About MCP Prompt Playground
MCP Crash Course is a hands-on learning repository for MCP concepts. Topic-specific branches organize examples and commits so learners can follow implementation steps in sequence.
Key features
- 01Topic-specific project branches
- 02Chronological commits for step-by-step study
- 03Examples covering SSE, adapters, Docker, and prompts
Use cases
- 01Learning MCP implementation concepts
- 02Following an SSE implementation history
- 03Exploring MCP with LangChain adapters
- 04Studying MCP prompts with FastMCP 2.0
MCP support
The repository teaches MCP through branch-based examples, including SSE, LangChain adapters, Docker, and MCP Prompts. It is learning material rather than a described MCP server.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMCP 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:
- Each
project/*branch covers a specific MCP feature or concept. - 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.project/prompts: Learn how to implement and work with MCP Prompts, featuring FastMCP 2.0.
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 ▶️
- Clone the repository:
git clone https://github.com/emarco177/mcp-crash-course.git cd mcp-crash-course - Choose a topic and check out the branch:
# Example for the SSE topic git checkout project/sse - Follow the commits: Use
git log --oneline --reverseto see the chronological list of commits for the branch. Then, usegit 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:
- Fork the repository.
- Create a new branch for your feature following the naming convention:
project/your-mcp-feature-name. - Make your changes, ensuring each commit represents a logical step in the learning process.
- Open a Pull Request against the
mainbranch.
License 📄
This project is licensed under the Apache License 2.0 - see the LICENSE file for details.
Happy learning! 🎉
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.