Project Tracker MCP Server
A TypeScript-based REST API that integrates project and task management with MCP (Model Context Protocol), allowing users to manage projects and tasks through natural language interactions.
Tools
natural_language_query
Process natural language queries about projects and tasks with intelligent parsing
workload_analysis
Analyze workload for a specific person with detailed insights
risk_assessment
Assess project risks and provide recommendations
README
Project Tracker API with MCP Integration
A TypeScript-based REST API for project and task management with MCP (Model Context Protocol) integration.
👨💻 Author
Jatinder (Jay) Bhola - Engineering Leader & Tech Lead
- 🏠 Location: Toronto, ON, Canada
- 🎯 Expertise: Cloud-Native & Event-Driven Architectures, Building Scalable Systems
- 🔗 Connect: GitHub | LinkedIn
"Engineering leader with 10+ years of experience improving developer workflows and scaling cloud-native systems. Proven track record in leading and delivering high-impact, customer-facing platforms and empowering engineering teams to build fast, resilient web applications."
Technology Stack
- Node.js 18+ with TypeScript
- Express.js framework
- PostgreSQL with Prisma ORM
- Redis for caching
- Zod for validation
- Jest for testing
- Swagger/OpenAPI for documentation
- MCP SDK for agent integration
Project Structure
project-tracker-api/
├── src/
│ ├── controllers/ # API route handlers
│ ├── services/ # Business logic layer
│ ├── models/ # Database models/schemas
│ ├── middleware/ # Validation, error handling
│ ├── utils/ # Helper functions and date utilities
│ ├── mcp/ # MCP server implementation
│ ├── config/ # Database and app configuration
│ └── test/ # Test setup and utilities
├── prisma/ # Database schema and migrations
├── docs/ # API documentation and setup guides
└── scripts/ # Setup and seed scripts
Architecture Overview

Getting Started
Quick Setup (Recommended)
For the interviewer or anyone who wants to get everything running quickly:
# One-command setup (recommended)
npm run setup
This will:
- ✅ Install all dependencies
- ✅ Start PostgreSQL and Redis services
- ✅ Create databases and run migrations
- ✅ Seed test data
- ✅ Build the project
- ✅ Run tests to verify everything works
- ✅ Create environment configuration
After setup, run the demo to see all features:
# Start the API server in one terminal
npm run dev
# Run the demo in another terminal
npm run demo
Manual Setup
If you prefer to set up manually:
- Clone the repository
- Install dependencies:
npm install - Initialize the database:
# Create databases createdb taskflow createdb taskflow_test # Generate Prisma client npm run prisma:generate # Run migrations npm run prisma:migrate - Seed test data:
node scripts/seed-test-data.js - Build the project:
npm run build - Start the development server:
npm run dev - Test MCP Integration:
# Test MCP server npm run mcp:test # Interactive testing with MCP Inspector npm run mcp:inspector
Database Configuration
Environment Variables
Create a .env file with the following variables:
# Main database
DATABASE_URL="postgresql://username:password@localhost:5432/taskflow"
# Test database (separate from main)
TEST_DATABASE_URL="postgresql://username:password@localhost:5432/taskflow_test"
# Redis configuration
REDIS_URL="redis://localhost:6379/0"
TEST_REDIS_URL="redis://localhost:6379/1"
# Optional: Use main database for tests (not recommended for production)
USE_MAIN_DB_FOR_TESTS=false
Setting Up Test Database
-
Create Test Database:
createdb taskflow_test -
Run Migrations on Test Database:
TEST_DATABASE_URL="postgresql://localhost:5432/taskflow_test" npx prisma migrate deploy -
Verify Setup:
npm run test:verify-env
🤖 MCP Integration
For detailed MCP documentation and architecture, see docs/ASSESSMENT_DEMONSTRATION.md.
Available Scripts
Development
-
npm run dev- Start development server with hot reload -
npm run build- Build for production -
npm start- Start production server -
npm run format- Format code with Prettier -
npm run lint- Run ESLint [TODO]
Database Management
npm run prisma:generate- Generate Prisma clientnpm run prisma:migrate- Run database migrationsnpm run prisma:studio- Open Prisma Studio for main databasenpm run prisma:studio:test- Open Prisma Studio for test databasenpm run prisma:studio:main- Open Prisma Studio for main database
Testing
npm test- Run all testsnpm run test:unit- Run unit tests onlynpm run test:integration- Run integration tests onlynpm run test:coverage- Run tests with coverage reportnpm run test:watch- Run tests in watch modenpm run test:setup- Create test databasenpm run test:reset- Reset test database (drop, recreate, migrate)npm run test:verify-env- Verify environment variables
MCP Integration
npm run mcp:start- Start MCP servernpm run mcp:debug- Start MCP server in debug modenpm run mcp:test- Run unified MCP testsnpm run mcp:inspector- Start MCP Inspector for interactive testing
Testing
Test Architecture
The project uses a comprehensive testing setup with:
- Unit Tests: Test individual service methods and business logic
- Integration Tests: Test API endpoints and database interactions
- Test Utilities: Centralized test data builders and assertions
- Date Utils: Centralized date conversion utilities for consistent testing
Test Configuration
- Separate Test Database: Prevents accidental data loss
- Redis Isolation: Uses separate Redis database for tests
- Environment Detection: Automatic test environment setup
- Clean Test Data: Automatic cleanup between tests
Running Tests
# Run all tests
npm test
# Run specific test suites
npm run test:unit
npm run test:integration
# Debug environment setup
npm run test:verify-env
Test Utilities
The test suite includes centralized utilities:
- TestData: Builders for creating test projects and tasks
- Assertions: Common assertion helpers for date comparisons
- MockUtils: Utilities for mocking cache and service calls
- TestEnv: Environment detection and configuration
Test Database Management
# Quick setup
npm run test:setup
# Reset test database
npm run test:reset
# Verify environment
npm run test:verify-env
API Documentation
Once the server is running, visit /api/docs for the Swagger documentation with organized endpoints:
- Projects: CRUD operations for project management
- Tasks: CRUD operations for task management
Security and TODOs
Read more about the MUST HAVE security integration
License
Code has been produced with the help of Claude IDE
ISC
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.