Coursera Spring Sale
40% Off Coursera Plus Annual!
Grab it
Explore the emerging security challenges in agentic AI development through this 28-minute conference talk from Docker's VP of Engineering, Nate Bittinger, presented at the AIAI Boston Summit. Discover how the Model Context Protocol (MCP) is becoming the backbone of modern AI workflows across platforms like VS Code and Claude Desktop, while simultaneously creating unexpected security risks as AI agents form unauthorized connections that expand attack surfaces. Learn to understand MCP's growing influence in AI development, identify critical vulnerabilities including ad-hoc servers, weak credentials, and inconsistent security policies, and implement centralized controls and governance frameworks to secure agentic development at enterprise scale. Gain insights into Docker's approach to helping development teams build and secure next-generation AI systems while maintaining operational efficiency and security compliance.
