← back
Letting AI Interface with your App with MCP — Kent C Dodds
Original: Letting AI Interface with your App with MCP — Kent C Dodds
Takeaway
MCP is the standard glue layer that finally lets every app expose itself to every AI assistant — build MCP servers or get bypassed.
Summary
- Kent C. Dodds frames MCP via Iron Man's Jarvis — the missing piece for AI assistants has always been integrations, not LLMs or UIs.
- Three phases of LLM apps: phase 1 (chat with manual context copy-paste), phase 2 (host apps with proprietary integrations like ChatGPT plugins), phase 3 (MCP as open standard so any service exposes tools to any AI host).
- MCP solves the long-tail problem: OpenAI/Anthropic will never build an integration for your city's pavilion-reservation site, but with MCP they don't have to.
- Argues product devs must expose their app via MCP to remain reachable as users migrate into AI assistants as the new UX layer.
- Demo covers MCP architecture and developer responsibilities (tool design, auth, descriptions).
mcpintegrationsai-ux
Original description
We are entering a new era of user interaction. It's being built right before our very eyes and changing rapidly. As crazy as it sounds, soon each one of us will get our own Jarvis capable of performing actually useful tasks for us with a completely different user interaction mechanism than we're used to. But someone's gotta give Jarvis the tools to perform these tasks, and that's where we come in. In this talk, Kent will live code an MCP server and use it with an AI assistant to help us catch the vision of what this future could look like and our role in it.