MCP architecture: host, client, server

The participant model and the two layers, which the exam states precisely.

4 min read · Lesson 1 of 10 in this domain

MCP exists to solve an M×N problem: without it, every AI application needs bespoke glue for every data source. MCP standardises that boundary so any compliant client can talk to any compliant server. The vocabulary matters because the exam uses it precisely. The host is the AI application itself. It creates one client per server, and each client holds a dedicated one-to-one connection — there is no multiplexing. The server is the program exposing capabilities. Underneath sit two layers: a data layer speaking JSON-RPC 2.0, and a transport layer handling connection and auth.

• Host — the AI application (Claude Code, Claude Desktop, an IDE). It coordinates one or more clients.
• Client — the host creates one client per server, each holding a dedicated connection. Connections are one-to-one; there is no multiplexing.
• Server — a program that provides context, running locally or remotely.
• MCP has two layers: a data layer (the JSON-RPC 2.0 protocol, primitives, notifications) and a transport layer (connection, framing, authorisation).
• The wire protocol is JSON-RPC 2.0 — not gRPC, not REST, not SOAP. Notifications are used where no response is required.
• "Local" and "remote" describe where the server runs and which transport it uses, not what it can expose. Both can offer all primitives.

Source: MCP — Architecture overview · Independent study aid, not affiliated with or endorsed by Anthropic.