Welcome to the Innovator Coffee, a podcast that bridges the gap between people and the world of AI and innovation. Follow us to explore the top AI applications, ecosystem insights, and the emerging trends.

In this episode of “Innovator Coffee" podcast, we featured an interview with Dr. Dimitry Chary from the MIT Media Lab. The discussion primarily focuses on MCP (Model Communication Protocol), explaining its role as a standardized JSON RPC schema that enables Large Language Models (LLMs) to interact seamlessly with various tools and services. The conversation also introduces Nanda, an MIT initiative aiming to establish an open, decentralized web of AI agents by addressing critical aspects such as agent discovery, reputation, security, and traceability, fostering a collective ecosystem for networked AI. While MCP excels in agent-to-tool communication, Nanda and other emerging protocols like A2A and ACP focus on the broader challenges of agent-to-agent interaction and a secure, accountable AI landscape.

Dr. Dimitry Chary is a researcher at the MIT Media Lab, where he works with Professor Ramesh Raskar in the decentralized AI group. He earned his PhD from UCLA in AI and computer vision.  At MIT, Dr. Chary focuses on a range of projects within the decentralized AI and networked AI agents space. His work includes:

• Decentralized AI.

• Networked AI agents.

Here is a summarized version of the podcast, broken down into six sections with timestamps:

• Introduction to Dr. Dimitry Chary and MCP's Core Purpose (00:03 - 05:43) 

• How MCP Servers Operate and Protocol Comparisons (05:43 - 13:03) 

• Technical Architecture of MCP (13:03 - 21:20) 

• The Nanda Project: Extending Beyond MCP (36:46 - 59:38) 

• Future Vision and Broader Implications of AI Agents (59:38 - 01:13:57) 

Hosts: 

Tom Kong

*Stanford EE alumni,

*Founder@ Stanford AGI Adventist Community (10K+ members so far from top VC, Engineers, startups from Silicon Valley )

*AI Lecturer, a serial entrepreneur in media and data. Advisor @ techtimes.com

*AI deployment for 8 years, with NLP and recent LLMs (RAG, Agent, Diffusion)

Wickey Wang

*IT Security Compliance/Auditor & CSTU Faculty

*Growth fund VC advisor, Early stage fund fellow and Angel Investor with cybersecurity and AI focus

*GAI Security book co-author 

*AI Security/EmergingTech Security Non-Profit (SafenAI) Co-founder

Special thanks to Hannah Wang who did the wonderful job to assist to complete this podcast. https://www.linkedin.com/in/hannah-wang-9302421b3/

Questions, Suggestions, Feedback and Comments? You can find us in LinkedIn:

https://www.linkedin.com/in/wickey-wang-cisa-six-sigma-green-belt-2aaa913

https://www.linkedin.com/in/thomaskong/