MCP Mashups: How AI Agents are Reviving the Programmable Web

What if you could build complex applications just by describing them? See how AI agents are reviving the programmable web, making mashups fun and easy again.

#1about 4 minutes

Remembering the creative API mashup era of the 2000s

Early developers combined services like Google Maps and Craigslist to create novel applications, sparking the API economy.

#2about 1 minute

Why the original mashup era couldn't last

Mashups declined due to the high maintenance burden of changing APIs and the lack of long-term commitment for side projects.

#3about 2 minutes

How MCP enables modern AI agent mashups

The Model Context Protocol (MCP) is an open standard that acts as a universal adapter for AI agents to interact with various APIs and tools.

#4about 2 minutes

Exploring the open and rapidly growing MCP ecosystem

MCP's open-source nature has led to a massive, community-driven ecosystem of servers and SDKs in languages like TypeScript, Python, and Rust.

#5about 2 minutes

Demo of an AI agent creating a restaurant map

An AI agent uses a natural language prompt to combine Google Maps and developer tools to build an interactive restaurant map in seconds.

#6about 1 minute

Demo of an AI agent converting Figma to code

An AI agent uses MCPs for Figma and developer tools to automatically generate a functional website from a design file.

#7about 2 minutes

Demo of an AI agent automating project setup

An AI agent automates the entire setup for a complex project by reading instructions, cloning repos, installing dependencies, and configuring containers.

#8about 2 minutes

Understanding the basic structure of an MCP server

An MCP server is built by defining tools with clear names, descriptive purposes, parameters, and an execution body using an SDK.

#9about 3 minutes

How AI agents use the agentic loop for tasks

The agentic loop is the process where an agent interprets a prompt, selects the best tools via an LLM, executes them, and repeats until the task is complete.

#10about 2 minutes