You are signed in. Close

You are signed out. Close

Thank you. Your subscription has started. Close

Thank you. You will get an email when a new comic comes out. Close

We could not confirm your payment. If you paid, use the link "Sign in" at the bottom of the page. Close

Something went wrong on our side. Please try again in a moment. Close

Project Visually
Random Sign in Subscribe
Previous episode AI agent permissions: who decides what an agent may do

How AI agents work: an AI that can only write, and still gets things done

MCP: how AI agents connect to the services you already use

MCP, the Model Context Protocol, is a standard way to connect AI agents to apps and services. Before MCP, every AI app needed its own link to every service, built by hand. Why was that a problem, and what did one shared standard change?

  1. 1 At first, every AI app needed its own link to every service, built by hand. Three apps and three services already make nine links to build and keep working.AI appsservicespicnic tableshotelcalendar

    At first, every AI app needed its own link to every service, built by hand. Three apps and three services already make nine links to build and keep working.

  2. 2 The park cannot build a link for your app and for every other AI app too. So it builds none, and your agent cannot book a table.picnic tablesthe parkyour appother AI apps

    The park cannot build a link for your app and for every other AI app too. So it builds none, and your agent cannot book a table.

The rest of this episode is for subscribers

Subscribe to read every premium episode. You can cancel when you want.

Paid yearly: $99 instead of $119.88

Next episode Context window: what happens when an AI agent's work stops fitting

Share this comic

More comics