Event details
Nov
12
LLM Collective
The LLM Collective is a user group for language model users of all experience levels and abilities to discuss the rapidly evolving changes in this space and create fun things.
This month, we're diving deeper into the Model Context Protocol (MCP) with a hands-on session led by Jérémie Lumbroso. Building on last month's local MCP setup, we'll explore the "remote" side of the protocol—connecting AI systems to custom tools and giving them new capabilities.
We'll work through a practical example: teaching an AI about the passage of time. This might sound whimsical (yes, that meme), but it demonstrates something profound about how we can expand AI understanding through MCP. This will be a step-by-step walkthrough that you can follow along with in real-time.
What you'll need:
- A GitHub account (required)
- A Replit account (recommended—register in advance if you want to deploy your own server during the session)
- A Claude account (easiest platform to work with remote MCPs)
Goal: Everyone leaves with their own working MCP server that they can hack, modify, and use with their AI tools.
This is an interactive, hands-on session, so come ready to code, ask questions, or just observe and learn. As always, we'll also have introductions and a news roundup.
Based on this article: https://medium.com/@jeremie.lumbroso/teaching-ai-the-significance-of-the-passage-of-time-yes-that-one-106ad7d20957
This month, we're diving deeper into the Model Context Protocol (MCP) with a hands-on session led by Jérémie Lumbroso. Building on last month's local MCP setup, we'll explore the "remote" side of the protocol—connecting AI systems to custom tools and giving them new capabilities.
We'll work through a practical example: teaching an AI about the passage of time. This might sound whimsical (yes, that meme), but it demonstrates something profound about how we can expand AI understanding through MCP. This will be a step-by-step walkthrough that you can follow along with in real-time.
What you'll need:
- A GitHub account (required)
- A Replit account (recommended—register in advance if you want to deploy your own server during the session)
- A Claude account (easiest platform to work with remote MCPs)
Goal: Everyone leaves with their own working MCP server that they can hack, modify, and use with their AI tools.
This is an interactive, hands-on session, so come ready to code, ask questions, or just observe and learn. As always, we'll also have introductions and a news roundup.
Based on this article: https://medium.com/@jeremie.lumbroso/teaching-ai-the-significance-of-the-passage-of-time-yes-that-one-106ad7d20957
University programs and activities are open to all eligible participants without regard to identity or other protected characteristics. Sponsorship of an event does not constitute institutional endorsement of external speakers or views presented.
View physical accessibility information for campus buildings and find accessible routes using the Princeton Campus Map app.