September 2026
Intermediate to advanced
350 pages
10h 3m
English
Content preview from AI Agents with MCP
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
Chapter 1. Agentic AI and MCP
Toward the end of 2024, Anthropic released the Model Context Protocol (MCP) to great fanfare. Not only did Anthropic standardize a way to transform chatbots from simple talkers into agents that could act, but it released MCP concurrently with support from popular AI-powered IDEs as well as Anthropic’s Claude Desktop, driving speedy adoption. One of the major pieces of the MCP architecture, the MCP server, was made to be incredibly simple to spin up, but powerfully complex when advanced workflows were needed. This led to a rapid flood of user-created MCP servers, augmenting generative AI workflows and cementing the adoption of MCP as the standard for building AI agents.
But what brought us from large language models (LLMs) to agents? To be glib: a whole lot of experimentation. When LLMs first entered the public consciousness, the primary way to interact with them was via a chat dialog on a website. They were simple conversational chatbots, prone to errors, and restricted to the information in their training data. Retrieval-augmented generation (RAG) came along to solve that, initially by software intercepting an LLM query, searching a vector database for related data, and enriching the LLM prompt with related data that it retrieved. Around the same time, ReAct (REasoning + ACTing) was introduced, a technique that gave LLMs the capability to alternate between reasoning and task-specific actions. Still, these actions were largely confined to the prompt. ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.