On this page
Read
The useful mental model
MCP is a shared language between an AI application, the host, and the programs that provide context, the servers. The host keeps one client connection per server. Each server tells the client what it offers: tools the model can call, resources to read, and prompt templates. The host offers those tools to its model, and the model's calls go through the client to the server. MCP covers the connection, not the model's reasoning or what the application does with the results.
In plain English
It is a USB-C port for AI apps. Instead of a different cable for every service, the app and the service agree on one plug.
Where builders use it
- 01Connecting an assistant to a calendar, files, or a database
- 02Letting a coding agent use a design tool
- 03Giving several AI apps the same company data through one server
Why it matters
Without a shared standard, every AI app needs a custom integration for every system. With MCP, a server built once can work with any application that supports it. It also moves the important questions to the server and the host: what the tools can do, who may call them, and what a person must approve.
Why now
Anthropic open-sourced MCP in November 2024, and the project's documentation lists support across many AI assistants and developer tools. The specification is still evolving, and a recent version changed how connections and discovery work, so check the current specification before relying on a detail.
A common misconception
“MCP is a tool or a model.”
It is a protocol, a set of rules for how an AI application and a server talk. It does not choose tools for the model, run the model, or decide how results are used.
“An MCP server is safe because it follows a standard.”
The standard defines how a connection works, not whether a tool is safe. What a tool can do, who can call it, and what needs a person's approval are decisions for the server and the host.
See
See the mental model
The visual is generated from the same structured knowledge as the written explanation.
A system map: an AI application (the host) keeps one MCP client per server. Each client connects to an MCP server through a standard connection. The server offers tools, resources, and prompts, and does the work in an external system such as a calendar or a database.
Builder example
Connect one system to many AI apps without rewriting it
A team wants assistants in two different AI apps to read the same project notes and create tasks in the same tracker.
Failure
They write a separate custom integration for each app. Each behaves slightly differently, and any change to the tracker means fixing both.
Intervention
Build one MCP server that exposes a resource for reading notes, a tool for searching notes, and a tool for creating tasks. Mark the task tool as one that changes things, require sign-in, and let each AI app connect to the same server.
Observable result
Both apps list the same tools from one server. A change to the tracker is made once, and the create-task action asks for approval in each app.
Sources
Go deeper
- Model Context Protocol - What is MCP?
- Model Context Protocol - Architecture overview
- Anthropic - Introducing the Model Context Protocol
Last researched 12 October 2026