New MCP specification addresses the main barrier to enterprise adoption

新版 MCP 规范解决了企业采用该技术的主要障碍

This week, the Model Context Protocol (MCP), an open source standard for how AI systems interact with external tools and data sources, saw its largest update since its introduction. 本周，模型上下文协议（Model Context Protocol，简称 MCP）迎来了自发布以来的最大规模更新。该协议是一个开源标准，旨在规范 AI 系统如何与外部工具及数据源进行交互。

Most notably, MCP’s protocol core is now stateless, so requests are no longer dependent on a session tied to an individual server instance. This change has the potential to address long-standing barriers to scalability. 最值得注意的是，MCP 的协议核心现已改为无状态（stateless），这意味着请求不再依赖于绑定到特定服务器实例的会话。这一改变有望解决长期以来阻碍其扩展性的难题。

The blog post announcing the specification, written by lead maintainers David Soria Parra and Den Delimarsky (who both work at Anthropic), says: The highlight of this release is a stateless protocol core—MCP is transforming from a bidirectional stateful protocol into a request/response stateless protocol. It was one of the most highly-requested features from developers who were eager to get better reliability and scalability for their MCP servers. 由主要维护者 David Soria Parra 和 Den Delimarsky（两人均就职于 Anthropic）撰写的规范发布博客中提到：“本次发布的核心亮点是无状态协议内核——MCP 正从双向有状态协议转型为请求/响应式无状态协议。这是开发者呼声最高的功能之一，他们迫切希望为自己的 MCP 服务器获得更好的可靠性和可扩展性。”

This update is “MCP’s most important since remote MCP first launched over a year ago,” Soria Parra also wrote. In addition, the update adds “Multi Round-Trip Requests, header-based routing, cacheable list results, authorization hardening, a formal extensions framework, and updated Tier 1 SDKs.” Soria Parra 还写道，这次更新是“自一年多前远程 MCP 首次推出以来，MCP 最重要的一次升级”。此外，本次更新还增加了“多往返请求（Multi Round-Trip Requests）、基于标头的路由、可缓存的列表结果、授权强化、正式的扩展框架以及更新的一级 SDK”。

The hope is that the changes, detailed in the protocol’s documentation, will make widespread deployment in an enterprise context much easier. MCP started as something that simply ran on a local machine, connecting models to local apps, so the new spec is a major rethink of some of its foundations. 人们希望这些在协议文档中详细说明的变更，能使该技术在企业环境中的大规模部署变得更加容易。MCP 最初只是在本地机器上运行，用于连接模型与本地应用程序，因此新规范是对其部分基础架构的一次重大重构。

There is also a new deprecation policy that ensures at least 12 months between when a feature’s formal deprecation is enacted and when the feature may actually be removed—with a narrow exception for critical security updates. This is again in keeping with the general “let’s make this work better at enterprise scale” theme of the new specification. 此外，新规范还引入了一项新的弃用政策，确保从功能正式弃用到实际移除之间至少有 12 个月的缓冲期（关键安全更新除外）。这再次呼应了新规范“让其在企业规模下运行得更好”的总体主题。

MCP is managed by the Agentic AI Foundation (AAIF), which sits under the Linux Foundation. MCP was originally introduced by Anthropic, just shy of two years ago, and Anthropic still has significant influence over its direction. MCP 由隶属于 Linux 基金会的 Agentic AI Foundation (AAIF) 管理。MCP 最初由 Anthropic 在近两年前推出，目前 Anthropic 对其发展方向仍具有重大影响力。

Nonetheless, it has grown beyond just Anthropic—OpenAI, Google, Microsoft, and Amazon also contribute to it—and it’s supported by many developer tools and, increasingly, a wide range of software and services used for other knowledge and creative work. The buck technically stops with individual maintainers, not any of these companies themselves, but as noted above, some of the principal maintainers currently work at Anthropic. 尽管如此，它的影响力已超越了 Anthropic 本身——OpenAI、Google、Microsoft 和 Amazon 也参与了贡献。它得到了许多开发工具的支持，并且正越来越多地被用于各类知识和创意工作的软件与服务所采用。从技术上讲，最终决策权掌握在个人维护者手中，而非上述任何一家公司，但如前所述，一些主要维护者目前确实就职于 Anthropic。