Making AI Personal: Building Context-Rich AI Tools with MCP
summary
Shows how to build a personal MCP server in a few hours: a JSON-RPC MCP with three messages (initialize, list tools, call tool) served over standard in/out MCP server that wraps functions or APIs. Demos include uptime check, YouTube lookup (about 1,400 views, 3.2 like-to-view ratio), Nyx package searches, and a DuckDB “remember that” inbox for weekly status summaries. Emphasizes narrow tool footprints for security and using reflection or annotations to expose function signatures as JSON.
AI-written summary · about
chapters (10)
- 0:00Intro
- 2:02What is agentic AI?
- 4:57Demo: Let's ask a question
- 7:30How did that work?
- 9:07How to build an MCP server
- 12:37The delegated-coding approach
- 16:16Testing tip
- 16:55Demo
- 19:22Examples
- 24:11Outro
related talks
25mTools in your AI's Toolbox : An introduction to MCP Servers
30mComposable AI: Building Next-Gen AI Agents with MCP
01h 31mBuild AI-Powered Automation Tools: MCP Workshop for Developers & Engineers
20mLetting AI Interface with your App with MCP
01h 01m.NET Meets MCP: Build Your Own AI-Powered Service with C#
35mMCP in Action: Real-World Use Cases & Design Patterns
39mHow to connect your systems to AI Tools with MCP Servers
37mLetting AI Interface with Your App with MCPs