# MCP host, client and server: what is the difference?

In MCP, the host is the AI application you use (such as Claude Desktop or VS Code), a client is the part of the host that keeps one connection to one server, and a server is the program that offers tools, resources and prompts. A host with three servers runs three clients.

## An example

VS Code is the host. When you connect it to a Sentry server and a filesystem server, it creates two MCP clients, one for each. The Sentry server runs on Sentry's platform and is reached over the internet; the filesystem server runs on your computer.

## Why the split matters

Each client has its own connection, permissions and sign-in, so one server never sees another server's data through the protocol. See [how MCP works](https://ai-powered.com/academy/glossary/mcp) and [Streamable HTTP and stdio](https://ai-powered.com/academy/glossary/streamable-http-and-stdio).

## Sources

Official documentation, checked on 19 November 2026:

- [MCP architecture overview (modelcontextprotocol.io)](https://modelcontextprotocol.io/docs/learn/architecture)

## Related terms

- [MCP](https://ai-powered.com/academy/glossary/mcp): MCP (Model Context Protocol) is an open standard for connecting AI applications to outside tools and data. An AI app connects to small programs called MCP servers, asks each one what it offers, and calls those tools when a task needs them.
- [Streamable HTTP and stdio](https://ai-powered.com/academy/glossary/streamable-http-and-stdio): MCP has two standard transports. stdio connects an app to a server it starts on the same computer, through standard input and output. Streamable HTTP connects an app to a server over the network with HTTP POST, optionally streaming responses, and supports normal web authentication.
- [Tool call](https://ai-powered.com/academy/glossary/tool-call): A tool call is a structured request from an AI model to run one of the functions it was given, with arguments that match the function's input schema. The app runs the function, sends the result back to the model, and the model uses it to answer or to decide its next step.
