cloner-mcp

motorthings/cloner-mcp

3.2

If you are the rightful owner of cloner-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.

The SuperAssistant Platform Cloner MCP is a server designed to clone and customize the SuperAssistant MVP platform, facilitating workflows such as GitHub repo creation, Supabase provisioning, and deployment to Railway and Vercel.

Tools
4
Resources
0
Prompts
0

SuperAssistant Platform Cloner MCP

A Model Context Protocol (MCP) server for cloning and customizing the SuperAssistant MVP platform. This MCP server orchestrates complete platform cloning workflows including GitHub repo creation, Supabase provisioning, and automated deployment to Railway and Vercel.

Overview

This MCP server enables you to:

  • 🤖 Interact with PuRDy assistant for requirements gathering (coming soon)
  • ✅ Validate API keys for Anthropic, Voyage AI, ElevenLabs, etc.
  • 🌐 Check domain availability and DNS configuration
  • 🎨 Validate brand colors for WCAG accessibility compliance
  • 📋 Verify system prerequisites (git, gh CLI, etc.)
  • 🚀 Automate complete platform cloning workflows (future phases)

Features

Phase 1 - Foundation (Current):

  • MCP server with FastMCP and STDIO transport
  • API key validation for multiple services
  • Domain availability and DNS checking
  • WCAG color accessibility validation
  • System prerequisite verification
  • Comprehensive error handling

Coming Soon:

  • PuRDy assistant for interactive requirements gathering
  • GitHub repository creation and customization
  • Supabase project provisioning and database migration
  • Railway and Vercel deployment automation
  • Complete end-to-end platform cloning

Prerequisites

  • Python 3.11 or higher
  • uv package manager
  • Internet connection for API calls

Quick Start

Installation

# Clone the repository
cd /Users/motorthings/Documents/GitHub/cloner-mcp

# Install dependencies with uv
uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
uv pip install -e .

# Verify installation
python mcp_server.py

Add to Claude Code

Add this MCP server to Claude Code for seamless integration:

# Option 1: Using claude CLI (if available)
claude mcp add --transport stdio platform-cloner \
  --scope user \
  -- uv --directory /Users/motorthings/Documents/GitHub/cloner-mcp run mcp_server.py

Option 2: Manual configuration

Edit your Claude Code MCP settings file:

Location: ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "platform-cloner": {
      "command": "uv",
      "args": [
        "--directory",
        "/Users/motorthings/Documents/GitHub/cloner-mcp",
        "run",
        "mcp_server.py"
      ]
    }
  }
}

Restart Claude Code after adding the configuration.

Testing with MCP Inspector

The MCP Inspector is a great way to test your MCP server interactively:

# Install MCP Inspector globally
npm install -g @modelcontextprotocol/inspector

# Run the inspector with your server
mcp-inspector uv --directory /Users/motorthings/Documents/GitHub/cloner-mcp run mcp_server.py

This will open a web interface (usually at http://localhost:5173) where you can:

  • View all available tools
  • Test tool invocations
  • See request/response logs
  • Debug MCP protocol communication

Architecture

Components

cloner-mcp/
�� src/cloner_mcp/
   �� server.py          # Main MCP server implementation
   �� purdy/             # PuRDy requirements assistant
      �� assistant.py   # PuRDy conversation handler
      �� prompts.py     # Requirements gathering prompts
   �� tools/             # MCP tool implementations
      �� github.py      # GitHub repository management
      �� supabase.py    # Supabase project provisioning
      �� railway.py     # Railway deployment
      �� vercel.py      # Vercel deployment
   �� templates/         # Configuration templates
�� tests/                 # Test suite
�� pyproject.toml        # Project configuration

Workflow

  1. Requirements Phase

    • User initiates requirements gathering
    • PuRDy conducts interactive conversation
    • System collects client needs, branding, features, etc.

  2. Repository Phase

    • Creates new GitHub repository
    • Clones SuperAssistant MVP template
    • Applies initial customizations

  3. Infrastructure Phase

    • Provisions Supabase project
    • Sets up database schema and functions
    • Configures authentication

  4. Deployment Phase

    • Deploys backend to Railway
    • Deploys frontend to Vercel
    • Configures environment variables
    • Sets up domain routing

  5. Finalization Phase

    • Verifies all services are running
    • Runs initial tests
    • Provides access credentials

Technology Stack

  • MCP Framework: Model Context Protocol for tool exposure
  • Anthropic Claude: Powers PuRDy requirements assistant
  • GitHub API: Repository creation and management
  • Supabase API: Database and authentication provisioning
  • Railway API: Backend deployment and hosting
  • Vercel API: Frontend deployment and hosting
  • httpx: Async HTTP client for API calls
  • python-dotenv: Environment configuration management

Development

Project Structure

  • src/cloner_mcp/: Main source code
  • tests/: Test suite with unit and integration tests
  • templates/: Configuration and code templates
  • docs/: Additional documentation

Running Tests

# Run all tests
uv run pytest

# Run with coverage
uv run pytest --cov=src/cloner_mcp

# Run specific test file
uv run pytest tests/test_server.py

Code Quality

# Format code
uv run black src tests

# Lint code
uv run ruff check src tests

# Type checking (if using mypy)
uv run mypy src

Adding New Tools

  1. Create tool implementation in src/cloner_mcp/tools/
  2. Define MCP tool schema in src/cloner_mcp/server.py
  3. Add tests in tests/
  4. Update documentation

Configuration

Environment Variables

See .env.example for all available configuration options.

MCP Server Options

Configure the MCP server behavior through environment variables:

  • MCP_SERVER_PORT: Port for the MCP server (default: 3000)
  • MCP_LOG_LEVEL: Logging level (debug, info, warning, error)

Troubleshooting

Common Issues

Authentication Errors

  • Verify all API tokens are correct and have proper scopes
  • Check token expiration dates
  • Ensure tokens have necessary permissions

Deployment Failures

  • Check service quotas on Railway/Vercel
  • Verify repository access permissions
  • Review deployment logs for specific errors

PuRDy Connection Issues

  • Confirm ANTHROPIC_API_KEY is valid
  • Check internet connectivity
  • Verify Claude API status

Debug Mode

Enable debug logging:

export MCP_LOG_LEVEL=debug

Contributing

Contributions are welcome! Please:

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes with tests
  4. Submit a pull request

License

MIT License - see LICENSE file for details

Support

For issues, questions, or contributions:

Acknowledgments