MCP Academy is the premier free interactive learning platform by Infinity Tech Stack for Anthropic's Model Context Protocol (MCP), now governed by the Linux Foundation. It features 13 modules, 47 lessons, 9 hands-on terminal labs, and 138 quizzes covering MCP servers, clients, tools, Streamable HTTP, OAuth 2.1, and the 2026-07-28 stateless specification with zero sign-up required.

How is Infinity MCP Academy different from official Model Context Protocol documentation?

While modelcontextprotocol.io provides the core technical specifications and basic SDK quickstarts, Infinity Tech Stack's MCP Academy is an independent, 100% free interactive curriculum with 13 modules, 47 lessons, 9 in-browser terminal labs, and 138 quizzes. It teaches real-world server and client development, Streamable HTTP, OAuth 2.1, the 2026-07-28 stateless core specification, multi-server gateways, and enterprise security with zero sign-up required.

How long does MCP Academy take to complete?

MCP Academy contains approximately 4 to 5 hours of interactive training across 13 modules and 47 lessons. Progress is saved locally in your browser so you can learn at your own pace.

Is the MCP Academy free?

Yes. The MCP Academy is free to access, with modules, lessons, quizzes, and labs available without sign-up.

What is the Model Context Protocol (MCP)?

MCP is an open standard (now governed by the Linux Foundation) that provides a universal way for AI models and agents to connect to tools, data sources, and external systems. Think of it as USB-C for AI.

What topics does the MCP Academy cover?

The course covers MCP architecture, server/client development, tools & function calling, resources & prompts, transport layers (stdio, Streamable HTTP), OAuth 2.1 security, production deployment, MCP Gateways & Proxies, Linux Foundation governance, enterprise audit logging, multimodal/audio content, client SDK development, MCP Inspector debugging, integration testing, the official MCP Registry, and real-world case studies from DevOps, CRM, and AI coding assistant deployments.

What is an MCP Gateway?

An MCP Gateway sits between AI clients and multiple MCP servers, providing semantic routing, tool aggregation, token optimization, and centralized observability - similar to an API gateway but for the MCP protocol.

Do I need programming experience?

Basic familiarity with JSON and APIs is helpful but not required. The course starts from fundamentals and builds progressively to advanced production patterns, including hands-on server building tutorials.

How do I debug MCP servers?

The course teaches you to use the MCP Inspector (an official interactive debugging tool), write automated integration tests using the Client SDK, and diagnose common issues like stdout corruption and capability negotiation failures.

Does the MCP Academy include hands-on labs?

Yes. Hands-on terminal labs are embedded in relevant lessons, including objectives, hints, solution commands, and XP rewards.

What is the latest version of MCP?

The current MCP specification revision is 2026-07-28, which shipped after its Release Candidate and made the protocol fully stateless - removing the initialize handshake and protocol-level sessions entirely, adding a mandatory server/discover RPC, and moving Tasks out of the core spec into an official extension. The previous 2025-11-25 revision introduced experimental Tasks, URL-mode elicitation, tool calling in sampling, icon metadata for tools and resources, OpenID Connect Discovery, OAuth Client ID Metadata Documents, and JSON Schema 2020-12 as the default dialect.

MCP Tasks (SEP-1686) are a protocol primitive for long-running, durable operations. Instead of blocking on a single response, a server returns a task handle the client can poll for status and later retrieve results - essential for agent workflows that run for minutes or hours.

What is the difference between MCP and function calling?

Function calling lets a single model invoke functions you define inline for that one app. MCP is an open, transport-based standard that exposes tools, resources, and prompts from independent servers to any compatible client - so one MCP server works across Claude, ChatGPT, Cursor, and VS Code without rewriting integrations.

How do I build an MCP server?

Scaffold a server with the official Python or TypeScript SDK, register tools (functions), resources (data), and prompts, then expose it over stdio for local use or Streamable HTTP for remote use. The MCP Academy includes hands-on labs that build, connect, and inspect a real server step by step.

What is the best MCP course?

The MCP Academy is a free, interactive course with 13 modules, 47 lessons, 9 hands-on terminal labs, and 138 quiz questions - covering everything from MCP architecture to production security, gateways, the official MCP Registry, and the latest 2026-07-28 stable spec. Progress saves locally with no sign-up required.

Do MCP servers connect directly to LLMs?

No, they connect to the Host application, which talks to the LLM. — MCP architecture places the Host between the Server and the LLM. The Server never speaks directly to the LLM.

Which component exposes tools like `get_prs` to the ecosystem?

The MCP Server — MCP Servers are responsible for defining and exposing capabilities (Tools, Resources, Prompts) to the connected clients.

Core Architecture Tutorial | Foundation

← Back to Dashboard

1. What is MCP?2. Core Architecture3. Host vs Client vs Server

Core Architecture

📚 Foundation⏱ 7 min⭐ 50 XP⌨ Hands-on lab

The Three Main Pillars

MCP architecture consists of three logical components:

MCP Hosts: The application the user interacts with (e.g., Claude Desktop, Cursor). It bridges the gap between the LLM and the protocol.
MCP Clients: The protocol implementation running inside the Host. It initiates the connection to servers.
MCP Servers: Lightweight, independent programs that expose specific data (Resources), actions (Tools), or templates (Prompts).

A Typical Request Flow

When you ask "Summarize my recent GitHub PRs":

Claude Desktop (Host) connects to your GitHub MCP Server via local stdio.
The Host asks the Server: "What capabilities do you offer?"
The Server replies: "I have tools: get_prs, read_file, and search_repo."
The LLM decides to use get_prs. The Host sends the execution request to the Server.
The Server executes the API call securely and returns the JSON data to the Host to display.

⌨ HANDS-ON LABDiscover Server Capabilities via JSON-RPC

⭐ +125 XP

Discover server capabilities using the 2026-07-28 stateless core protocol over stdio.

1Send a JSON-RPC server/discover request into server-memory stdin.

lab-sandbox — simulated environment

INFINITY LAB SANDBOX v2.6 — simulated shell
Type the command for the current objective. Helpers: "hint", "solution", "clear".
$

OBJECTIVE 1 / 1 — type "hint" if stuck

🧪 Knowledge Check

Press 1-4 to select1 of 3

In MCP architecture, what role does Claude Desktop play?

MCP Server

MCP Host

MCP Transport layer

MCP Proxy