AI and ML<\/p>\n
Now happier running in a conventional K8s environment, with `an easier-to-live-with lifecycle\u00a0<\/p>\n
The Agentic AI Foundation, part of the Linux Foundation, has released an update to the Model Context Protocol (MCP) that aims to help enterprises adopt AI-based automation.<\/p>\n
Open-sourced by Anthropic in November 2024, MCP<\/a> provides a way for AI applications (agents) based on models like GPT-5.6 Sol or Claude Opus 5 to connect to existing data sources, tools, or other applications. It defines how content is exchanged in a client-server architecture.<\/p>\n “The new release is MCP\u2019s most important since remote MCP first launched over a year ago,” wrote David Soria Parra, a member of technical staff at Anthropic and co-inventor of MCP, in a blog post<\/a>. “It is a leap in serving scalable MCP servers and takes all the lessons learned over the last 18 months to provide a robust foundation for MCP\u2019s future.”<\/p>\n The latest version<\/a> of the specification does away with the legacy stateful architecture<\/a>, making it more like HTTP services where network requests do not need to retain the state of the session.<\/p>\n “Historically, running MCP at scale required sticky routing or shared state to maintain continuity across sessions,” explained Caitie McCaffrey, a Microsoft software engineer and core MCP maintainer, in a blog post<\/a>. “This made large-scale production deployments complex to implement and operate even when the capabilities being exposed were stateless.”<\/p>\n The revised protocol<\/a> changes the underlying architecture to eliminate the overhead of managing session state, which allows organizations to run MCP servers behind standard load balancers on existing Kubernetes and DevOps tooling.<\/p>\n The version 2026-07-28 release also includes a Specification Feature Lifecycle and Deprecation Policy<\/a>, because large companies want clear roadmaps and timelines when it comes to software changes.<\/p>\n “The goal is a predictable timeline that SDK authors and implementers can plan migrations against when protocol surface area is retired,” the documentation explains.<\/p>\n The revised spec comes with a new policy that guarantees a minimum period of 12 months between feature deprecation and removal, which should please enterprise engineering teams, since\u00a0they’ll need to make fewer updates to MCP servers.<\/p>\n On the security front, the latest spec revision adds Specification Enhancement Proposal (SEP) 2468<\/a>, which calls for the inclusion and validation of an issuer (iss) parameter in authorization responses. This should help prevent OAuth Mixup Attacks<\/a>.\u00a0<\/p>\n An attack of this sort can occur when an OAuth client connects to multiple OAuth providers via multiple MCP servers. If an attacker controls one of these servers, the miscreant could potentially obtain an access token or code from one of the other servers. Checking the iss parameter defends against that particular attack vector.<\/p>\n Large organizations should also appreciate support for the Enterprise Managed Authorization<\/a> extension, which makes it possible to manage MCP servers through a central identity provider.<\/p>\n Another improvement involves the evolution of tasks<\/a> \u2013 long-running tool calls or batch operations \u2013 into an extension<\/a>. The main benefit is that tasks shift from a blocking request to an asynchronous request.<\/p>\n “The payoff is operational resilience at scale,” explains McCaffrey. “Because a task is durable and addressed by a stable handle, clients can persist task IDs to durable storage so that polling can resume after a crash or restart \u2014 no fragile, long-lived connections held open while waiting for work to finish, which the old blocking model forced on clients and servers that did not want to implement it.”<\/p>\n Other notable additions include header-based routing<\/a> and cacheable list results<\/a>. Some migration cost is expected, particularly for developers who implemented MCP code that relies on session identifiers. \u00ae<\/p>\n","protected":false},"excerpt":{"rendered":"AI and ML Now happier running in a conventional K8s environment, with `an easier-to-live-with lifecycle\u00a0 The Agentic AI…\n","protected":false},"author":2,"featured_media":717874,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[554,733,4308,86,56,54,55],"class_list":["post-717873","post","type-post","status-publish","format-standard","has-post-thumbnail","category-artificial-intelligence","tag-ai","tag-artificial-intelligence","tag-artificialintelligence","tag-technology","tag-uk","tag-united-kingdom","tag-unitedkingdom"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/717873","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/comments?post=717873"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/717873\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media\/717874"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media?parent=717873"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/categories?post=717873"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/tags?post=717873"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}