MCP Color Picker
Enables the color picker UI to be displayed within VS Code GitHub Copilot Chat in Agent mode.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Color Pickeropen the color picker"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
π¨ MCP Color Picker β 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)
Related MCP server: Colors MCP Server
Setup
1. Install & build
npm install
npm run build2. Start the server
npm run serveYou should see:
β
MCP Color Picker running at http://localhost:3001/mcpConnect to VS Code Copilot
Add the server to your VS Code MCP config.
Option A β project-level (.vscode/mcp.json in your workspace):
{
"servers": {
"color-picker": {
"type": "http",
"url": "http://localhost:3001/mcp"
}
}
}Option B β 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! π
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:3001Copy the generated URL (e.g. https://random-name.trycloudflare.com) and add
it as a Custom Connector in Claude:
Profile β Settings β Connectors β Add custom connector
Note: Custom connectors require a paid Claude plan (Pro, Max, or Team).
How it works
File | Role |
| MCP server β registers the |
| HTML entry point for the color picker UI |
| UI logic β connects to the host via the MCP App SDK |
| Bundles everything into a single self-contained HTML file |
Key concepts
registerAppToolβ registers the tool with_meta.ui.resourceUri, telling the host to render a UI when this tool is calledregisterAppResourceβ serves the bundled HTML when the host requests itApp.connect()β establishes bidirectional communication between the UI and the hostapp.ontoolresultβ 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 serverOr run both at once:
npm run devThis server cannot be deployed
Maintenance
Related MCP Connectors
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
The Figma MCP server brings Figma design context directly into your AI workflow.
MCP-native notes and memory for ChatGPT, Claude, and other AI tools.
The OpenRouter MCP server plugs OpenRouter into the AI tools you already use. Once connected, your assistant can pull live OpenRouter data (models, prices, your credits, rankings, and docs) and send quick test messages, all without leaving your editor.
Related MCP Servers
- AlicenseAqualityCmaintenanceA lightweight MCP server that enables AI assistants to collect interactive user feedback via a browser window with full Markdown rendering and syntax highlighting.122 npm3MIT
- AlicenseAqualityDmaintenanceA simple color utility MCP server for frontend developers. Convert, mix, adjust, and analyze colors right from your AI agents.1124 npmMIT
- FlicenseNot gradedqualityDmaintenanceEnables users to generate color palettes (complementary, analogous, triadic, etc.) and check WCAG contrast ratios within AI chat applications using interactive UI.-
- AlicenseNot gradedqualityBmaintenanceAn MCP server that lets coding agents ask their human via interactive UIs like sliders, forms, diffs, and live previews.MIT