Suthahar Jegatheesan MSDEVBUILD / blog Multi-Stack Dev Build · by Suthahar
Search
Azure

What is MCP?

Model Context Protocol — how an AI assistant reaches GitHub, your database, your files and Slack.

What you'll learn

  • Why a model on its own cannot reach GitHub, SQL or Slack
  • How an MCP client and server carry one request down and back
  • Why M + N connectors beats M × N bespoke integrations
Azure 8 steps 27 seconds —views

Was this useful?

Share

Understand it one step at a time

The short runs these in order in about 27 seconds. Here they are written out — pick any step to jump the short straight to it.

1 Step 1 of 8

AI can talk. It cannot reach your tools

A language model answers purely from its training and the prompt. It has no native route into GitHub, your database, your files, or Slack.

Frequently asked questions

What problem does MCP actually solve?
Without it, every AI assistant that wants to talk to every tool — GitHub, SQL, Slack, and so on — needs its own bespoke integration: M assistants times N tools worth of connectors. MCP standardizes the protocol so each tool needs one MCP server and each assistant needs one MCP client — M + N instead of M × N.
Can a language model reach external systems like GitHub or a database on its own?
No — a model has no ability to call out to anything by itself. An MCP client and server carry the request down to the tool and the response back, which is what actually lets the assistant act rather than just generate text.

Free app · no app store

These are built for a phone

Every short is drawn at full portrait height, the shape a phone already is. Installed, it opens full-bleed with no address bar across the top — and the whole library reads offline.

How it works

Read deeper on Azure

Twenty seconds gets the shape of an idea across. These go into how it behaves in production.

More shorts

Get new posts by email

New technical articles, Azure AI and GitHub Copilot updates, and upcoming events. No spam, unsubscribe anytime.

↑↓ navigate ↵ open