One Year of MCP — with David Soria Parra and AAIF leads from OpenAI, Goose, Linux Foundation
Latent Space: The AI Engineer Podcast
In this episode of the Latent Space Podcast, Alessio and Swix host David Soria Parra from Anthropic, along with Jim Zemlin from the Linux Foundation, Nick Cooper from OpenAI, and Brad from Block, to discuss the Model Context Protocol (MCP) and the newly launched Agentic AI Engineering Foundation (AAIF). The conversation covers the evolution of MCP, its adoption across major tech companies, and its role in agentic AI. They delve into the technical aspects of MCP, including authentication, transport protocols, and the challenges of balancing model improvements with protocol design. The discussion also explores the goals of the AAIF, its governance, and the incentives for projects to join the foundation, highlighting the importance of community, open standards, and the potential for agentic AI to transform various industries.
Part 1: MCP Origins and Technical Foundation
Part 2: Architecture, Registry, and Use Cases
Part 3: Advanced Features and User Interface
Part 4: The Agentic AI Foundation and Governance
Part 5: Future Outlook and Community
Sign in to continue reading, translating and more.
Open full episode in Podwise