The Model Context Protocol has received its largest update since launch, with a stateless protocol core designed to make AI tool connections easier to scale. Ars Technica reports that requests no longer have to depend on a session tied to one server instance.
MCP is an open-source standard for connecting AI systems to tools and data sources. It began as a local-machine protocol, but it is increasingly used across developer tools and enterprise services. Stateless request handling should make load balancing, reliability, and server deployment simpler for teams running MCP at larger scale.
The update also adds multi-round-trip requests, header-based routing, cacheable list results, authorization hardening, a formal extensions framework, updated Tier 1 SDKs, and a deprecation policy that generally gives at least 12 months before removal.
Anthropic introduced MCP and still has influence through maintainers, but the protocol now sits under the Linux Foundation’s Agentic AI Foundation. OpenAI, Google, Microsoft, and Amazon also contribute, making the standard a shared battleground for agent infrastructure.