MCP turns one and makes big moves. Also inside: a new eBook launch and our Annual Survey raffle winner.
View in browser
The New Stack Logo
TNS Weekly Update

ISSUE 499
MCP Turns One with Big Moves

TECH TALK

"Every AI problem is essentially a data problem”

— Confluent’s Sean Falconer, "IBM’s Confluent Acquisition Is About Event-Driven AI"

TNS Makers

2026 Will Be the Year of Agentic Workloads in Production on Amazon EKS

In this episode of The New Stack Makers, Amazon's Mike Stefaniak discusses how AI workloads are reshaping Kubernetes, why AWS open-sourced a Model Context Protocol (MCP) server for EKS, and what’s actually happening with agentic AI in production environments. Tune in to catch the insights!

Watch the Episode
social_LiveNow_vs-2_16x9 (3)

Just Launched: Our New 'AI for the Enterprise' eBook

We’re thrilled to announce the official release of our newest eBook, “AI for the Enterprise: The Playbook for Developing and Scaling Your AI Strategy.” This brand-new eBook brings together lessons from global organizations and provides a framework for measuring true ROI, reducing operational toil, and building a culture of experimentation and learning.

Get Your Copy

MCP Turns 1, and a New Open Source Foundation Is Born

Things move so quickly these days. Why, we could have sworn it was just yesterday when Anthropic open sourced the Model Context Protocol — MCP, to its friends — a standard for connecting AI agents to data, tools and services.

And now it’s time to buy it a smash cake.

Yes, MCP is one year old now, and one of the most popular posts with New Stack readers last week marked the occasion, looking back and forward at what’s ahead for the project. The post by Cody de Arkland, head of developer experience at Sentry, noted that Anthropic’s “lofty” claims for MCP have largely come to fruition.

“In its first year, it’s hard to build a case that says Anthropic overpromised,” de Arkland wrote. “MCP still has room to improve, but the protocol filled a need and has found its audience fast.”

Not that it’s been easy. For instance, in Sentry’s early attempts to build with MCP, he wrote, the code broke a lot, highlighting a need for better observability with the protocol. “[W]e’re absolutely seeing a rise in people wanting a clearer understanding of what’s happening under the hood with their MCP servers. MCP feels like magic until it breaks and you’re digging for why.”

The next phase of MCP will likely see some tool consolidation and standardization of paths. With the announcement Monday of MCP’s donation to the Agentic AI Foundation, a brand spanking-new entity under the Linux Foundation umbrella, there are a lot of milestones ahead.

 

— Heather Joslyn, editor-in-chief, TNS

Reader Favorites

What DocumentDB Means for Open Source
Available through the MIT license, the schemaless data store supports multiagent session history, memory and collaboration.

How Okta Scaled From 12 to 1,000 Kubernetes Clusters With Argo CD
Okta engineers share the five-year journey of scaling Auth0's private cloud from 12 clusters to over 1,000 using the CNCF-graduated GitOps project.

Combining Rust and Python for High-Performance AI Systems
Overcome Python's AI performance bottlenecks. Learn how to integrate Rust for C++-level speed and concurrency without leaving the Python ecosystem.

DevOps Is Still Waiting for Its Cursor Moment
Why are we still manually fixing production? A look at why AI hasn't conquered infrastructure and what a "Cursor for DevOps" will need to succeed.

5 Ways To Transform ITOps With a Human and AI Agent Model
This model allows you to harness the speed, scalability and processing power of AI alongside human creativity, context, collaboration and judgment.

Why You Should Break Your ML Pipelines on Purpose

Traditional monitoring won't catch feature drift or data quality issues. Chaos engineering helps you find hidden issues before they cause damage.

SAP Expands Its AI Stack for Developers

SAP unveils a series of new AI-powered tools and services for developers at its ecosystem at its TechEd 2025 event in Berlin.

On-Demand Webinars

SpectroCloud Webinar 1

Scaling Edge Platforms to Thousands of Global Locations

Live from AWS re:Invent, YUM! Brands and AWS joined Spectro Cloud and TNS to dig into how to enable centralized management and scalable, production-grade infrastructure to bring innovation closer to customers. Missed it? No worries — the webinar is now available on-demand.

Watch On-Demand
SpectroCloud Webinar 2

How Highly Regulated Industries Thrive at the Edge

In this webinar, GE HealthCare and  Spectro Cloud joined TNS to explore how GE HealthCare leverages cloud native and edge technologies to improve care for 1 billion patients and ensure agility, consistency, and compliance across thousands of connected medical environments. The entire session is now available on-demand, so you can watch it at your convenience.

Catch the Replay
TNS_Annual_Reader_Survey

In the Spotlight: Congrats to Our Reader Survey Raffle Winner!

Last month, we completed our annual reader survey. Thank you to everyone who participated. We look forward to sharing results with you and using your feedback to continue improving what we do here at TNS.

Special shout-out to our first raffle winner of a $500 gift card, Stephanie Lemmeyer! Stephanie is a DevOps pro who visits TNS at least once a month since she first began reading a year or two ago to discover new use cases and tools as well as stay informed of trends.

The second raffle winner has been drawn and notified. We're waiting to hear if they would like to be featured here. Thanks again to all who took the survey!

Connect with The New Stack

LinkedIn
X
Facebook
Bluesky
Youtube

The New Stack

1111 6th Ave Ste 550, PMB 50938, San Diego, CA 92101-5211

 

Not loving everything we send? You can update your preferences or unsubscribe from all email communications.