Making Rails AI-Native with the Model Context Protocol
summary
Demonstrates how Rails becomes an AI-native app by adding a minimal template that creates an MCP server endpoint and an MCP tool generator so scaffolding yields HTTP-exposable tools alongside models. Shows a concrete flow: host loads tools, LLM issues tool calls, host executes travel and weather tools, LLM combines results and returns an action (book trip ID 41). Includes CRUD examples, a custom weather tool, a Rails-based MCP host, and a quick production deploy.
AI-written summary · about
chapters (9)
- 0:00AI-native Rails intro
- 3:00What is MCP
- 8:26MCP for LLM interactions
- 11:00Building MCP server
- 14:15MCP tools for Active Record
- 17:12Deploying MCP Rails app
- 21:52Custom MCP tools
- 24:41MCP host in Rails
- 26:08Summary
related talks
25mTools in your AI's Toolbox : An introduction to MCP Servers
26mBuilding AI-Enabled Spring Applications with Model Context Protocol (MCP)
33mThe Model Context Protocol: Connecting AI to Everything
30mComposable AI: Building Next-Gen AI Agents with MCP
50mBeyond local tools: Dive into the Model Context Protocol (MCP)
48mBuilding Scalable AI Tool Servers with Model Context Protocol (MCP) and Heroku
25mMaking AI Personal: Building Context-Rich AI Tools with MCP
34mPackaging & Deploying AI Tools with Model Context Protocol