Because I'm never allowed to be done with The Book, a new roadmap for MCP has just dropped. Luckily for all of us who are still catching up with the changes introduced in the 07-28-2026 spec, the roadmap update is not a change to the protocol,
It's been a while, hasn't it? I've been incredibly busy, juggling my part-time work, a string of big enterprise contracts (Koch's Principle Companion, a new learning agent for Microsoft, and an MCP workshop series for Nelnet), and finishing up AI Agents
As always, a whole lot has happened in the AI world since the last newsletter went out. Let's try to do a quick catch-up! First, in Software Survival 3.0, Steve Yegge (of Beads and Gas Town fame/infamy), argues a hopeful case for the future of
I'm finally emerging (kind of) from the haze of the holidays, surgery recovery, and the entire household getting the flu with a bevy of news for you. We drove from Boston to Florida for the holidays to spend it with our family down there, spent a lot of
Just a very quick note to let you know that my upcoming book "AI Agents with MCP" is now available for pre-order on Amazon.
On Thursday afternoon, I'll be giving a workshop on how to give your LLM-based applications superpowers by creating MCP clients for them, allowing you to add tools to your application's repertoire without having to build the tools yourself (unless you want to). I know I
I picked one hell of a week (or several) to be heads-down. Between writing new chapters and updating old ones for AI Agents with MCP, finishing my slides and project for my virtual workshop at ODSC West on building MCP clients, the general festivities that come with being a
Today the early release version of AI Agents with MCP was updated with the work I've been doing on it over the past month. What comes with this is a major change to the book's organization so that we can go deeper into building with the
I wrote a guest blog for the Open Data Science Conference, where I'll be giving a virtual workshop on building MCP clients in order to supercharge intelligent AI applications. If you ever wanted a quick overview (with code!) on how to build an MCP client that will allow
Today I returned to the Real Python podcast after several years to talk about my recent post about autoconverting REST APIs to MCP servers, Jeremiah Lowin's article that inspired it, and, of course, AI Agents with MCP. You can give the episode a listen here or wherever you
A few days ago, the maintainers of the Model Context Protocol announced that they had released the MCP Registry. This is an exciting development in the world of MCP for a few reasons: * It creates a standard way to distribute servers * It's open-source * Most excitingly, it allows
This might be the most common MCP antipattern I see, and it's not helped by a bevy of startups and products offering to automate this process for you. Of course, it's tempting: APIs are APIs after all, right? Wrong.