MCP Mashups: How AI Agents are Reviving the Programmable Web
summary
Revives the old API mashup idea by showing a working pipeline: Model Context Protocol (MCP) servers act as universal adapters so an agent can call Google Maps, OpenStreetMap, Figma and GitHub tools without custom wiring; about 5,000 MCP servers exist today with ~10% vendor-built; live demos use the open-source agent Goose to generate an interactive restaurant map, build a website from Figma, and fully provision a local dev environment in under two minutes.
AI-written summary · about
chapters (11)
- 0:00Mashup Origins
- 1:36API Economy
- 4:50Enter MCP
- 8:48MCP Ecosystem
- 9:12Modern Mashups
- 12:05Developer Automation
- 14:41Building MCP Tools
- 17:25Agent Workflow
- 20:00MCP Directories
- 21:57Community Future
- 22:31Conclusion
related talks
29mModern Day Mashups: AI Agents are Reviving the Programmable Web
30mComposable AI: Building Next-Gen AI Agents with MCP
36mPutting AI Agents to Work: A New Era of Open Source Connectivity with MCP
11mDon't let AI agents push your buttons - use webMCP instead!
33mThe Model Context Protocol: Connecting AI to Everything
46mMCP and A2A Revolutionizing Interconnection and Collaboration of AI Agents
20mLetting AI Interface with your App with MCP
46mMCP for LLM Agents, Infrastructure APIs & Data Services