Q&A with Kent C. Dodds
summary
Focus is on Model Context Protocol (MCP) as a replacement for websites that lets services be actioned via chat apps so the end user pays for the model and the service avoids per‑user LLM costs. Actual tools used: Cursor, ChatGPT, Gemini, plus Raycast and Claude. Biggest technical pain is non‑determinism and not controlling which model or client users run, like browser variability. MCP servers are hosted on Cloudflare, which simplifies deployment. Web devs shift to building MCP servers.
AI-written summary · about
related talks
45mModel Context Protocol (MCP): The future of user interactions?
44mBeyond the Prompt: How MCP Connects Language Models to Real Tools
46mMCP for LLM Agents, Infrastructure APIs & Data Services
32mMCP for dummies: Feed more context to LLM
33mThe Model Context Protocol: Connecting AI to Everything
26mBuilding AI-Enabled Spring Applications with Model Context Protocol (MCP)
43mLLMs, Meet Your Tools: The Magic of Model Context Protocol
25mFrom Idea to Integration: An Intro to the Model Context Protocol (MCP)