Uploaded July 2026 | Updated September 2026, 2 weeks ago
🎙️ What are enterprises using MCPs for?
João Moura talks about how when CrewAI started rolling out MCP support, they assumed customers would want access to thousands of public MCP servers. Turns out, that wasn't the priority. What enterprises actually wanted was a way to manage their own internal MCPs — the ones they'd already built in-house. The real value of MCP isn't the marketplace. It's the standard itself. When everyone uses the same protocol, migrating from one tool to another gets simpler — swap the MCP, and your setup should still work. MCP has enough adoption and momentum now that it's here to stay.
🎧 Watch the full episode: youtu.be/DGGLhUt42LM
🔗 View all podcasts: datasciencedojo.com/podcast
#MCP #AgenticAI #AIInfrastructure #CrewAI #Interoperability #FutureofDataAndAI
🎙️ What are enterprises using MCPs for?
João Moura talks about how when CrewAI started rolling out MCP support, they assumed customers would want access to thousands of public MCP servers. Turns out, that wasn't the priority. What enterprises actually wanted was a way to manage their own internal MCPs — the ones they'd already built in-house. The real value of MCP isn't the marketplace. It's the standard itself. When everyone uses the same protocol, migrating from one tool to another gets simpler — swap the MCP, and your setup should still work. MCP has enough adoption and momentum now that it's here to stay.
🎧 Watch the full episode: youtu.be/DGGLhUt42LM
🔗 View all podcasts: datasciencedojo.com/podcast
#MCP #AgenticAI #AIInfrastructure #CrewAI #Interoperability #FutureofDataAndAI





![Should You Trust ChatGPT With Your Data? | Jerry Liu x Data Science Dojo
🎙️ Future of Data and AI Podcast: Highlight with Jerry Liu (CEO & Co-Founder, LlamaIndex)
Should you trust ChatGPT with your data? Jerry Liu breaks it down.
In this highlight, Jerry explains how modern AI systems handle user data, what actually gets stored, and why understanding data flows is crucial before pasting sensitive information into any AI tool. He clarifies common misconceptions, privacy boundaries, and what organizations should keep in mind when using LLMs for real-world work.
💡 Key takeaway: AI tools aren’t inherently risky — but you need to know how they treat your data before you trust them.
Watch this clip to understand the real story behind data privacy in ChatGPT and other LLMs.
🔗 Watch the full episode: [Insert Link]
🎧 Explore more episodes: https://www.youtube.com/playlist?list=PL8eNk_zTBST_jMlmiokwBVfS_BqbAt0z2 Should You Trust ChatGPT With Your Data? | Jerry Liu x Data Science Dojo](https://i.ytimg.com/vi/nEDvHwM15mc/mqdefault.jpg)




