Claude Imagine
A visual UI builder that enables Claude to create and update web interfaces in real-time by sending HTML updates to a browser through an MCP server with WebSocket communication.
README
Claude Imagine
A visual UI builder powered by Claude AI using the Model Context Protocol (MCP).
Claude connects to an MCP server via HTTP transport, which relays UI commands to a browser via WebSocket. This enables Claude to build and update web interfaces in real-time.
Architecture
┌─────────────┐ ┌──────────────────┐ ┌─────────┐
│ Claude CLI │──HTTP──►│ server-mcp.js │◄──WS───│ Browser │
└─────────────┘ │ (MCP Server) │ └─────────┘
│ │
│ Tools: │
│ - update_ui │
│ - log_thought │
└──────────────────┘
Quick Start
1. Install Dependencies
npm install
2. Start the MCP Server
npm run server:mcp
Server runs at http://localhost:3000
3. Add MCP Server to Claude (one-time)
claude mcp add --transport http imagine http://localhost:3000/mcp
4. Open Browser
Navigate to http://localhost:3000 in your browser.
5. Use Claude
# Interactive mode
claude
# Or non-interactive
claude --print --dangerously-skip-permissions \
"Use update_ui to create a hello world page"
MCP Tools
| Tool | Description |
|---|---|
update_ui |
Updates HTML content in the browser |
log_thought |
Displays status/thinking messages |
Project Structure
ClaudeImagine/
├── src/
│ └── server-mcp.js # MCP server (HTTP transport)
├── public/
│ └── index.html # Browser UI
├── scripts/
│ └── create-isolated-claude.js
├── tests/
│ ├── prerequisites/ # Unit tests
│ └── e2e/ # Integration tests
├── docs/
│ ├── CLAUDE-LEARNING.md # Key discoveries
│ ├── ROADMAP.md # Development plan
│ └── ...
├── claude_config.json # MCP configuration
└── package.json
Configuration
claude_config.json
{
"mcpServers": {
"imagine": {
"type": "http",
"url": "http://localhost:3000/mcp"
}
}
}
Environment Variables
| Variable | Default | Description |
|---|---|---|
PORT |
3000 | Server port |
HOST |
127.0.0.1 | Server host |
Development
# Start server
npm run server:mcp
# Run tests
npm test
# Check MCP connection
claude mcp list
Documentation
- CLAUDE-LEARNING.md - Key technical discoveries
- ROADMAP.md - Development roadmap
- LESSONS-LEARNED.md - Project insights
Key Learnings
- HTTP Transport - Claude connects to a running server (not spawned)
- Tool Naming - Tools become
mcp__imagine__<tool_name> - Session Management - Each Claude session creates an MCP session
- WebSocket Bridge - Single server handles both MCP and browser
See docs/CLAUDE-LEARNING.md for full details.
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.
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.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.
E2B
Using MCP to run code via e2b.