New MCP specification addresses the main barrier to enterprise adoption
Ars Technica AI · Samuel Axon · 2026-07-30
The Model Context Protocol has released its largest update since launch, making its core stateless so that AI tool requests are no longer tied to individual server sessions, directly targeting the scalability barrier that has blocked enterprise adoption.
Appears in
Extraction
Topics: model-context-protocolai-infrastructureenterprise-aiapi-standards
Claims
- MCP's protocol core has been redesigned to be stateless, eliminating dependency on sessions tied to individual server instances.
- The statelessness change is intended to address long-standing scalability barriers that have prevented enterprise-scale adoption of MCP.
- This update is the largest change to MCP since the protocol was first introduced.
- The update was authored by Anthropic employees David Soria Parra and Den Delimarsky, who are lead MCP maintainers.
Key quotes
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.