Guide · Connecting

Model Context Protocol and tool use

The Model Context Protocol is an open standard for connecting AI assistants to outside systems: files, databases, APIs and applications. Anthropic published it in November 2024, and it has since been adopted well beyond them. It replaces one custom integration per tool per assistant with one server any client can speak to.

Last reviewed Who this is for: People who have hit the ceiling of pasting things into a chat window and want the assistant to reach their actual files, data and tools.

How long does it take to learn?

Connecting an existing server takes ten minutes. Understanding what you just granted takes an evening. Writing your own server is a weekend if you can already code, and it is the point where the whole idea stops being abstract.

The fastest path, in order

  1. 01

    Learn the three pieces

    A host is the app you use, a client lives inside it, a server exposes one system. That separation is the entire idea: the server is written once and every client can use it, which is why the standard exists at all.

  2. 02

    Connect an existing server first

    Filesystem, GitHub or a Postgres server, attached to a client you already use. Seeing an assistant read your own repository is what makes the abstraction click, and it costs nothing.

  3. 03

    Learn what tools, resources and prompts each mean

    Tools are actions the model can take, resources are things it can read, prompts are reusable templates the server offers. Most confusion about MCP is these three being blurred together.

  4. 04

    Understand the permission you just granted

    A tool call is code running on your machine with your access. Read what a server can do before connecting it, and treat a third-party server the way you would treat a browser extension asking for everything.

  5. 05

    Write a small server of your own

    One tool, one resource, against something you actually use. The official SDKs make this an afternoon, and having written one is what makes every other server legible.

  6. 06

    Design for failure

    Tools time out, return nonsense and get called with arguments you did not anticipate. A server that fails clearly is worth more than one with ten features, because the model reads your error message and can act on it.

Tools worth your time

ToolWhat it is for
Claude Desktop and Claude CodeThe reference clients: the fastest way to have a working MCP setup today.
Official MCP SDKsTypeScript and Python libraries for writing a server without handling the protocol yourself.
MCP InspectorLocal tool for calling your server's tools by hand, which is how you debug one.
Filesystem serverThe canonical first connection: scoped read and write access to a directory you choose.
GitHub serverIssues, pull requests and code, which turns an assistant into something that knows your project.
Database serversPostgres and friends, read-only until you are certain. Start read-only and stay there a while.

Server directories are growing quickly and are not curated in any meaningful sense. A server runs with your permissions on your machine. Read the source of anything you did not write, prefer servers whose scope you can restrict, and connect one at a time.

Mistakes that cost people weeks

The track that teaches it

Why this is the fastest way to actually get there

MCP is documented for people building servers and barely explained to people trying to understand what it is for. Most of the difficulty is conceptual, and it disappears in about twenty minutes if the three pieces are introduced in the right order.

  • The mental model comes first and the code second, which is the opposite of the official docs and the right way round for learning.
  • Security is taught as part of connecting rather than as a warning at the end, because the first server you connect is where the habit is set.
  • A track that gets rewritten as the standard moves. This subject is a year old and still changing, which is exactly where recorded courses go stale fastest.

Questions people ask

A standard plug. Before it, every AI app needed custom code for every tool it touched. With it, a tool is exposed once as a server and any assistant that speaks the protocol can use it.

Anthropic published it as an open standard in November 2024. It is open source, and adoption has spread well past Anthropic's own products, which is the reason it is worth learning rather than one vendor's feature.

No, to connect servers others have written: that is configuration, not programming. Yes, to write your own, though a small server is a genuinely reasonable first coding project.

The protocol is a protocol. The risk is in the servers, because a tool call is code running with your access. Treat an unfamiliar server the way you would treat any software you did not write, and start read-only.

What MCP is and why it exists, connecting servers to the assistants you already use, writing your own, and keeping control once the model can act rather than only answer.

Vincoria opens soon.

One email when the doors open. Nothing else.

Founding members hear first. No spam.

Used only to tell you when Vincoria opens. One click to leave, from any email. Privacy policy

Next stepStart Lesson 01 · freeDevelop with AI · 9 min