MCP Server Demo

A demonstration Model Context Protocol (MCP) server that provides tools and resources for Java CI/CD workflows and GitLab CI template management.

📁 Repository Structure

mcp-server-demo/
├── main.py                 # Main entry point for the MCP server
├── server.py               # MCP server implementation with tools and resources
├── pyproject.toml          # Python project configuration and dependencies
├── uv.lock                 # Dependency lock file
├── .gitlab-ci.yml          # GitLab CI configuration (template-based)
├── ci-templates/           # GitLab CI template resources
│   ├── build.gitlab-ci.yml
│   ├── sast-scanner.gitlab-ci.yml
│   ├── sca-scanner.gitlab-ci.yml
│   └── build-image.gitlab-ci.yml
└── README.md               # This file

Related MCP server: Multi-service MCP Server

🚀 Features

MCP Server Tools

• Mathematical Operations: sum_two_numbers() - Add two integers

• CI/CD Template Management: Access to GitLab CI template resources

• Java Build Tools: Maven-based build commands and configurations

• Security Scanning: SAST and SCA scanning capabilities

• Docker Operations: Image building and registry management

• Deployment Automation: Environment-specific deployment commands

GitLab CI Templates

• Build Templates: Java and Python build configurations

• Security Scanning: SAST and SCA scanning templates

• Docker Integration: Image build and push templates

• Reusable Components: Template-based CI/CD pipeline generation

🛠️ Setup Instructions

Prerequisites

• Python 3.13 or higher

• uv package manager

Installation

1. Clone the repository

   git clone <repository-url>
   cd mcp-server-demo

2. Install dependencies

   uv sync

3. Verify installation

   uv run python --version

🚀 Starting the MCP Server

Method 1: Using uv run

uv run mcp dev main.py

Method 2: Direct execution

uv run python main.py

Method 3: Using the MCP CLI

uv run mcp run main.py

🔧 Configuration

Environment Variables

The server uses standard MCP configuration. No additional environment variables are required for basic operation.

GitLab CI Templates

The ci-templates/ directory contains reusable GitLab CI templates:

• build.gitlab-ci.yml - Build job templates for Java and Python

• sast-scanner.gitlab-ci.yml - Static Application Security Testing templates

• sca-scanner.gitlab-ci.yml - Software Composition Analysis templates

• build-image.gitlab-ci.yml - Docker image build and push templates

📋 Usage Examples

Using the MCP Server Tools

1. Add two numbers

   result = sum_two_numbers(5, 3)  # Returns 8

2. Access CI templates

   # Access build template
   build_template = read_build_ci_file()
   
   # Access SAST scanner template
   sast_template = read_sast_scanner_ci_file()

Generating GitLab CI Files

The server provides resources to help generate GitLab CI configurations using the available templates:

1. Java Application CI

   • Uses .build-java template

   • Includes SAST and SCA scanning

   • Docker image building and deployment

2. Python Application CI

   • Uses .build-python template

   • Includes security scanning

   • Container deployment capabilities

🔍 Available Resources

File Resources

• file://ci-templates/build.gitlab-ci.yml - Java and Python build templates

• file://ci-templates/sast-scanner.gitlab-ci.yml - SAST scanning templates

• file://ci-templates/sca-scanner.gitlab-ci.yml - SCA scanning templates

• file://ci-templates/build-image.gitlab-ci.yml - Docker build templates

Dynamic Resources

• greeting://{name} - Personalized greeting messages

• pipeline://{project_name} - CI/CD pipeline status

• project://{project_name} - Project information

• template://{template_name} - Template information

🧪 Testing

Run the server in development mode

uv run mcp dev main.py

Test individual tools

uv run python -c "from server import sum_two_numbers; print(sum_two_numbers(10, 5))"

📦 Dependencies

Core Dependencies

• mcp[cli]>=1.11.0 - Model Context Protocol server and CLI tools

Development Dependencies

• Python 3.13+ for modern language features

• uv for fast dependency management

🤝 Contributing

1. Fork the repository

2. Create a feature branch

3. Make your changes

4. Add tests if applicable

5. Submit a pull request

📄 License

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

🆘 Troubleshooting

Common Issues

1. MCP server not starting

   • Ensure Python 3.13+ is installed

   • Verify dependencies with uv sync

   • Check for port conflicts

2. Template access issues

   • Verify ci-templates/ directory exists

   • Check file permissions

   • Ensure template files are properly formatted

3. GitLab CI generation problems

   • Verify template syntax

   • Check for missing template dependencies

   • Ensure proper job inheritance

Getting Help

• Check the MCP documentation

• Review the template files in ci-templates/

• Examine the server implementation in server.py

🔗 Related Links

• Model Context Protocol

• GitLab CI/CD Documentation

• uv Package Manager