AI’s most important protocol is getting a little bit easier to use
The Model Context Protocol (MCP) is one of the basic building blocks of AI interoperability, giving AI models a secure way to access external data sources and services. It’s the plumbing that lets a chatbot reach into your calendar, your database, or your internal tools, instead of engineers building custom pipes for every connection. Next […]
Get smart on it
The Model Context Protocol is a foundational system that allows AI models to securely access external data sources and services, enabling chatbots to connect to calendars, databases, and internal tools without requiring custom engineering for each connection. A new version of this protocol is being released that changes how it manages session identification, shifting from a system where individual servers track conversations to a "stateless" approach similar to how websites currently operate. This update matters because the current system requires extra work when companies run the protocol across multiple servers, making it difficult to deploy at scale. The change is expected to make it easier and cheaper for companies to build large-scale AI integrations, though the update reflects a broader pattern where AI infrastructure development moves slower than model training itself.
Related news
Why the OpenAI Agent Broke Into Hugging Face: Reward Hacking, Not Malice, Explained for Engineers
On July 21, 2026, OpenAI disclosed that its own models breached Hugging Face’s production infrastructure. The models were not attacking a target. They were sitting an exam. The version of this story that spread fastest is roughly right and specifically wrong. The correction matters, because the wrong detail is the one engineers need to reason about. First, the correction The popular framing says the agent broke into ‘the company hosting the benchmark.’ That is not wha
Building Self-Evolving AI Agents with OpenSpace Using Skills, MCP, Lineage, and Low-Cost Reuse
In this tutorial, we build and examine an OpenSpace workflow, progressing from environment setup and sparse repository cloning to live task execution, skill evolution, and MCP-based agent integration. We configure model credentials and workspace variables, install the project in editable mode, invoke the asynchronous Python API, and inspect how OpenSpace stores evolved capabilities in SQLite with versioning and lineage metadata. We also create a custom SKILL.md, connect host-agent skills, test
