MCP Color Picker
An interactive color picker that renders as a UI inside MCP-compatible hosts like VS Code GitHub Copilot and Claude.
README
šØ MCP Color Picker ā Sample MCP App
An interactive color picker that renders as a UI inside MCP-compatible hosts like VS Code GitHub Copilot and Claude.
Prerequisites
- Node.js 18+
- VS Code with GitHub Copilot (or Claude / Claude Desktop)
Setup
1. Install & build
npm install
npm run build
2. Start the server
npm run serve
You should see:
ā
MCP Color Picker running at http://localhost:3001/mcp
Connect to VS Code Copilot
Add the server to your VS Code MCP config.
Option A ā project-level (.vscode/mcp.json in your workspace):
{
"servers": {
"color-picker": {
"type": "http",
"url": "http://localhost:3001/mcp"
}
}
}
Option B ā global (~/.copilot/mcp.json):
{
"servers": {
"color-picker": {
"type": "http",
"url": "http://localhost:3001/mcp"
}
}
}
Then in VS Code:
- Open Copilot Chat (
Ctrl+Alt+I/Cmd+Alt+I) - Switch to Agent mode (dropdown in the chat input)
- Type: "open the color picker"
The interactive color picker UI will render right inside the chat! š
Connect to Claude (web / desktop)
For Claude.ai or Claude Desktop you need to expose the server publicly. In a separate terminal:
npx cloudflared tunnel --url http://localhost:3001
Copy the generated URL (e.g. https://random-name.trycloudflare.com) and add
it as a Custom Connector in Claude:
Profile ā Settings ā Connectors ā Add custom connector
Note: Custom connectors require a paid Claude plan (Pro, Max, or Team).
How it works
| File | Role |
|---|---|
server.ts |
MCP server ā registers the color_picker tool + serves the HTML UI resource |
mcp-app.html |
HTML entry point for the color picker UI |
src/mcp-app.ts |
UI logic ā connects to the host via the MCP App SDK |
vite.config.ts |
Bundles everything into a single self-contained HTML file |
Key concepts
registerAppToolā registers the tool with_meta.ui.resourceUri, telling the host to render a UI when this tool is calledregisterAppResourceā serves the bundled HTML when the host requests itApp.connect()ā establishes bidirectional communication between the UI and the hostapp.ontoolresultā receives data pushed from the server when the tool runs
Rebuilding after UI changes
npm run build # rebuild the UI
npm run serve # restart the server
Or run both at once:
npm run dev
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.