StartupManch/gcp-mcp-server

GCP MCP Server

A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact seamlessly with your Google Cloud Platform environment. Built with TypeScript and featuring 25+ tools across 8 major GCP service categories.

✨ Key Features

• 🤖 AI-Native: Natural language interface for all GCP operations
• 🔐 Secure: Uses your existing GCP credentials (no external access required)
• 🌐 Multi-Project: Seamlessly work across multiple GCP projects and regions
• ⚡ Comprehensive: 25 tools covering compute, storage, databases, serverless, and more
• 🛠️ Developer-Friendly: Full TypeScript implementation with excellent error handling
• 🔄 Reliable: Built-in retry logic and robust error handling
• 📊 Observable: Comprehensive logging for debugging and monitoring

🚀 Quick Start

Prerequisites

• Node.js v18 or higher
• Google Cloud SDK configured with authentication
• Claude Desktop, Cursor, Windsurf, or any MCP-compatible AI assistant

Installation & Setup

1. Authenticate with GCP:

   gcloud auth application-default login
   

2. Install via NPX (recommended):

   npx gcp-mcp-server
   

3. Configure your AI assistant:

   Claude Desktop - Add to claude_desktop_config.json:

   {
     "mcpServers": {
       "gcp": {
         "command": "npx",
         "args": ["-y", "gcp-mcp-server"]
       }
     }
   }
   

   Cursor - Add to MCP settings:

   {
     "gcp": {
       "command": "npx",
       "args": ["-y", "gcp-mcp-server"]
     }
   }
   

   Windsurf - Add to ~/.windsurf/config.json:

   {
     "mcpServers": {
       "gcp": {
         "command": "npx",
         "args": ["-y", "gcp-mcp-server"]
     }
   }
   

4. Restart your AI assistant and start chatting with your GCP environment!

🛠️ Available Tools (25 Total)

🔧 Core Management (5 tools)

� Compute Engine (4 tools)

🗄️ Cloud Storage (3 tools)

📊 BigQuery (3 tools)

🗃️ Cloud SQL (2 tools)

⚡ Cloud Functions (2 tools)

🏃 Cloud Run (2 tools)

🚢 Google Kubernetes Engine (2 tools)

📝 Cloud Logging (2 tools)

💡 Example Conversations

Getting Started

User: "Show me all my GCP projects"
Assistant: [Lists all accessible projects with IDs and names]

User: "Use project my-web-app-prod"
Assistant: [Selects project and shows available regions]

Infrastructure Management

User: "List all running compute instances in us-west1"
Assistant: [Shows VM instances with status, machine type, and IPs]

User: "What storage buckets do I have?"
Assistant: [Lists buckets with size, location, and storage class]

User: "Show me my Cloud Run services"
Assistant: [Displays services with URLs, traffic allocation, and status]

Data & Analytics

User: "What BigQuery datasets are in my project?"
Assistant: [Lists datasets with creation time and location]

User: "Query my sales table for last month's revenue"
Assistant: [Executes SQL and returns results]

Cost Management

User: "What's my current billing status?"
Assistant: [Shows billing account, budget alerts, and current usage]

User: "Forecast my costs for the next 3 months"
Assistant: [Displays cost predictions based on usage trends]

Troubleshooting

User: "Show me error logs from my app in the last hour"
Assistant: [Queries Cloud Logging and displays relevant errors]

User: "Why is my Cloud Function timing out?"
Assistant: [Analyzes function configuration and recent logs]

🏗️ Architecture

The server is built with a clean, modular architecture:

src/
├── types/           # TypeScript type definitions
├── utils/           # Utilities (logging, errors, state management)
├── tools/           # Tool definitions and handlers
│   ├── definitions.ts
│   └── handlers.ts
├── config.ts        # Configuration constants
├── server.ts        # MCP server implementation
└── index.ts         # Application entry point

🔧 Development

Local Development Setup

# Clone the repository
git clone https://github.com/startupmanch/gcp-mcp-server
cd gcp-mcp-server

# Install dependencies
npm install

# Build the project
npm run build

# Run in development mode
npm run dev

Available Scripts

npm run dev          # Development mode with auto-reload
npm run build        # Production build
npm run start        # Start built server
npm run test         # Run test suite
npm run lint         # Lint code
npm run format       # Format code with Prettier
npm run clean        # Clean build artifacts

Testing with MCP Inspector

# Build and test with MCP Inspector
npm run build
npx @modelcontextprotocol/inspector ./bin.js

📋 Requirements

• Node.js: Version 18 or higher
• Google Cloud SDK: Properly configured and authenticated
• GCP Projects: Access to at least one GCP project with appropriate IAM permissions

Required GCP APIs

The following APIs should be enabled in your GCP project:

• Cloud Resource Manager API
• Compute Engine API
• Cloud Storage API
• BigQuery API
• Cloud SQL Admin API
• Cloud Functions API
• Cloud Run API
• Cloud Logging API
• Cloud Billing API
• Kubernetes Engine API

� Security & Permissions

Required IAM Roles

Your GCP account needs the following roles (or equivalent custom roles):

• roles/viewer (basic read access)
• roles/compute.viewer (Compute Engine resources)
• roles/storage.objectViewer (Cloud Storage)
• roles/bigquery.user (BigQuery)
• roles/cloudsql.viewer (Cloud SQL)
• roles/cloudfunctions.viewer (Cloud Functions)
• roles/run.viewer (Cloud Run)
• roles/container.viewer (GKE)
• roles/logging.viewer (Cloud Logging)

Security Features

• Local Credentials: Uses your local GCP authentication
• No External Access: All operations run locally
• Principle of Least Privilege: Only requests necessary permissions
• Secure by Default: No credentials stored or transmitted

🐛 Troubleshooting

Common Issues

Authentication Errors

# Re-authenticate with GCP
gcloud auth application-default login

# Verify access
gcloud projects list

Permission Denied

• Verify your IAM roles include the required permissions
• Check that APIs are enabled in your GCP project

Server Not Starting

• Ensure Node.js v18+ is installed
• Verify GCP credentials are configured
• Check the server logs for specific errors

Debug Mode

Enable debug logging:

export LOG_LEVEL=debug
npx gcp-mcp-server

🤝 Contributing

We welcome contributions! Here's how to get started:

1. Fork the repository
2. Create a feature branch: git checkout -b feature/amazing-feature
3. Make your changes and add tests
4. Run the test suite: npm test
5. Commit your changes: git commit -m 'Add amazing feature'
6. Push to the branch: git push origin feature/amazing-feature
7. Open a Pull Request

Development Guidelines

• Follow TypeScript best practices
• Add tests for new functionality
• Update documentation for new features
• Follow conventional commit messages
• Ensure all tests pass before submitting

📄 License

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

🙏 Acknowledgments

• Built on the Model Context Protocol
• Uses Google Cloud Client Libraries
• Inspired by the amazing MCP ecosystem

Made with ❤️ for the AI and Cloud communities

For support, feature requests, or bug reports, please open an issue on GitHub.