Skip to main content
AI

MCP 2026-07-28 Specification: transport going stateless

MCP 2026-07-28 Specification: transport going stateless Image: Primary
The Model Context Protocol released its 2026-07-28 specification on Monday, introducing a stateless protocol core and updated Tier 1 SDKs, the project's lead maintainers David Soria Parra and Den Delimarsky announced. The specification transforms MCP from a bidirectional stateful protocol into a request-response stateless protocol, a change the maintainers said was one of the most highly requested features from developers seeking better reliability and scalability. Every request is now self-describing with an optional discovery call, allowing any request to land on any server instance behind a plain round-robin load balancer. Method and tool names travel in Mcp-Method and Mcp-Name HTTP headers so gateways can route and authorize on headers directly. Server-to-client requests for sampling and elicitation are redesigned to use Multi Round-Trip Requests, removing the need for constantly open bidirectional streams. List responses carry cache hints and deterministic order so clients can cache tool catalogs and keep upstream prompt caches stable across reconnects. The release formally locks in an extensions framework with Tasks joining other extensions such as MCP Apps and Enterprise Managed Authorization. Authorization hardening changes include RFC 9207 issuer validation and a formal shift away from Dynamic Client Registration toward client metadata documents. A formal deprecation policy sets a twelve-month minimum window for upgrades. The TypeScript, Python, Go, and C# SDKs are updated to match the specification with detailed migration notes. The Rust SDK supports the new spec in beta. Roots, Sampling, Logging, and the legacy HTTP+SSE transport are deprecated with a year-long offramp.
Sources
Published by Tech & Business, a media brand covering technology and business. This story was sourced from blog.modelcontextprotocol.io and reviewed by the T&B editorial agent team.
Back to Newswire
Keep reading
Full wire
AI Science
AI Science

NASA and IBM release open lunar foundation model on Hugging Face

NASA and IBM Research released the NASA-IBM Lunar Foundation Model, an open-source AI model built for lunar science, hosted publicly on Hugging Face with its codebase on GitHub. NASA said the model was trained primarily on 17 yea...

AI Products
AI Products

SemiAnalysis acquires Citrini Research; founder plans new fund

Citrini Research founder James van Geelen has sold the independent investment-research firm to SemiAnalysis, a semiconductor and AI research shop, for an undisclosed sum, according to Bloomberg. Sources told the outlet that van G...