# Building Your First MCP Server and Client Canonical URL: ## Overview This hands-on workshop introduces the Model Context Protocol (MCP) through a practical, end-to-end build. Participants learn what MCP is, why it matters, and how to design MCP servers for AI agents rather than treating them as simple REST API wrappers. Using Python and FastMCP, participants build a working MCP server around the SpaceX API, test it locally, connect it to an MCP-compatible host, and create a minimal MCP client that can discover and call server tools. The course balances implementation with design judgment. Alongside building a functioning server and client, participants learn how to reduce tool sprawl, design around agent workflows, manage context-window costs, and create tool descriptions and outputs that work well for large language models. ## What you'll learn - Explain MCP’s purpose and describe the host-client-server architecture. - Distinguish between tools, resources, and prompts, and when to use each. - Design MCP servers around agent workflows, outcomes, and context-window limits. - Recognize common MCP design anti-patterns, including endpoint-for-endpoint REST wrappers. - Build and test a local MCP server in Python using FastMCP, MCP Inspector, and an MCP-compatible host. - Build a minimal MCP client that connects to a server, lists tools, and calls them. ## Curriculum #### Module 1: Introduction to MCP and Agent-Facing Design - Examine the integration problem MCP is designed to solve and how it standardizes connections between AI applications and external tools, resources, and workflows. - Review MCP architecture, including the roles of the host, client, and server. - Explore how context windows affect tool design and output design. - Identify the three main server primitives: tools, resources, and prompts. #### Module 2: Why Many MCP Servers Perform Poorly - Analyze why MCP servers should not be designed as one-to-one REST wrappers and the cost of excessive tool discovery for agents. - Evaluate why agent iteration is slower and more expensive than human trial and error. - Assess how output format and schema size affect context efficiency. - Apply principles of outcome-based tool design to improve server performance. #### Module 3: Build an MCP Server with FastMCP - Initialize a new FastMCP project, create a simple tool, and inspect the server with the MCP Inspector. - Review the SpaceX API and identify likely user workflows for tool design. - Build a naive version to observe anti-patterns, then refactor into a smaller, more effective toolset. - Format outputs for LLM consumption using Markdown and improve tool descriptions, matching logic, and error handling. #### Module 4: Build a Minimal MCP Client - Connect to the server from a local client, discover tools via tools/list, and call tools programmatically. - Examine the handshake and tool-call lifecycle between client and server. - Observe how an LLM-driven host uses the same pattern to interact with MCP servers. #### Module 5: Deployment, Security, and Ecosystem Overview - Transition from local stdio development to remote deployment, including remote transport and hosting basics. - Review security and authorization considerations for remote MCP servers. - Survey the broader MCP ecosystem, including documentation, SDKs, and registries. ## Schedule - Oct 1, 2026 8:00am–12:00pm — Live Online - Oct 29, 2026 1:00pm–5:00pm — Live Online - Nov 24, 2026 8:00am–12:00pm — Live Online ## Instructors ### Dan Rodney — School Director, Instructor, & Senior Course Developer Dan Rodney has been a designer and web developer for over 20 years, creating coursework and leading innovative training initiatives at Noble Desktop. He teaches courses covering Figma, HTML & CSS, Adobe Photoshop, InDesign, Illustrator, and Power BI. Dan has also been at the forefront of integrating AI into design and business workflows, spearheading Noble Desktop’s latest AI course offerings. In addition to teaching and curriculum development, he writes custom scripts for InDesign (Make Book Jacket, Proper Fraction Pro, and more) and works with automation and AI-driven tools in his free time. You can find Dan on X (Twitter), LinkedIn, Facebook, and at danrodney.com. Learn more about [Dan Rodney's](/dan-rodney) background and expertise. ### Garfield Stinvil — Senior Instructor Garfield is an experienced software trainer with over 16 years of real-world professional experience. He started as a data analyst with a Wall Street real estate investment company & continued working in the professional development department at New York Road Runners Organization before working at Noble. He enjoys bringing humor to whatever he teaches and loves conveying ideas in novel ways that help others learn more efficiently. Since starting his professional training career in 2016, he has worked with several corporate clients including Adobe, HBO, Amazon, Yelp, Mitsubishi, WeWork, Michael Kors, Christian Dior, and Hermès. Outside of work, his hobbies include rescuing & archiving at-risk artistic online media using his database management skills. ### Mourad Kattan — Program Director & Instructor Mourad Kattan is an instructor and Program Director of Business, Finance, & Excel at Noble Desktop, teaching classes and designing courses in Excel, finance, accounting, and financial modeling. Before Noble Desktop, Mourad worked as a financial analyst at Credit Suisse and H/2 Capital Partners. In those positions, he used advanced analytical and financial skills to evaluate a variety of investments. Mourad graduated from the University of Pennsylvania summa cum laude and is part of the Beta Gamma Sigma honor society. Learn more about [Mourad Kattan's](/mourad-kattan) background and expertise. ### Christophe Drayton — Instructor Christophe is the instructor for the UX & UI Design Certificate, Figma Advanced, and Generative AI courses at Noble Desktop, and the founder and Chief Design Officer of Kaaiind, which specializes in Applied Artificial Intelligence in the Creative field. With over 20 years in Branding, UX Design, and Accessibility across Europe and the US, Christophe has positively impacted the digital experience of a large spectrum of companies, ranging from big data to startups, government entities to nonprofits, both in the private and public sectors. As an Educator, Christophe has led transformative and award-winning UX programs at Thinkful, the City University of New York (CUNY), and the Brooklyn Public Library, which have opened doors for underrepresented groups in tech who have secured roles at top companies like Google, Uber, Citi, and IBM. Most recently, he has developed innovative curricula about AI in the workplace for the University of Phoenix, LinkedIn Learning, and Coursera. Today, he focuses on developing Allie, one of the first AI-powered, patent-pending color-blind safe and WCAG-compliant design system generator, while concluding his 5-year fundamental research on color vision deficiencies in digital environments. Christophe believes in hands-on, practical application of human-centered strategy and ethical and inclusive design. He is passionate about sharing his knowledge to inspire and empower the next generation of designers, especially those entering the field through nontraditional paths. ## Pricing **Tuition:** $649