ControlAI MCP - Enterprise AI Project Management Server

ControlAI MCP is a world-class, enterprise-grade AI project management solution built as a Model Context Protocol (MCP) server. It provides intelligent task management, multi-agent coordination, conflict resolution, and real-time project monitoring for AI agent ecosystems.

🌟 Features

✨ Intelligent Project Management

• 🧠 AI-Powered Task Analysis: Natural language processing for automatic task breakdown and categorization
• 📊 Smart Priority Assignment: Intelligent priority and complexity assessment
• 🎯 Automated Task Generation: Convert project descriptions into actionable tasks

🤖 Multi-Agent Coordination

• 🔄 Intelligent Agent Assignment: AI-driven task-to-agent matching based on capabilities
• ⚖️ Conflict Resolution: Automatic detection and resolution of resource conflicts
• 📈 Performance Optimization: Real-time optimization suggestions for better task distribution

🚀 Real-Time Monitoring

• 📡 WebSocket Updates: Live project status updates and notifications
• 📊 Interactive Dashboard: Real-time metrics and insights
• 🔍 Advanced Analytics: Project progress tracking and performance metrics

🛡️ Enterprise Grade

• 🏗️ Scalable Architecture: Built for high-performance multi-agent environments
• 🔒 Robust Data Management: SQLite with sql.js for reliable persistence
• 🌐 Cross-Platform: Works on Windows, macOS, and Linux
• 🔌 VS Code Integration: Native MCP protocol support for seamless IDE integration

🚀 Quick Start

Prerequisites

• Node.js 18.0.0 or higher
• TypeScript 5.0.0 or higher
• Azure OpenAI API access (for AI features)

Installation

# Clone the repository
git clone https://github.com/codai-ecosystem/codai-project.git
cd codai-project/packages/controlai-mcp

# Install dependencies
pnpm install

# Build the project
pnpm run build

Environment Configuration

Create a .env file in your project root:

# Azure OpenAI Configuration
AZURE_OPENAI_ENDPOINT=https://your-openai-instance.openai.azure.com/
AZURE_OPENAI_API_KEY=your-api-key-here
AZURE_OPENAI_DEPLOYMENT=gpt-4o

# ControlAI Configuration (Optional)
CONTROLAI_PORT=7001
CONTROLAI_HOST=localhost
CONTROLAI_DATABASE_PATH=/path/to/your/database
CONTROLAI_CORS_ORIGIN=*

Running the Server

# Development mode with hot reload
pnpm run dev

# Production mode
pnpm run start

# Run tests
pnpm run test

🛠️ Usage

1. MCP Integration

ControlAI MCP implements the Model Context Protocol, making it compatible with VS Code and other MCP-enabled tools.

VS Code Configuration

Add to your VS Code settings or MCP configuration:

{
  "mcps": {
    "controlai": {
      "command": "node",
      "args": ["path/to/controlai-mcp/dist/server.js"],
      "env": {
        "AZURE_OPENAI_ENDPOINT": "your-endpoint",
        "AZURE_OPENAI_API_KEY": "your-key"
      }
    }
  }
}

2. Available Tools

📝 create_project

Create a new project with intelligent analysis.

{
  "name": "E-commerce Website",
  "description": "Build a modern e-commerce platform with React, Node.js, and MongoDB",
  "priority": "high",
  "tags": ["web", "ecommerce", "fullstack"]
}

🔍 analyze_plan

Break down project plans into actionable tasks using AI.

{
  "projectId": "project-uuid",
  "plan": "Create a user authentication system with login, registration, password reset, and role-based access control"
}

🤖 register_agent

Register AI agents with specific capabilities.

{
  "name": "Senior Developer Agent",
  "type": "coding_agent",
  "capabilities": ["programming", "typescript", "react", "testing"],
  "workspaceId": "workspace-1",
  "maxConcurrentTasks": 3
}

📋 assign_task

Intelligently assign tasks to the most suitable agents.

{
  "taskId": "task-uuid",
  "agentId": "agent-uuid" // Optional - AI will suggest if omitted
}

📊 get_dashboard_data

Retrieve real-time dashboard metrics and insights.

{
  "workspaceId": "workspace-1"
}

3. WebSocket Real-Time Updates

Connect to the WebSocket server for live updates:

const ws = new WebSocket('ws://localhost:7001');

ws.on('message', (data) => {
  const message = JSON.parse(data);
  console.log(`Event: ${message.type}`, message.payload);
});

Event Types:

• project_created - New project added
• task_assigned - Task assigned to agent
• task_status_updated - Task progress update
• agent_registered - New agent joined
• plan_analyzed - Project plan broken down
• conflict_detected - Resource conflict identified

🏗️ Architecture

Core Components

┌─────────────────┐    ┌─────────────────┐    ┌─────────────────┐
│   MCP Server    │────│  HTTP/WS APIs   │────│   Dashboard     │
│    (Stdio)      │    │   (Express)     │    │   (Real-time)   │
└─────────────────┘    └─────────────────┘    └─────────────────┘
         │                       │                       │
         │              ┌─────────────────┐              │
         └──────────────│ CoordinationSvc │──────────────┘
                        └─────────────────┘
                               │
          ┌────────────────────┼────────────────────┐
          │                    │                    │
  ┌───────────────┐    ┌───────────────┐    ┌───────────────┐
  │ DatabaseService│    │  AI Service   │    │ WebSocket Mgr │
  │   (sql.js)     │    │ (Azure OpenAI)│    │  (Real-time)  │
  └───────────────┘    └───────────────┘    └───────────────┘

Data Flow

1. Project Creation: User creates project → AI analyzes → Tasks generated
2. Task Assignment: Task created → AI evaluates agents → Best match assigned
3. Status Updates: Agent reports progress → Database updated → WebSocket broadcast
4. Conflict Resolution: System detects conflicts → AI suggests solutions → Auto-resolve

📖 API Reference

MCP Tools

REST Endpoints

• GET /health - Health check
• WS / - WebSocket connection for real-time updates

🧪 Testing

# Run all tests
pnpm run test

# Run with coverage
pnpm run test:coverage

# Run in watch mode
pnpm run test:watch

🔧 Configuration

Environment Variables

Advanced Configuration

Create controlai.config.js:

export default {
  server: {
    port: 7001,
    host: 'localhost',
    cors: { origin: '*' }
  },
  database: {
    path: './data/controlai.db'
  },
  ai: {
    provider: 'azure-openai',
    deploymentName: 'gpt-4o'
  },
  websocket: {
    enabled: true,
    heartbeatInterval: 30000
  }
};

🛡️ Security

• ✅ Input validation with Zod schemas
• ✅ SQL injection prevention with prepared statements
• ✅ Environment variable protection
• ✅ CORS configuration
• ✅ Rate limiting ready (configurable)

📊 Performance

Benchmarks

• Task Creation: < 200ms (with AI analysis)
• Agent Assignment: < 100ms
• Database Queries: < 50ms
• WebSocket Broadcast: < 10ms
• Memory Usage: ~50MB base + data

Scalability

• Concurrent Agents: 1000+
• Projects: Unlimited
• Tasks per Project: 10,000+
• WebSocket Connections: 100+

🤝 Contributing

We welcome contributions! Please see our Contributing Guide for details.

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

📝 License

This project is licensed under the MIT License. See LICENSE for details.

🔗 Related Projects

• CODAI Ecosystem: Main Repository
• MemoRAI MCP: Memory management for AI agents
• Glass Browser: Web automation toolkit

📞 Support

• 📧 Email: support@codai.ro
• 💬 Discord: CODAI Community
• 🐛 Issues: GitHub Issues
• 📖 Docs: Documentation Site

🚀 Roadmap

• <input disabled="" type="checkbox"> Q1 2025: GitHub Integration
• <input disabled="" type="checkbox"> Q2 2025: Slack/Teams Integration
• <input disabled="" type="checkbox"> Q3 2025: Advanced Analytics Dashboard
• <input disabled="" type="checkbox"> Q4 2025: Multi-tenant Support