AI RundownDaily
Reference Guide · Free to Share

MCP Architecture Diagram

A visual reference for the Model Context Protocol (MCP) — the emerging standard for connecting AI agents to external tools, APIs, and data sources.

Based on the official MCP specification  ·  Read the full MCP guide →

The Three-Layer Architecture

HOST

MCP Host

The AI application (Claude Desktop, Cursor, custom app). Manages connections, enforces trust boundaries, routes requests.

e.g. Claude Desktop, Cursor, custom agent

CLIENT

MCP Client

Lives inside the Host. Maintains a 1:1 connection with each MCP Server. Handles protocol negotiation and message routing.

e.g. One client per server connection

SERVER

MCP Server

Exposes capabilities (Tools, Resources, Prompts) to the client. Can be local (stdio) or remote (HTTP/SSE). Calls external APIs or systems.

e.g. Filesystem, GitHub, Slack, databases

Transport: stdio (local)  |  HTTP + SSE (remote)  ·  Protocol: JSON-RPC 2.0

HOST

MCP Host

The AI application (Claude Desktop, Cursor, custom app). Manages connections, enforces trust boundaries, routes requests.

CLIENT

MCP Client

Lives inside the Host. Maintains a 1:1 connection with each MCP Server. Handles protocol negotiation and message routing.

SERVER

MCP Server

Exposes capabilities (Tools, Resources, Prompts) to the client. Can be local (stdio) or remote (HTTP/SSE). Calls external APIs or systems.

Request Flow: User → Tool → Answer

1

User sends request

User types a message or triggers an action in the Host application.

2

Host routes to LLM

Host sends the conversation (with available tool list) to the AI model.

3

Model selects tool

LLM decides which MCP tool to call and generates the tool call arguments.

4

Host authorises

Host checks user consent and permission policies before allowing the call.

5

Client calls Server

MCP Client sends the tool call to the appropriate MCP Server.

6

Server executes

Server calls the underlying API, filesystem, or database and returns results.

7

Result returned

Result flows back: Server → Client → Host → LLM → final answer to user.

MCP Primitives — What Servers Expose

⚙️

Tools

Defined by Server

Executable functions the model can call. Have names, descriptions, and JSON Schema input specs. Examples: search_files, send_email, query_db.

📄

Resources

Defined by Server

Read-only data the model can read. URI-addressed. Examples: file:///repo/README.md, postgres://db/schema.

💬

Prompts

Defined by Server

Reusable prompt templates with arguments. Let servers define standard workflows.

🔁

Sampling

Defined by Server→Host

Server requests the Host to call the LLM. Enables agentic loops where servers can initiate model inference.

Go Deeper