# Building Your First MCP Server and Client Course 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 instead of treating them as thin wrappers over REST APIs. 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 then build a minimal MCP client that can discover and call server tools. The course emphasizes both implementation and design judgment. In addition to building a functioning server and client, participants learn how to reduce tool sprawl, design around agent workflows, manage context-window costs, and produce tool descriptions and outputs that work well for large language models. ## What you'll learn - Explain the purpose of MCP and describe the host-client-server architecture. - Distinguish between tools, resources, and prompts, and identify when each is appropriate. - Describe how context windows affect MCP server design. - Recognize common anti-patterns in MCP server design, especially endpoint-for-endpoint REST wrappers. - Build a local MCP server in Python using FastMCP. - Design tools around outcomes and workflows rather than API structure. - Test an MCP server using the MCP Inspector and an MCP-compatible host. - Build a minimal MCP client that connects to a server, lists tools, and calls them. - Describe the basics of deploying a remote MCP server and the security considerations involved. ## 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 ### Bruce Gay — Instructor Bruce is an engaging trainers and program manager who brings 25+ years practical experience to deliver effective and experiential training to students. Able to engage adult learners with a range of backgrounds and professional experiences. Successful at building effective stakeholder relationships and coordinating multi-disciplinary teams for solution delivery. Bruce has over 25 years of project and program management experience across multiple industries. He has a Masters degree from The George Washington University and a B.A. from the University of North Carolina Chapel Hill. Bruce currently runs his own freelance training and consulting business, helping project managers and team leaders improve their business skills, become better leaders, and achieve professional greatness. Bruce is a well-received speaker in the areas of design thinking, project management, cross-team collaboration, and AI tools for projects, and has presented at regional and international conferences. ### Steve Pesklo — Instructor Steve is an energetic trainer who focuses on applying technical concepts to everyday work practices. He is the founder and president of SoftLake Solutions, a company that specializes in providing data and AI applications to identify fraud for Internal Audit, Criminal Investigations, Forensic Accounting, Privacy, and Compliance. Steve brings a large amount of experience across multiple industries and government agencies. He is an expert in implementing large data analysis projects across the world, including Inland Revenue in the UK and Argentina, New Zealand, Africa and across Europe. Previously, he was the manager of Data Architecture and Data Services for a large mortgage company. He is a frequent speaker on data analytics and project management topics and speaks fluent German. He has been teaching at the Graduate School for over 10 years. Steve has an M.B.A. from the University of St. Thomas and a B.S. in Computer Science from California Lutheran University and the Universität Salzburg in Austria. He is certified as a Certified Fraud Examiner (CFE), Project Management Professional (PMP), and a Certified ScrumMaster (CSM). ### Brian Simms — Instructor Brian Simms is a seasoned educator and training leader with extensive experience developing and delivering innovative learning programs in project management and emerging technologies. Over the course of his career, he has designed adaptive learning models that combine instructor-led sessions, live online experiences, and self-paced study, ensuring professionals can access training in flexible and effective ways. His work has emphasized the integration of artificial intelligence into professional development, helping organizations and individuals understand how AI can be applied to solve real-world challenges in leadership, project execution, and decision-making. In addition to his instructional expertise, Brian has guided curriculum development, led large training initiatives, and advanced the use of collaboration tools that improve learner engagement and retention. His depth of experience and forward-looking perspective make him uniquely equipped to prepare federal professionals to navigate the complexities of data, project management, and the transformative potential of AI. ### Clarissa J. Corbin — Instructor Clarissa J. Corbin is an accomplished corporate trainer, project manager, and business consultant with over 25 years of experience designing and delivering impactful learning experiences. As President and CEO of Projections Training Solutions, she partners with federal agencies, private corporations, and international organizations to provide results-driven training in leadership, project management, business analysis, and emerging technologies. Clarissa has trained more than 10,000 professionals worldwide, serving clients such as the DoD, NASA, FEMA, Microsoft, Citibank, PNC Bank, Del Monte, and Symantec. Her expertise has taken her across the globe, leading initiatives in Singapore, China, Japan, South Korea, Africa, Jamaica, Trinidad & Tobago, and St. Thomas, USVI. Known for her ability to engage diverse audiences and create interactive, high-impact sessions, Clarissa equips participants with practical solutions they can apply immediately. At Graduate School USA (GSUSA), Clarissa is regarded as one of the most versatile and trusted instructors. She teaches across multiple programs. She played a pivotal role in redesigning the flagship “Managing for Results” course, while also contributing to the development and review of numerous others. Her contributions have earned her two GSUSA Customer Excellence Awards and a two-year appointment to the GSUSA Instructor Advisory Council, underscoring her commitment to innovation, quality, and learner success. ### Natalya H. Bah — Instructor Natalya Bah has been a part-time instructor at the Graduate School USA for over fifteen years. Natalya teaches across multiple curricula, including Leadership and Management, Project Management, and Human Resources. She has created a curriculum for the school, including Change Management Workshops and project management courses. She has served as an action learning coach, instructor, and facilitator for government leadership programs in the Center for Leadership and Management. Natalya also provides self-assessments and dynamic team-building sessions on behalf of the Graduate School USA. Outside of Graduate School USA, Ms. Bah is a self-employed business owner providing executive coaching, training, and consulting services to the public and private sectors. She created the Define and Achieve Your Goals Process™ and is a certified Birkman Method© Consultant. She received her Master of Science degree in Project Management from George Washington University’s School of Business, where she served as a teaching assistant and received the Project Management Award. She is also a certified Project Management Professional (PMP). ### Michiel Pruijssers Michiel is a Principal Designer and Forward Deployed Engineer at Microsoft's Industry Solutions Engineering Division, where he partners with strategic enterprise customers to architect and ship production AI systems. With over 15 years of experience, he operates at the intersection of user research, design, engineering, and cloud architecture, anchored by deep expertise in machine learning. His career spans senior roles at Snorkel AI, Determined.ai, and earlier Microsoft teams behind foundational AI products including LUIS.ai, Azure Bot Service, and Azure Stack, where he led both customer discovery and platform design for some of the industry's most technically ambitious ML offerings. He pairs rigorous qualitative research with hands-on building, shipping his own production SaaS products in Python while also teaching students through cohort-based AI courses. His instruction is grounded in real practice: what it takes to design, build, and operate AI systems that actually hold up in the wild. ## Pricing **Tuition:** $649