---
layout: default
title: Home
description: Production-ready Model Context Protocol server for Google Cloud Dataproc operations
permalink: /
---
# Dataproc MCP Server
[](https://badge.fury.io/js/%40dipseth%2Fdataproc-mcp-server)
[](https://npmjs.org/package/@dipseth/dataproc-mcp-server)
[](https://github.com/dipseth/dataproc-mcp/actions)
[](https://coveralls.io/github/dipseth/dataproc-mcp?branch=main)
[](https://opensource.org/licenses/MIT)
[](https://nodejs.org/)
[](https://www.typescriptlang.org/)
[](https://modelcontextprotocol.io/)
A production-ready Model Context Protocol (MCP) server for Google Cloud Dataproc operations with intelligent parameter injection, enterprise-grade security, and comprehensive tooling. Designed for seamless integration with **Roo (VS Code)**.
## 🚀 Quick Start
### **Recommended: Roo (VS Code) Integration**
Add this to your Roo MCP settings:
```json
{
"mcpServers": {
"dataproc": {
"command": "npx",
"args": ["@dipseth/dataproc-mcp-server@latest"],
"env": {
"LOG_LEVEL": "info"
}
}
}
}
```
### **With Custom Config File**
```json
{
"mcpServers": {
"dataproc": {
"command": "npx",
"args": ["@dipseth/dataproc-mcp-server@latest"],
"env": {
"LOG_LEVEL": "info",
"DATAPROC_CONFIG_PATH": "/path/to/your/config.json"
}
}
}
}
```
## 📋 Configuration
### Project-Based Configuration
The server supports a project-based configuration format:
```yaml
# profiles/@analytics-workloads.yaml
my-company-analytics-prod-1234:
region: us-central1
tags:
- DataProc
- analytics
- production
labels:
service: analytics-service
owner: data-team
environment: production
cluster_config:
# ... cluster configuration
```
### Authentication Methods
For detailed information on authentication methods, refer to the [Authentication Implementation Guide](AUTHENTICATION_IMPLEMENTATION_GUIDE.md).
### Environment Variables
| Variable | Description | Default |
|----------|-------------|---------|
| `DATAPROC_CONFIG_PATH` | Path to configuration file | `config/server.json` |
| `LOG_LEVEL` | Logging level (debug, info, warn, error) | `info` |
| `GOOGLE_APPLICATION_CREDENTIALS` | Path to service account key | - |
| `DATAPROC_PROJECT_ID` | Default GCP project ID | - |
| `DATAPROC_REGION` | Default Dataproc region | `us-central1` |
### Configuration File Structure
```json
{
"projectId": "your-gcp-project",
"region": "us-central1",
"authentication": {
"type": "service_account_impersonation",
"serviceAccountEmail": "dataproc-service@project.iam.gserviceaccount.com",
"impersonationChain": ["intermediate@project.iam.gserviceaccount.com"]
},
"defaultParameters": {
"numWorkers": 2,
"machineType": "n1-standard-4",
"diskSize": 100
},
"profiles": {
"development": {
"numWorkers": 2,
"machineType": "n1-standard-2"
},
"production": {
"numWorkers": 10,
"machineType": "n1-standard-8"
}
}
}
```
## 🔧 MCP Client Integration
### Claude Desktop
```json
{
"mcpServers": {
"dataproc": {
"command": "npx",
"args": ["@dataproc/mcp-server"],
"env": {
"LOG_LEVEL": "info"
}
}
}
}
```
### Roo (VS Code)
```json
{
"mcpServers": {
"dataproc-server": {
"command": "npx",
"args": ["@dataproc/mcp-server"],
"env": {
"LOG_LEVEL": "info",
"DATAPROC_CONFIG_PATH": "./config/server.json"
}
}
}
}
```
## 📚 Documentation
- **[Quick Start Guide](./QUICK_START.md)** - Get started in 5 minutes
- **[API Reference](./API_REFERENCE.md)** - Complete tool documentation
- **[Configuration Examples](./CONFIGURATION_EXAMPLES.md)** - Real-world configurations
- **[Security Guide](./SECURITY_GUIDE.md)** - Best practices and compliance
- **[Installation Guide](./INSTALLATION_GUIDE.md)** - Detailed setup instructions
## 🛠️ Key Features
- **🎯 60-80% Parameter Reduction** - Intelligent default injection
- **🔐 Enterprise Security** - Service account impersonation, credential management
- **📊 Multi-Environment Support** - Dev/staging/production configurations
- **⚡ Async Query Tracking** - Real-time job monitoring and results
- **🔄 Auto-Cleanup** - Intelligent resource management
- **📈 Performance Monitoring** - Built-in metrics and health checks
## 🤝 Support
- **GitHub Issues**: [Report bugs and request features](https://github.com/dipseth/dataproc-mcp/issues)
- **Documentation**: [Complete documentation](https://dipseth.github.io/dataproc-mcp/)
- **NPM Package**: [Package information](https://www.npmjs.com/package/@dataproc/mcp-server)
## 📄 License
This project is licensed under the MIT License - see the [LICENSE](https://github.com/dipseth/dataproc-mcp/blob/main/LICENSE) file for details.
---
Built with ❤️ for the [Model Context Protocol](https://modelcontextprotocol.io/) ecosystem.
