When does class start/end?
Class hours may vary, please reach out to contact@ascendientlearning.com if you have any questions.
Building Agentic AI with Model Context Protocol
Build agentic AI applications through Model Context Protocol resources, tools, and sampling. MCP architecture and core components cover hosts, models, contexts, layers, protocols, connections,...
Read More
$2,000USD
Duration
2 days
Course Code
GAI-2104
Available Formats
Classroom
Overview
Course Description
Build agentic AI applications through Model Context Protocol resources, tools, and sampling. MCP architecture and core components cover hosts, models, contexts, layers, protocols, connections, message types, the development tools, and the filesystem reference server. Resources and roots cover exposing data through resources, building resource URIs and types, reading and discovering resources, real-time updates, and establishing focus with roots. Prompt templates and tool use cover prompt structure, prompt discovery, multi-step workflows, embedded resources in prompts, defining tools for LLM readability, exposing tools for discovery, tool-use patterns, and error handling. Sampling and agentic applications cover sampling requests from MCP servers, response generation, human-in-the-loop confirmation, security best practices, and integrating LLMs, tools, and resources end-to-end. Hands-on labs produce a resource server, a tool-exposing MCP server, a sampling flow with human-in-the-loop confirmation, and a working agentic application prototype. The course is designed for software developers and data scientists with Python and introductory generative-AI experience.
Skills Gained
By the end of this course, participants will be able to:
- Describe the architecture and components of the Model Context Protocol
- Configure RAG using MCP resources and roots
- Compose prompt templates plus multi-step workflows that satisfy MCP discovery rules
- Expose tools for LLM-driven applications
- Build, test, and debug agentic applications using MCP
Who Can Benefit
This course is designed for:
- Software Developers
- Data Scientists
Prerequisites
Participants should enter this course with:
- Practical Python experience
- GAI-1101 or equivalent
Organizational Objectives
This course assists organizations to:
- Reduce custom integration cost by adopting MCP as the agent-integration standard
- Lower operational risk through MCP security best practices and human-in-the-loop sampling
- Build a working knowledge of MCP across development teams in two days
- Establish a shared MCP-server library that compounds reuse across agent projects
Software
All attendees must have a modern web browser and an Internet connection.
Course Details
Course Details
Module 1 - Introduction to Model Context Protocol
By the end of this module, you will be able to describe the MCP architecture and component roles, define hosts, models, and contexts, and recognize the protocol’s layers, message types, and connections.
- Why Model Context Protocol?
- Core Architecture and Components
- Defining Hosts, Models, and Contexts
- MCP Layers, Protocols, and Connections
- Message Types and Purposes
- Hands-on Lab: Use the MCP development tools to explore the filesystem reference server end-to-end.
Module 2 - Enabling RAG with Resources and Roots
By the end of this module, you will be able to expose data with MCP resources, build resource URIs and types, support real-time resource updates, and establish focus through roots.
- Exposing Data with Resources
- Building Resource URIs and Types
- Reading Resources from the Server
- Resource Discovery with Templates
- Updating Resources in Real-Time
- Establishing Focus with Roots
- Hands-on Lab: Build a resource server that exposes documents and supports pub/sub for real-time updates.
Module 3 - Building Patterns with Prompt Templates
By the end of this module, you will be able to author MCP prompts with discoverable structure, expand prompts into multi-step workflows, embed resources in prompts, and integrate prompts into agent applications.
- Understanding the Prompt Structure
- Making Prompts Discoverable
- Expanding Prompts into Multi-step Workflows
- Embedding Resources in Prompts
- Integrating Prompts into Applications
- Hands-on Lab: Expose discoverable prompt templates and workflows from one MCP server with embedded resources.
Module 4 - Enabling Tool-Use on Servers
By the end of this module, you will be able to define tools for LLM readability, expose tools for discovery, apply tool-use patterns, and validate tools through error handling and exception tests.
- Defining a Tool for LLM Readability
- Patterns of Tool Use
- Exposing Tools for Discovery
- Testing and Validating Tools
- Handling Errors and Exceptions
- Hands-on Lab: Create and expose one MCP tool, then test its integration with an LLM client end-to-end.
Module 5 - Using LLMs from MCP Servers with Sampling
By the end of this module, you will be able to write sampling requests from MCP servers, generate sampling responses, integrate human-in-the-loop confirmation, and apply sampling-specific security best practices.
- How Sampling Works and What It’s for
- Writing Sampling Requests
- Creating Sampling Responses
- Adding a Human-in-the-Loop
- Security Considerations and Best Practices
- Hands-on Lab: Build an MCP sampling request/response pair and add a human-in-the-loop confirmation step.
Module 6 - Building Agentic Applications with MCP
By the end of this module, you will be able to choose where an agent lives, integrate LLMs with MCP tools and resources, build a simple agentic application, and test and debug it end-to-end.
- Understanding Where the Agent will “Live”
- Understanding Agentic Applications
- Integrating LLMs, Tools, and Resources
- Building a Simple Agentic Application
- Testing and Debugging Agentic Applications
- Future Directions for Agentic Applications
- Hands-on Lab: Develop and debug a simple agentic application that integrates LLMs, MCP tools, and resources.
Schedule
FAQ
Does the course schedule include a Lunchbreak?
Classes typically include a 1-hour lunch break around midday. However, the exact break times and duration can vary depending on the specific class. Your instructor will provide detailed information at the start of the course.
What languages are used to deliver training?
Most courses are conducted in English, unless otherwise specified. Some courses will have the word "FRENCH" marked in red beside the scheduled date(s) indicating the language of instruction.
What does GTR stand for?
GTR stands for Guaranteed to Run; if you see a course with this status, it means this event is confirmed to run. View our GTR page to see our full list of Guaranteed to Run courses.
How do I find an Ascendient Learning training location?
We have training locations across the United States and Canada - View a complete list of classroom training locations.
Which delivery formats are available?
At Ascendient Learning, we offer training that is Instructor-Led, Online, Virtual, and Self-Paced.
Does Ascendient Learning deliver group training?
Yes, we provide training for groups, individuals and private on sites. View our group training page for more information.
What does vendor-authorized training mean?
As a vendor-authorized training partner, we offer a curriculum that our partners have vetted. We use the same course materials and facilitate the same labs as our vendor-delivered training. These courses are considered the gold standard and, as such, are priced accordingly.
Is the training too basic, or will you go deep into technology?
It depends on your requirements, your role in your company, and your depth of knowledge. The good news about many of our learning paths, you can start from the fundamentals to highly specialized training.
How up-to-date are your courses and support materials?
We continuously work with our vendors to evaluate and refresh course material to reflect the latest training courses and best practices.
Are your instructors seasoned trainers who have deep knowledge of the training topic?
Ascendient Learning instructors have an average of 27 years of practical IT experience and have also served as consultants for an average of 15 years. To stay current, instructors spend at least 25 percent of their time learning new, emerging technologies and courses.
Do you provide hands-on training and exercises in an actual lab environment?
Lab access is dependent on the vendor and the type of training you sign up for. However, many of our top vendors will provide lab access to students to test and practice. The course description will specify lab access.
Will you customize the training for our company’s specific needs and goals?
We will work with you to identify training needs and areas of growth. We offer a variety of training methods, such as private group training, on-site of your choice, and virtually. We provide courses and certifications that are aligned with your business goals.
How do I get started with certification?
Getting started on a certification pathway depends on your goals and the vendor you choose to get certified in. Many vendors offer entry-level IT certification to advanced IT certification that can boost your career. To get access to certification vouchers and discounts, please contact info@ascendientlearning.com.
Will I get access to content after I complete a course?
You will get access to the PDF of course books and guides, but access to the recording and slides will depend on the vendor and type of training you receive.
How do I request a W9 for Ascendient Learning?
View our filing status and how to request a W9.
Reviews
The tool provided to practice the course teachings is very functional and easy to use.
Brandon was a great instructor. The virtual course materials and labs provided were very informative.
Some Labs are very good but some steps it ask to update but its already updated, but overall its very good training.
This was effective way to provide a ton of information in a short time period.
Fantastic and great training. Tons of hands-on labs to really make you understand the material being thought.
