In this week's episode of AI That Works, we're diving into the world of MCPs - the good, the bad, and the context window!
We're cutting through the noise to discuss whether MCPs are really worth the hype, or if there are better solutions out there for your AI applications. We'll explore how MCPs work in practice, when they make sense, and when they might be holding you back. Plus, we'll talk about the different kinds of alpha that are available to companies in the AI space and how you can get an edge, including using the best tools for the job.
Join us as we navigate this on-again, off-again relationship with MCPs and try to find some practical takeaways for building better AI solutions.
Check out our github: https://www.github.com/boundaryml/baml
AI That Works repo: https://github.com/ai-that-works/ai-that-works
Socials:
X: https://x.com/boundaryml
Discord: https://discord.com/invite/yzaTpQ3tdT
LinkedIn: https://www.linkedin.com/company/boundaryml/
⏱️ Chapters:
Intro
Defining MCP
Roadblocks for MCP
MCP Use Cases
Model Source Considerations
RL-ing the Model
Primary Use Cases
Session Security
Upcoming Live Event
Transcript
I've watched this one closely. Ask me anything about it and I'll point you to the exact moment.