What is Mcp Crash Course

MCP Crash Course is a comprehensive repository designed to teach the fundamentals and advanced concepts of the Model Context Protocol (MCP), which connects AI applications powered by Large Language Models (LLMs) to external tools and data sources.

Use cases

Use cases for MCP include developing AI applications that require real-time data processing, integrating different AI tools, and creating scalable applications using containerization.

How to use

To use the MCP Crash Course, clone the repository and navigate through the branches that cover specific MCP features or concepts. Each branch contains commits ordered chronologically to facilitate step-by-step learning.

Key features

Key features include a branch-based structure for learning, topics covering Server-Sent Events (SSE), integration with LangChain adapters, and Docker containerization for MCP applications.

Where to use

MCP can be used in various fields such as AI development, data science, and software engineering, particularly where context-aware AI systems are needed.

MCP Crash Course 🚀

Welcome to the MCP Crash Course! This repository is designed to teach you the fundamentals and advanced concepts of the Model Context Protocol (MCP) in a hands-on way.

What is MCP? 💡

The Model Context Protocol (MCP) helps connect AI-agentic applications powered by Large Language Models (LLMs) to external tools and data sources, enabling more capable and context-aware AI systems.

How it Works 🤔

This repository uses a unique branch-based structure for learning:

1. Each project/* branch covers a specific MCP feature or concept.
2. Within each branch, commits are ordered chronologically. Follow the commits one by one to learn the topic step-by-step.

Simply check out the branch for the topic you want to learn and walk through the commits!

Available Topics (Branches) 📚

Here are the topics currently available:

• project/sse: Learn how to implement Server-Sent Events (SSE) with MCP.
• project/langchain-mcp-adapters: Explore integrating MCP with LangChain adapters.
• project/docker-mcp: Understand how to containerize your MCP applications using Docker.

More topics might be added, so keep an eye out!

Prerequisites 🛠️

Before you start, make sure you have the following installed:

• 🐍 Python (version 3.10 or higher)
• 📦 uv (the fast Python package installer and resolver)
• ✨ Cursor IDE
• ☁️ Claude Desktop

Getting Started ▶️

1. Clone the repository:

   git clone https://github.com/emarco177/mcp-crash-course.git
   cd mcp-crash-course
   

2. Choose a topic and check out the branch:

   # Example for the SSE topic
   git checkout project/sse
   

3. Follow the commits: Use git log --oneline --reverse to see the chronological list of commits for the branch. Then, use git checkout <commit_hash> or your Git client to step through the history and learn.

Contributing 🤝

Contributions are welcome! If you’d like to add a new topic or improve an existing one:

1. Fork the repository.
2. Create a new branch for your feature following the naming convention: project/your-mcp-feature-name.
3. Make your changes, ensuring each commit represents a logical step in the learning process.
4. Open a Pull Request against the main branch.

License 📄

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.

Happy learning! 🎉