Contact Us

Intermediate course

MCP Crash Course: Complete Model Context Protocol in a Day

Build, Connect, Deploy: Master MCP Servers, MCP Clients, Tools & Resources for Powerful LLM Applications

Rating: 4.64,123 ratings37,005 students8.5 total hours90 lectures
Open course in DoJo Back to courses
MCP Crash Course: Complete Model Context Protocol in a Day Intermediate

Course facts

  • Last updated 04/2026
  • English English [Auto], Bulgarian [Auto] , 16 more
  • Instructor: Eden Marco
  • practical AI capability and workflow improvement

What you'll learn

Practical outcomes

  • Model Context Protocol (MCP) Theory
  • Model Context Protocol (MCP) Servers
  • Model Context Protocol (MCP) Clients
  • Model Context Protocol (MCP) Tools, Resources, Prompts
  • MCP Security

Curriculum

17 sections • 90 lectures • 8h 30m total length

Welcome & Course Overview6 lectures • 19min
  1. Course Objectives04:27
  2. About Me01:10
  3. Why Do We Need MCP? Solving the AI Agent Integration Problem04:48
  4. What is MCP? Live Demo with Claude & Cursor05:47
  5. Course Resources00:06
  6. Course Community02:32
Hello World MCP- Configuring Pre Built MCP Servers (Weather Server)8 lectures • 43min
  1. Clone + Compile a Pre Built MCP Server08:50
  2. Cursor MCP Documentation Overview05:56
  3. Configure Cursor with a local MCP Server06:56
  4. Configure Claude Desktop with a local MCP Server05:17
  5. Recap01:11
  6. Exposing Tools From MCP Servers (Hello World Example) - Part 1/205:04
  7. Exposing Tools From MCP Servers (Hello World Example) - Part 2/206:34
  8. NodeJS Implementation Overview02:45
  9. Recap Quiz 4 questions
Model Context Protocol Architecture3 lectures • 19min
  1. MCP Architecture Concepts: Hosts, Servers, Clients, and the Protocol07:20
  2. Understanding MCP Transport Layers: STDIO vs. Streamable HTTP07:38
  3. Server VS FastMCP VS FastMCP 2.004:08
MCP Servers4 lectures • 29min
  1. The Theory of MCP Servers08:44
  2. MCP Inspector (Observability)02:54
  3. LLM.txt05:33
  4. mcpdoc12:13
Building, Securing, and Containerizing an MCP Server10 lectures • 1hr 1min
  1. What are we building?05:15
  2. Project Setup: Virtual Environment ,Cursor Rules, MCP Docs Indexing05:51
  3. Vibe Coding an MCP Server that exposes a Shell (terminal) Tool11:10
  4. Exposing a resource in our MCP Server04:24
  5. Beware the MCP Server Supply Chain: Hacking Demo via Dependencies06:38
  6. AI Agent Security Risk: Exploiting Permissive Tools (Demo)02:49
  7. Why Use Docker for Your MCP Server? Key Advantages Explained01:49
  8. Lets Wrap our MCP Server to run in a Docker Container09:12
  9. Integrating an MCP running in a Container05:23
  10. Testing our Containerized Container + Security Remediation08:48
  11. Docker Quiz 4 questions
Connecting LLM Clients: Tool Calling Mechanisms and MCP10 lectures • 1hr 1min
  1. Intro00:56
  2. How LLMs REALLY Use Tools: Understanding Tool Calling05:06
  3. Bridging the Gap: The LangChain MCP Adapter Explained04:23
  4. Inside the MCP Protocol: How Components Interact09:00
  5. Practice Test: LLM Tool Calling, MCP Protocol & LangChain Integration 6 questions
  6. [Hands On] Setting Up Our Environment10:01
  7. [Hands On] Setting Up Our Environment- Cheat Sheet00:17
  8. [Hands On] SSE MCP05:43
  9. [Hands On] Imports08:46
  10. [Hands On] Connecting MCP Client to Server & Initializing Session with LangGraph08:45
  11. [Hands On] Under the Hood of MCP with LangSmith Tracing08:13
Prompts and Reources8 lectures • 48min
  1. MCP Prompts and Resources High Level04:43
  2. Prompts13:30
  3. Introduction To Resources00:34
  4. Resources Theory03:44
  5. Pokemon Resources Implementation08:55
  6. MCP Resources in Claude Desktop & Cursor03:50
  7. Installing Claude Code04:46
  8. MCP Resources In Claude Code08:14
I LOVE SSE Servers5 lectures • 18min
  1. intro01:10
  2. SSE Recap02:42
  3. MultiServerMCPClient: Unifying Tool Access Across Different Transports05:45
  4. Awesome MCP Servers05:23
  5. Integrating Playwright for browser automation02:34
Secure, Cloud native MCP Servers: Auth0 + Cloudflare Workers16 lectures • 1hr 19min
  1. Introduction: How to Bridge Local AI Apps and Secure Cloud APIs with MCP Servers03:32
  2. E2E Demo: Secure MCP Server, Auth0 Auth & API Call02:27
  3. [Hands On] Setting Up Our Environment07:35
  4. [Hands On] Code Walkthrough: Todos API with Hono & JWT Middleware04:14
  5. [Hands On] Walkthrough: jwt.ts Middleware and Auth0 Setup02:52
  6. Configuring Auth0 API: Permissions, Offline Access & Local Vars06:49
  7. Cloudflare Worker Deployment Walkthrough04:56
  8. Building Secure AI Connections with MCP, Auth0 & Cloudflare Quiz 5 questions
  9. Remote MCP Server: Auth0 App, Callback URLs & KV Namespace07:57
  10. OAuth Roles & Flow Explained (Remote MCP Server)06:32
  11. OAuth Flow Deep Dive with Remote MCP Server & Inspector - Part 104:52
  12. OAuth Flow Deep Dive with Remote MCP Server & Inspector - Part 205:03
  13. [Optional] Understanding Auth Scopes & Fixing API Authorization Errors03:52
  14. Quick Check In01:19
  15. Deploying an MCP Server to Cloudflare Workers05:32
  16. [Optional] MCP Server Architecture & OAuth Flow Quiz 7 questions
  17. Testing a Remote MCP Server with Cloudflare AI LLM Playground & Auth003:35
  18. Connecting Claude Desktop to a Remote MCP Server via Proxy07:31
MCP Interview0 lectures • 0min
  1. MCP Interview
Agent 2 Agent1 lecture • 2min
  1. Introduction to A2A - Agent to Agent Protocol01:56
FastMCP 2.0 featuring Jeremaiah Lowin5 lectures • 35min
  1. How FastMCP Began: Jeremiah's Journey and the Need for Better MCP Tools05:56
  2. Why FastMCP is Popular: Responsiveness & High-Level Tooling07:46
  3. The MCP Economy & FastMCP Cloud: MCPs as the New SaaS04:15
  4. Building Your Own Composed MCP Server from APIs09:55
  5. The Future of Software Engineers: Humans, Agents, and Portable Context07:06
Advanced Topics In MCP3 lectures • 23min
  1. [Theory] Sampling07:37
  2. [Theory] MCP Registry05:14
  3. [Hands On] Context Engineering: Optimizing MCP in Claude Code10:30
Whats Wrong with MCP2 lectures • 22min
  1. The 4 Major Drawbacks of the Model Context Protocol06:31
  2. Code Mode By Cloudflare15:57
Agent Skills4 lectures • 38min
  1. Intro02:08
  2. The GIST of Skills13:36
  3. Custom Skills with Auxiliary Scripts18:14
  4. Skills VS MCP03:52
Industry Insights: Building Autonomous Agents with Assaf Elovic4 lectures • 12min
  1. MCP --> Skills ?03:07
  2. Autonomous Learning with skyll.app03:54
  3. Better Coding and Overcoming AI Bias03:43
  4. Security Implications of Dynamic Skills01:30
Bonus1 lecture • 1min
  1. Bonus00:22

Who it is for

  • Advanced GenAI Users
  • Data Scientists
  • Application Developers
  • AI Engineers

Course description

Overview

This course contains the use of artificial intelligence :) Please note that this is not a course for beginners. This course assumes that you have a background in software engineering and are proficient in Python. I will be using Cursor IDE but you can use any editor you'd like since we only use basic feature of the IDE like debugging and running scripts . Ideal students are software developers / data scientists What is the Model Context Protocol? The Model Context Protocol (MCP) is an open-source standard, introduced by Anthropic in 2024, that allows AI models to seamlessly connect with external data sources, tools, and software systems Architecture Components MCP Hosts: Programs like Claude Desktop, Cursor, Windsurf, or AI tools that want to access data through MCP MCP Clients: Protocol clients that maintain 1:1 connections with servers (Content ETA April) MCP Servers: Lightweight programs that each expose specific capabilities through the standardized Model Context Protocol Local Data Sources: Your computer's files, databases, and services that MCP servers can securely access (Content ETA End of March) Remote Services: External systems available over the internet (e.g., through APIs) that MCP servers can connect to (Content ETA End of March) Authenticaiton Key Capabilities Resources: Components that expose data and content from your servers to LLMs Prompts: Functionality to create reusable prompt templates and workflows Tools: Features that enable LLMs to perform actions through your server Sampling: Capability that lets your servers request completions from LLMs Transports: MCP's communication mechanism between clients and servers Topic Covered: MCP + Agent Security best practices Containerizing MCP Servers Protocol Flow MCP + Docker MCP + LangChain OAuth 2.0 with MCP featuring Auth0 MCP Deployment (featuring Cloudflare) A2A - Agent 2 Agent Protocol (WIP)

Instructor

Eden Marco

Eden Marco LLM Specialist @ Google Cloud I’m a passionate Software Engineer with years of experience in back-end development and cloud architecture. I was one of the first engineers at Orca Security, where I helped shape the company’s core technology, and today I work as a GenAI Architect at Google Cloud, helping organizations design and deploy advanced generative AI and cloud-native solutions. I’m also proud to be a LangChain Ambassador, actively contributing to the open-source community and helping developers build powerful LLM applications using the LangChain ecosystem. I hold a Bachelor’s degree in Computer Science from the Technion, and I’ve always had a deep passion for teaching and mentorship. I taught Functional Programming and Introduction to Computer Science at Reichman University, where I guided the next generation of software engineers. My courses are built on real-world experience and designed to give you practical, production-ready skills—whether you’re just getting started or looking to level up.