AI Development Pipeline MCP Integration

A comprehensive Model Context Protocol (MCP) server implementation that enables seamless integration between Claude AI, VSCode, Augment, and various cloud services including Vercel, Airtable, and Square.

🚀 Features

• Local MCP Server: Direct stdio integration with Claude Desktop

• Cloud MCP Server: HTTP endpoint for web-based Claude integration

• 7 Powerful MCP Tools: File operations, shell commands, and AI agent integration

• Multi-Platform Support: Windows (PowerShell) and Unix (Bash) startup scripts

• Production Ready: Vercel deployment configuration included

📋 Prerequisites

• Node.js 18+ and npm

• TypeScript and ts-node

• Claude Desktop (for local integration)

• Vercel account (for cloud deployment)

🛠️ Installation

1. Clone the repository:

2. Install dependencies:

3. Configure environment variables:

🔧 Configuration

Create a .env file in the root directory with the following variables:

🖥️ Local MCP Server Setup

For Windows (PowerShell):

For Unix/Linux/macOS (Bash):

Manual Start:

🔗 Claude Desktop Integration

1. Start the local MCP server using one of the methods above

2. Configure Claude Desktop by adding the following to your Claude Desktop configuration:

3. Restart Claude Desktop to load the MCP server

☁️ Cloud Deployment (Vercel)

Automatic Deployment (Recommended)

1. Connect to GitHub:

   • Go to Vercel Dashboard

   • Click "New Project" and import your GitHub repository

   • Vercel will automatically detect the configuration

2. Manual Deployment:

Build Configuration

The project includes a vercel.json configuration that handles:

• TypeScript compilation

• API route setup

• CORS headers

• Output directory configuration

Environment Variables

Configure these in your Vercel dashboard:

• AIRTABLE_API_KEY

• AIRTABLE_BASE_ID

• AIRTABLE_TABLE_NAME

• SQUARE_ACCESS_TOKEN

• SQUARE_APPLICATION_ID

• NEXTAUTH_SECRET

• MCP_API_KEY

• All other variables from .env.example

Claude Integration

Add to Claude as an HTTP MCP server:

• URL: https://your-app.vercel.app/api/mcp

• Method: POST

• Headers: Content-Type: application/json

🛠️ Available MCP Tools

The server provides 7 powerful tools for AI-driven development:

1. read_project_file - Read files from the workspace

2. write_project_file - Write/update files in the workspace

3. run_shell_command - Execute shell commands (npm, git, etc.)

4. check_file_exists - Check if files exist

5. list_directory_files - List directory contents

6. run_augment_prompt - Send prompts to Augment coding agent

7. run_project_tests - Execute project tests

📁 Project Structure

🧪 Testing

Run the TypeScript compiler to check for errors:

Test the local MCP server:

🔒 Security Considerations

• Never commit - They contain sensitive API keys

• Use environment variables for all secrets in production

• Review API permissions before deploying to production

• Enable proper authentication for cloud deployments

🤝 Contributing

1. Fork the repository

2. Create a feature branch (git checkout -b feature/amazing-feature)

3. Commit your changes (git commit -m 'Add amazing feature')

4. Push to the branch (git push origin feature/amazing-feature)

5. Open a Pull Request

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

🆘 Troubleshooting

Common Issues:

"Module not found" errors:

• Ensure all dependencies are installed: npm install

• Check TypeScript configuration in tsconfig.json

MCP server won't start:

• Verify Node.js version (18+ required)

• Check that ts-node is available: npx ts-node --version

Claude Desktop integration issues:

• Ensure the MCP server is running before starting Claude

• Check the file path in Claude Desktop configuration

• Restart Claude Desktop after configuration changes

Getting Help:

• Check the Issues page

• Review the MCP documentation at modelcontextprotocol.io

• Join the Claude AI community discussions

🔗 Related Projects

• Model Context Protocol

• Claude Desktop

• Vercel

• Airtable API

📊 Project Status

✅ Ready for Production

• Local MCP server fully functional

• Cloud deployment configured

• All 7 MCP tools tested and validated

• Cross-platform startup scripts included

• Comprehensive documentation provided

Built with ❤️ for the AI development community