MCP Protocol Blog

Update on the Next MCP Protocol Release

An update on the timeline and priorities for the next Model Context Protocol specification version

Read more →

September 26, 2025

MCP Apps in Practice: Wiring, Negotiation and Testing

How an MCP App is wired (_meta.ui.resourceUri, ui:// resources, the app MIME type, CSP), how client and server negotiate the extension, the failure modes that leave you with plain text, and a stdlib script that checks a live server.

Read more →

October 25, 2026

Server Instructions in Practice: Spec Versions and Testing

Where MCP server instructions are delivered in each spec revision (initialize vs server/discover), how far the published A/B evidence goes, where each kind of knowledge belongs, the failure modes to expect, and a stdlib script that checks a live server.

Read more →

October 25, 2026

The Official Ruby SDK for MCP Reaches Tier 1

The official Ruby SDK for the Model Context Protocol is now a Tier 1 SDK under the MCP SDK tiering system, with full support for the 2026-07-28 specification revision and a 100% conformance pass rate across both scored spec revisions.

Read more →

September 29, 2026

January MCP Core Maintainer Update

A lot has happened since we first released MCP. We wrapped up 2025 with a major spec update and the momentum hasn’t slowed down. None of it would have happened without the community: every PR, every issue filed, every server and client built. That energy is what keeps MCP moving forward. To keep that momentum going, the Core Maintainer team is evolving as well. Departing Core Maintainers First, some news. Inna Harper and Basil Hosmer will be stepping away from the Core Maintainer team to focus on other projects.

Read more →

January 23, 2026

Exploring the Future of MCP Transports

When MCP first launched in November of 2024, quite a few of its users relied on local environments, connecting clients to servers over STDIO. As MCP became the go-to standard for LLM integrations, community needs evolved, leading to the build-out of infrastructure around remote servers. There’s now growing demand for distributed deployments that can operate at scale. The Streamable HTTP transport was a significant step forward, enabling remote MCP deployments and unlocking new use cases. However, as enterprise deployments scale to millions of daily requests, early adopters have encountered practical challenges that make it difficult to leverage existing infrastructure patterns. The friction of stateful connections has become a bottleneck for managed services and load balancing.

Read more →

December 19, 2025

MCP joins the Agentic AI Foundation

Today marks a major milestone for the Model Context Protocol. Anthropic is donating MCP to the Agentic AI Foundation, a directed fund under the Linux Foundation. MCP will become a founding project of the newly created foundation. In one year, MCP has become one of the fastest-growing and widely-adopted open-source projects in AI: Over 97 million monthly SDK downloads, 10,000 active servers and first-class client support across major AI platforms like ChatGPT, Claude, Cursor, Gemini, Microsoft Copilot, Visual Studio Code and many more.

Read more →

December 9, 2025

One Year of MCP: November 2025 Spec Release

Today, MCP turns one year old. You can check out the original announcement blog post if you don’t believe us. It’s hard to imagine that a little open-source experiment, a protocol to provide context to models, became the de-facto standard for this very scenario in less than twelve months. But not only do we hit the first anniversary milestone today - we’re also releasing a brand-new MCP specification version. Before we get to the details of what’s new, let’s do a bit of a retrospective.

Read more →

November 25, 2025

Adopting the MCP Bundle Format (.mcpb) for Portable Local Servers

The MCP Bundle format (MCPB) is now part of the Model Context Protocol project. This distribution format simplifies how developers package and share local MCP servers.

Read more →

November 21, 2025

Chrome DevTools MCP: Giving AI Coding Assistants Eyes to See Beyond Blind Programming

Google Chrome team releases Chrome DevTools MCP server, revolutionizing AI programming experience. Through Model Context Protocol, AI assistants can directly debug web pages in browser, analyze performance, and inspect network requests, ending the era of 'blind coding'.

Read more →

September 24, 2025