_PATH=/path/to/your/examples
3. Test
Run the test suite to verify everything works:
npm test
4. Configure Claude Desktop
Add to your Claude Desktop config (~/.config/claude/claude_desktop_config.json):
{
"mcpServers": {
"component-library": {
"command": "node",
"args": ["/absolute/path/to/component-library-mcp-ts/dist/index.js"],
"env": {
"COMPONENTS_PATH": "/path/to/your/library/src",
"DOCS_PATH": "/path/to/your/docs",
"EXAMPLES_PATH": "/path/to/your/examples"
}
}
}
}
For development mode (with hot reload):
{
"mcpServers": {
"component-library": {
"command": "npx",
"args": ["tsx", "/absolute/path/to/component-library-mcp-ts/src/index.ts"],
"env": {
"COMPONENTS_PATH": "/path/to/your/library/src",
"DOCS_PATH": "/path/to/your/docs",
"EXAMPLES_PATH": "/path/to/your/examples"
}
}
}
}
Documentation Structure
Organize your documentation like this:
docs/
├── components/
│ ├── Panel.md # Component documentation with frontmatter
│ ├── Button.md
│ ├── Form.md
│ └── TextBox.md
└── examples/
├── Panel.tsx # Component examples (optional)
├── Button.tsx
└── Form.tsx
Component Documentation Format
Use Markdown with YAML frontmatter:
---
name: Panel
category: layout
description: A flexible container component for grouping content
importPath: '@your-library/Panel'
status: stable
version: 2.1.0
dependencies: ['Button', 'Icon']
accessibility: WCAG 2.1 AA compliant
---
# Panel Component
The Panel component provides consistent spacing and styling for grouped content.
## Props
| Prop | Type | Required | Default | Description |
|------|------|----------|---------|-------------|
| title | string | No | - | Optional header title |
| variant | 'default' \| 'bordered' \| 'shadow' | No | 'default' | Visual style |
## Usage
\`\`\`tsx
import { Panel } from '@your-library/Panel';
function Example() {
return (
<Panel title="Settings" variant="shadow">
<p>Content goes here</p>
</Panel>
);
}
\`\`\`
TypeScript Support
The server includes full TypeScript support with:
Type Definitions
interface ComponentInfo {
name: string;
category?: string;
description?: string;
importPath?: string;
status?: 'stable' | 'beta' | 'deprecated' | 'experimental';
version?: string;
dependencies?: string[];
props?: ComponentProps;
documentation?: string;
accessibility?: string;
}
interface ComponentProps {
[key: string]: {
type: string;
required: boolean;
description?: string;
defaultValue?: any;
}
}
Prop Extraction
The server automatically extracts props from TypeScript interfaces:
// Your component file
interface PanelProps {
/** Optional title for the panel header */
title?: string;
/** Visual style variant */
variant?: 'default' | 'bordered' | 'shadow';
/** Content to display */
children: ReactNode;
}
Usage in Claude
Once configured, use these commands in Claude:
Basic Commands
"Use the component-library MCP to list all components"
"Get details about the Panel component using component-library"
"Show me examples of using the Form component"
"List all components in the 'forms' category"
Building Applications
"Use component-library MCP to gather information about components needed for a user dashboard"
"Help me build a settings page using our component library - get the relevant components"
Development
Scripts
# Build TypeScript
npm run build
# Run in development mode (with tsx)
npm run dev
# Run tests
npm test
# Start production server
npm start
Project Structure
component-library-mcp-ts/
├── src/
│ ├── index.ts # Main server implementation
│ ├── types.ts # TypeScript type definitions
│ └── test.ts # Test suite
├── dist/ # Compiled JavaScript (after build)
├── example-docs/ # Example documentation
│ ├── components/ # Component docs with frontmatter
│ └── examples/ # Component examples
├── tsconfig.json # TypeScript configuration
├── package.json
└── README.md
Extending the Server
Add new tools by extending the setupTools() method:
// In src/index.ts
this.server.tool(
'search_components',
'Search components by keyword',
{
query: z.string().describe('Search query'),
limit: z.number().optional().describe('Maximum results')
},
async (args) => {
// Implementation here
return {
content: [{
type: 'text',
text: JSON.stringify(results)
}]
};
}
);
Advanced Features
Custom Metadata
Extend component metadata in frontmatter:
---
name: DataGrid
category: display
description: High-performance data grid with virtual scrolling
importPath: '@your-library/DataGrid'
status: beta
version: 3.0.0-beta.2
minReactVersion: 18.0.0
dependencies:
- VirtualScroller
- TableHeader
- TableCell
performance:
maxRows: 100000
virtualScrolling: true
accessibility:
wcag: 2.1 AA
ariaSupport: full
keyboardNavigation: true
---
Environment-Specific Configs
Use different paths for different environments:
{
"mcpServers": {
"component-library-dev": {
"command": "npx",
"args": ["tsx", "/path/to/src/index.ts"],
"env": {
"COMPONENTS_PATH": "/path/to/dev/components",
"NODE_ENV": "development"
}
},
"component-library-prod": {
"command": "node",
"args": ["/path/to/dist/index.js"],
"env": {
"COMPONENTS_PATH": "/path/to/prod/components",
"NODE_ENV": "production"
}
}
}
}
Troubleshooting
TypeScript Build Issues
# Clear build and rebuild
rm -rf dist
npm run build
Component Not Found
- Ensure file naming matches component name
- Check that paths are correctly configured
- Verify frontmatter YAML is valid
Props Not Detected
- Props interface must be named
*Props(e.g.,PanelProps) - Ensure component files are accessible via
COMPONENTS_PATH - Check TypeScript syntax is valid
Server Connection Issues
- Use absolute paths in Claude Desktop config
- Ensure Node.js is in PATH
- Check server has read permissions for all paths
- Try development mode with
tsxfor debugging
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.