{"id":1101642,"date":"2026-07-21T01:25:15","date_gmt":"2026-07-21T01:25:15","guid":{"rendered":"https:\/\/www.europesays.com\/uk\/1101642\/"},"modified":"2026-07-21T01:25:15","modified_gmt":"2026-07-21T01:25:15","slug":"ais-most-important-protocol-is-getting-a-little-bit-easier-to-use","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/uk\/1101642\/","title":{"rendered":"AI’s most important protocol is getting a little bit easier to use"},"content":{"rendered":"

The Model Context Protocol<\/a> (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\u2019s 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 week, that protocol is getting a significant update, and while it might not be noticeable to end users, it could make a big difference in how the ecosystem develops.<\/p>\n

The official spec<\/a> for the new version has been public since May, but we got an unusually clear explanation<\/a> of the changes Monday morning from the folks at Arcade \u2014 a two-year-old startup that\u2019s built its entire business around the work of getting AI agents to actually function inside real companies, letting them securely connect to and act on tools like Gmail, Slack, and Salesforce. <\/p>\n

Arcade raised $60 million<\/a> in June based on the idea that most AI agents don\u2019t fail because the underlying models are weak but because the infrastructure around them isn\u2019t ready yet, and that\u2019s what this update is trying to address. Essentially, MCP is changing the way it handles session IDs \u2014 the little tokens that servers use to remember \u201cah, this is the same conversation as five seconds ago\u201d \u2014 so servers can operate more easily at a larger scale.<\/p>\n

As Arcade founder Nate Barbettini puts it:<\/p>\n

\n

[Under the current system] The first time an MCP client like Claude connects to a server, it sends a \u201chello\u201d: I\u2019m Claude, here\u2019s my version, here are my capabilities. The server replies with its own capabilities and hands back a session ID\u2026 From then on, the client sends that session ID on every request so the server knows it\u2019s the same conversation. Sometimes the ID expires, so the client has to notice, request a new one, and carry on\u2026.<\/p>\n

Picture a real deployment. You\u2019re running a server for millions of users, behind a load balancer whose entire job is to route each request to whatever server in the farm is free, sometimes in a different region. Now every one of those machines has to know about a session ID that some other machine handed out. It\u2019s not impossible, but it\u2019s a serious pain, and it fights the load balancer instead of working with it.<\/p>\n<\/blockquote>\n

In other words, the current setup assumes one server remembers you, but real companies spread traffic across dozens of servers that don\u2019t talk to each other by default, so today\u2019s MCP servers have to do extra work just to keep track of who\u2019s who. That\u2019s been a significant headache for anyone running an MCP server at scale, and part of the reason we haven\u2019t seen more companies ship large-scale, first-party MCP integrations despite all the hype around agentic AI this year. <\/p>\n

Under the new system, the protocol will take a looser, \u201cstateless\u201d approach to session IDs on the server side, similar to how most ordinary websites already work, which should make the whole system a lot easier to maintain and, in theory, cheaper to run at scale.<\/p>\n

That\u2019s all pretty technical, but it\u2019s an important reminder that not every part of AI development is moving at breakneck speeds. While model training races ahead, a lot of the technical infrastructure those models need is still subject to the slow log-rolling of standards-body consensus. It really is happening; it\u2019s just a little slower!<\/p>\n

When you purchase through links in our articles, we may earn a small commission<\/a>. This doesn\u2019t affect our editorial independence.<\/p>\n","protected":false},"excerpt":{"rendered":"The Model Context Protocol (MCP) is one of the basic building blocks of AI interoperability, giving AI models…\n","protected":false},"author":2,"featured_media":1101643,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","_share_on_mastodon":"0"},"categories":[3163],"tags":[323,1942,6773,53,16,15],"class_list":["post-1101642","post","type-post","status-publish","format-standard","has-post-thumbnail","category-artificial-intelligence","tag-ai","tag-artificial-intelligence","tag-mcp","tag-technology","tag-uk","tag-united-kingdom"],"share_on_mastodon":{"url":"https:\/\/pubeurope.com\/@uk\/116955363803631266","error":""},"_links":{"self":[{"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/posts\/1101642","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/comments?post=1101642"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/posts\/1101642\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/media\/1101643"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/media?parent=1101642"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/categories?post=1101642"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/tags?post=1101642"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}