🚀 We're in early access! Submit feedback — your input shapes the platform.
← All Topics

Model Context Protocol

📖 10 lessons🎯 6 missions🔧 1 workshop🚀 1 project⏱️ ~15 hours
Filter by rank:

📖Lessons

1
beginner📖 14 minlesson

Introduction to Model Context Protocol (MCP)

Understand MCP - the universal standard for connecting AI to external systems

mcpprotocolintroductionarchitecture
2
beginner📖 16 minlesson

MCP Architecture & Protocol

Deep dive into MCP's client-server architecture and JSON-RPC 2.0 protocol

mcparchitecturejsonrpcprotocol
🔒
intermediate📖 18 minlessonPRO

Building MCP Servers

Build production-ready MCP servers with Python and TypeScript

mcpserverspythontypescripttools
🔒
intermediate📖 16 minlessonPRO

Building MCP Clients

Create MCP clients to connect to servers and orchestrate tools

mcpclientsintegrationorchestration
🔒
intermediate📖 17 minlessonPRO

MCP Tools & Resources

Master tool definition, resource providers, and dynamic capabilities

mcptoolsresourcespromptsschemas
🔒
beginner📖 15 minlessonPRO

Pre-built MCP Servers

Use official and community MCP servers for instant integration

mcpserversintegrationgoogle-drivegithubslack
🔒
advanced📖 16 minlessonPRO

Security & Authentication

Secure MCP servers and protect against vulnerabilities

mcpsecurityauthenticationoauthvulnerabilities
🔒
beginner📖 15 minlessonPRO

MCP with Claude Desktop

Configure and optimize MCP servers in Claude Desktop

mcpclaude-desktopconfigurationtool-search
🔒
advanced📖 18 minlessonPRO

Production MCP Deployment

Deploy MCP servers to cloud infrastructure at scale

mcpdeploymentkubernetesdockerproduction
🔒
intermediate📖 17 minlessonPRO

MCP with OpenAI & Google

Use MCP with OpenAI Agents SDK and Google ADK

mcpopenaigooglemulti-platform

🎯Missions

🔒
intermediate🎯 30–45 minmissionRank 07PRO

M-049Add Authentication to an MCP Server

Nebula Corp's MCP server is wide open — any client can call any tool. Build an authentication middleware that validates API keys, checks permissions per tool, and rejects unauthorized requests. The middleware should sit between incoming requests and the handler, enforcing access control before any tool executes.

🔒
intermediate🎯 30–45 minmissionRank 06PRO

M-050Build an MCP Prompt Template Server

Nebula Corp wants to share reusable prompt templates across all their AI assistants via MCP. Build a prompt template server that registers templates with argument placeholders, lists available prompts, and renders them with provided arguments. The server should support variable interpolation like {{customerName}} and validate that all required arguments are provided.

🔒
advanced🎯 40–55 minmissionRank 08PRO

M-052Build an MCP Tool Composition Pipeline

Nebula Corp's AI assistants need to chain multiple MCP tools together to answer complex queries. Build a tool composition engine that takes a plan (a sequence of tool calls where later steps can reference earlier results), executes them in order, and returns the combined result. Handle errors gracefully — if one step fails, the pipeline should report which step failed and why.

4
beginner🎯 15–30 minmissionRank 05

M-047Build Your First MCP Message Handler

Nebula Corp is adopting the Model Context Protocol to let AI assistants access internal tools. Before building a full server, they need a message handler that can parse MCP JSON-RPC requests, validate them, and route to the correct handler. Build the protocol layer that processes initialize, tools/list, and tools/call messages.

🔒
beginner🎯 25–40 minmissionRank 05PRO

M-048Build Your First MCP Server

Nebula Corp wants to expose their internal customer database to AI assistants via the Model Context Protocol. The skeleton MCP server is set up with the transport layer, but the tool registration and request handling are missing. Wire up the server so it registers a 'lookup_customer' tool, handles incoming tool calls, and returns properly formatted MCP responses.

🔒
intermediate🎯 30–45 minmissionRank 06PRO

M-051Implement MCP Resource Endpoints

Nebula Corp's MCP server can handle tool calls, but it doesn't expose any resources yet. AI assistants need to browse available data before calling tools. Implement the resource provider so the server can list available resources (customer profiles, order history) and return their contents when requested via resource URIs like 'customer://C001/profile'.