Click on "Install 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., "@Claude Imaginecreate a dashboard with a header, sidebar, and main content area"
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.
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
Quick Start
1. Install Dependencies
2. Start the MCP Server
Server runs at http://localhost:3000
3. Add MCP Server to Claude (one-time)
4. Open Browser
Navigate to http://localhost:3000 in your browser.
5. Use Claude
MCP Tools
Tool | Description |
| Updates HTML content in the browser |
| Displays status/thinking messages |
Project Structure
Configuration
claude_config.json
Environment Variables
Variable | Default | Description |
| 3000 | Server port |
| 127.0.0.1 | Server host |
Development
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