Cover of AI Agents with MCP

O'Reilly Media · 275 pages

AI Agents with MCP

Model Context Protocol for Building Clients, Services, and End-to-End Agents

Print & ebook 2026 · Early release available now

Anthropic released the Model Context Protocol at the end of 2024, and it quickly became the standard way to turn a chatbot into an agent that can act, plan, and use tools on its own. This book goes deep on MCP, well beyond the documentation. You’ll build up your own client and then a server, both supporting the full spec in Python, and get a real feel for how the protocol works along the way.

Inside the book

What you'll build

01

The protocol end-to-end

Where MCP came from, why it exists, and how clients, servers, and transports fit together to make it work.

02

Build real servers & clients

You'll build up a working client, then a server that provides tools, prompts, and resources, built the way you'd actually ship it.

03

Ship production-ready MCP

Test and secure your servers, share them with others, dig into how transports really work, and, if you're up for it, contribute back to MCP itself.

Contents

Table of contents

  1. 01Agentic AI and MCP
  2. 02An Introduction to the Model Context Protocol
  3. 03Making an Intelligent Application Agentic with MCP Clients
  4. 04MCP Clients: Advanced Use and Best Practices
  5. 05Building MCP Servers: Providing Tools, Prompts and Resources to Applications
  6. 06Building MCP Servers: Advanced Use with Utilities and Integrating Client Capabilities
  7. 07Testing, Securing, and Sharing Your MCP Server
  8. 08Connecting Clients and Servers: MCP Transports
  9. 09Wrapping Up: Tools to Help You Build, MCP Extensions, and Contributing to MCP

Chapter list for the early release; final titles and order may change.

About the author

Kyle Stratis
Kyle Stratis is the founder and principal consultant of Stratis Data Labs, where he helps startups and established firms with AI engineering, computer vision, data engineering, and ML engineering — drawing on more than a decade as a software engineer. He also serves as VP of Engineering at Telepath, bringing cutting-edge AI research into production.

Working on something with agents or MCP?

Work with Stratis Data Labs

Get the book