Model Context Protocol Guidebook - A comprehensive guide to MCP with hands-on projects and examples
Model Context Protocol (MCP) Guidebook
A comprehensive learning resource for mastering the Model Context Protocol
This documentation website provides a structured, hands-on learning path for understanding and implementing MCP - the open standard for connecting AI systems to external data sources and tools.
📚 What's Inside
This guidebook covers 11 progressive sections:
- HTTP Theory - Foundational HTTP concepts
- REST APIs - RESTful architecture principles
- JSON-RPC 2.0 - The protocol MCP uses for communication
- Fundamental Primitives - Core MCP building blocks (Tools, Resources, Prompts)
- Capabilities & Transport - Advanced MCP features (Sampling, Logging, Roots)
- OpenAI Agents SDK - Integration with OpenAI's agent framework
- MCP Specifications - Official protocol specifications
- Hands-On Projects - Practical implementation exercises
- OAuth 2.1 - Authentication and security patterns
- Extra Stateful Capabilities - Advanced features
- Extra Resources - Supplementary materials and references
🎯 Content Source
All course content is sourced from the Panaversity Learn Agentic AI Repository, specifically from their comprehensive MCP learning materials.
🚀 Quick Start
Prerequisites
- Node.js >= 20.0
- npm (comes with Node.js)
Installation
npm install
Local Development
npm start
This command starts a local development server and opens up a browser window at http://localhost:3000/learn-mcp/. Most changes are reflected live without having to restart the server.
Build
npm run build
This command generates static content into the build directory and can be served using any static contents hosting service.
Serve Production Build Locally
npm run serve
Test your production build locally before deploying.
📦 Deployment
GitHub Pages Deployment
Using SSH:
USE_SSH=true npm run deploy
Using HTTPS:
GIT_USER=<Your GitHub username> npm run deploy
This command builds the website and pushes to the gh-pages branch.
Other Hosting Platforms
The built static files in the build/ directory can be deployed to:
- Vercel
- Netlify
- AWS S3 + CloudFront
- Azure Static Web Apps
- Any static hosting service
🛠️ Built With
- Docusaurus 3.9.2 - Modern static site generator
- React 19 - UI framework
- MDX - Markdown with JSX support
- Prism - Syntax highlighting (GitHub light theme, Dracula dark theme)
🎨 Features
- ✅ 11 structured learning sections with progressive complexity
- ✅ Dark/Light theme support with system preference detection
- ✅ Built-in search for quick content discovery
- ✅ Responsive design optimized for mobile, tablet, and desktop
- ✅ Syntax highlighting for Python, TypeScript, JSON, Bash
- ✅ External resource links to official MCP documentation
- ✅ Progressive learning path from basics to advanced topics
📖 Documentation Structure
docs/
├── intro.md # MCP introduction
├── 01-http-theory/ # HTTP fundamentals
├── 02-rest/ # REST API principles
├── 03-json-rpc/ # JSON-RPC 2.0 protocol
├── 04-fundamental-primitives/ # Tools, Resources, Prompts
├── 05-capabilities-and-transport/ # Advanced MCP features
├── 06-openai-agents-sdk/ # OpenAI integration
├── 07-mcp-specs/ # MCP specifications
├── 08-projects/ # Hands-on projects
├── 09-oauth/ # OAuth 2.1 authentication
├── 10-extra-stateful-capabilities/ # Advanced capabilities
└── 11-extra/ # Additional resources
🤝 Contributing
To contribute to the source material, please visit the Panaversity repository and follow their contribution guidelines.
📄 License
Please refer to the source repository for licensing information.
🔗 Links
- Source Content: Panaversity MCP Materials
- Official MCP Spec: Model Context Protocol
- Docusaurus: Documentation
Built with ❤️ using Docusaurus