Model Context Protocol tutorial

Learn how AI apps connect to tools and data with MCP, then design, build and run your own servers safely.

Course contents

MCP Basics — What the Model Context Protocol is, why it was made, the open spec and its 2026-07-28 version, the standard shape of every setup, and the three things a server can offer: tools, resources and prompts.
MCP Mental Model — The five roles in every MCP setup (user, host, client, server, backend), why each server gets its own client, and the main duties of hosts and servers.
Connected Protocol Workflows — Custom integrations versus MCP, hardcoded versus discovered tools, the steps of one connected request from discovery to answer, context assembly, interoperable servers, and governance basics.

Protocol Architecture — The three layers of MCP (application, message, transport), the three kinds of messages, progress updates, cancellation on each transport, and how server requests became Multi Round-Trip Requests.
JSON-RPC Messages — Every field of MCP requests, responses and notifications, id matching, the core methods, _meta and resultType, error codes, tool errors versus protocol errors, and why servers are now stateless.
Transports — How MCP messages travel: stdio with process lifecycle, line framing and sandboxing; Streamable HTTP with one POST per request, SSE streams and MCP headers; legacy HTTP+SSE; and local versus remote trade-offs.
Discovery and Versioning — server/discover, per-request versions in _meta, the -32022 unsupported version error, server and client capabilities, list changes through subscriptions/listen, the legacy initialize handshake, and clean shutdown.

Tools — How to define MCP tools well: name, title, description, JSON Schema 2020-12 input schemas, atomic single-verb design, strict types, and annotations for side effects.
Resources — The MCP resource model: URIs, names and MIME types, text and base64 blob contents, resource templates, common kinds of resources, and why reads must be read-only and deterministic.
Prompts — MCP prompts: names, titles, descriptions and arguments; prompts/get messages with embedded resources; argument completion; safe interpolation; and prompts versus server instructions.

Tool Call Execution — The steps of an MCP tool call: catalog, inspection, selection, approval, tools/call and results, with content blocks, outputSchema and structuredContent, isError, progress and cancellation.
Tool Schema Validation — Validating MCP tool calls on client and server: missing, wrong-type, out-of-range and unknown arguments; schema design; error frames; output validation; and partial results.
Resource URIs — Resource URI parts and schemes, path and query templates, text and base64 contents with MIME types, the resource methods, and freshness with ttlMs, cacheScope and update notices.
Resource Context Assembly — Turning MCP resources into safe, useful context: source tags, freshness, field filtering, truncation, redaction, read-only enforcement and scope validation.

Multi Round-Trip Requests — How servers ask for input in 2026-07-28: input_required results, inputRequests and inputResponses, the client retry loop, requestState and how to protect it, round limits, and the Tasks extension.
Elicitation — How MCP servers ask users for input: elicitation/create in form and URL mode, client capabilities, flat form schemas, host and server validation, accept, decline and cancel, and keeping secrets out of forms.
Roots, Sampling and Logging — The three client features deprecated in 2026-07-28, why they were deprecated, the 12-month window, and migration paths: tool arguments and scopes, the host's model or your own model API, and stderr with OpenTelemetry.

Server Architecture — Designing MCP servers: one domain per server, modular handlers with handler, service and backend layers, atomic tools, least privilege, and explicit approval contracts for risky tools.
Development Environment — The tools for building MCP servers: the TypeScript and Python SDKs, the MCP Inspector, project structure, environment variables and secrets, pinned dependencies, and publishing to the MCP Registry.
Host Configuration — Connecting MCP servers to hosts: stdio and HTTP entries, VS Code mcp.json with inputs and dev mode, Visual Studio config locations, servers vs mcpServers, keeping secrets out, and start-up checks.
Building Servers with SDKs — Building a complete MCP server: McpServer setup, registering tools, resources and prompts, stdio and HTTP transports, the same server in Python, and testing with handler tests, the Inspector and CI.

Multi-Server Architectures — How hosts connect to many MCP servers at once: one client per server, tool name prefixes, routing calls, cross-server policy, rate limits and audit logs.
Remote MCP and Authorization — How remote MCP servers use OAuth 2.1: 401 challenges, protected resource metadata, auth server discovery, client registration, PKCE, the resource parameter, scopes and audience checks.
Performance, Caching and Extensions — Keeping MCP fast: pagination with cursors, deterministic tool order, ttlMs and cacheScope caching, list-changed invalidation, lazy tool groups and extension negotiation.

Security — Defending MCP setups: over-broad tools, prompt injection, tool poisoning, confused deputy, token passthrough, SSRF, state handle hijacking, local server compromise and unsafe URLs.
Reliability and Operations — Running MCP in production: classifying failures, error frames, safe retries, versioning and deprecation, health checks, audit logs, emergency disable, evaluation, cost and an improvement loop.
MCP Reference — A quick-reference page for MCP 2026-07-28: MCP vs alternatives, roles, methods, error codes, HTTP statuses, headers, result fields, auth and security checklists, deprecations and a glossary.

Host Experience Design — Designing the user experience of MCP hosts: approval policies from tool annotations, approval dialogs, remembered decisions, accessible elicitation forms, progress and cancellation, errors and multi-server display.
Developer Tool Servers — Connecting development workflows through MCP: a design-system server for UI/UX and frontend, a read-only database server for backend work, repository resources, guards inside tools and clear tool descriptions.
Testing and Security Workflows — Testing and security through MCP: test-runner and secret-scanner tools, unit and contract tests for MCP servers, end-to-end checks, and securing dev-tool servers with scopes, guards and least privilege.