The Agentic AI Foundation has released significant updates to the Model Context Protocol (MCP), introducing a stateless architecture, enhanced authentication, and formal deprecation guidelines to strengthen the open standard connecting AI agents to enterprise software.
The updated MCP features a fully stateless architecture that improves scalability and reduces complexity for developers integrating AI agents with existing systems. The hardened authentication model strengthens security protocols for agent-to-software interactions.
A formal 12-month deprecation policy provides clear timelines for feature transitions, giving organizations predictable planning windows for updates. This structured approach addresses concerns about stability in rapidly evolving AI infrastructure.
MCP has become the connective layer enabling AI agents to interact with diverse software systems and data sources. The protocol's open standard design allows interoperability across platforms, reducing vendor lock-in.
These updates reflect growing enterprise adoption of agentic AI systems and demand for production-ready infrastructure. The changes aim to make MCP more suitable for mission-critical deployments where reliability, security, and long-term maintainability are essential.
Denmark's government is cracking down on academic dishonesty by requiring upper secondary students to verbally defend their essays and complete assignments under computer monitoring.
Google has expanded its Ask Maps feature to handle food orders, hotel reservations, and attraction searches through conversational AI. The update rolls out to 130+ countries in English.
Meta released Muse Spark 1.2 and its coding agent Muse Code, competing on price rather than performance with rates as low as 20 cents per million output tokens.
Content creators using AI face uncertainty as the EU AI Act takes effect. Some worry about business disruption while others are embracing transparency as a competitive advantage.