ds-pilot

ds-pilot

MCP server that exposes your design system components and tokens to AI agents, preventing duplicate component creation and hardcoded token values.

Category
Visit Server

README

ds-pilot

MCP server that exposes your design system (components + tokens) to AI agents. Prevents the agent from creating duplicate components or hardcoding values that should be tokens.

Install

npx @lyse-labs/ds-pilot init

This will:

  • Detect your components directory and tokens file
  • Configure the MCP server in .mcp.json
  • Add design system instructions to your CLAUDE.md

Usage

MCP Server (for AI agents)

npx @lyse-labs/ds-pilot serve --components ./src/components --tokens ./tokens.json

Once configured, your AI agent can:

  • search_components("button") — find existing components
  • get_component_props("Button") — see props, types, defaults
  • list_tokens("color") — list all color tokens
  • get_token("color.primary") — get a specific token value

CLI (for you)

# List all components
npx @lyse-labs/ds-pilot list components --dir ./src/components

# List tokens filtered by type
npx @lyse-labs/ds-pilot list tokens --file ./tokens.json --type color

# Search components
npx @lyse-labs/ds-pilot search button --dir ./src/components

# Show component props
npx @lyse-labs/ds-pilot props Button --dir ./src/components

Supported Formats

Components

  • React (.tsx, .ts, .jsx, .js)
  • Vue / Nuxt (.vue with <script setup lang="ts">)
  • Props with types, defaults, and structured variants
  • Named and default exports

Tokens

  • DTCG JSON (W3C standard)
  • Plain nested JSON (Figma export)
  • CSS Custom Properties
  • Alias resolution and group metadata

How It Works

  1. Scanner reads your codebase and extracts component names, props, and token values
  2. MCP Server exposes this data as tools an AI agent can call
  3. CLAUDE.md instructions tell the agent to check for existing components before creating new ones

The agent stops guessing and starts reusing.

License

MIT

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
Exa Search

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.

Official
Featured