Skip to content

A developer's guide to the Model Context Protocol — the open standard connecting AI apps to tools and data. Covers architecture, wire protocol, building servers (TypeScript & Python) and clients, all 10 SDKs, configuration, security, testing, production patterns, and the ecosystem.

License

Notifications You must be signed in to change notification settings

cloudstreet-dev/MCP-Model-Context-Protocol

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

The Model Context Protocol Book

A comprehensive guide for developers who want to understand, build, and deploy MCP servers and clients.

MCP is the open standard that connects AI applications to the tools and data they need. This book takes you from "what is MCP?" to "I'm running MCP servers in production."


Who This Book Is For

  • Backend developers building tools and APIs that AI agents should be able to use
  • AI/ML engineers creating applications that need to interact with external systems
  • Full-stack developers integrating MCP into existing products
  • Technical leads evaluating MCP for their organization
  • Anyone curious about how the sausage gets made when Claude checks the weather

No prior MCP knowledge required. Familiarity with JSON, APIs, and at least one programming language (TypeScript or Python preferred) will help.


Table of Contents

Part I: Understanding MCP

Chapter Title What You'll Learn
01 The Problem MCP Solves Why MCP exists, the N-times-M integration nightmare, and MCP's "USB-C moment"
02 Architecture Hosts, clients, servers, trust boundaries, capability negotiation, and the three-layer cake
03 The Wire Protocol JSON-RPC 2.0, message types, method catalog, initialization handshake, error codes, pagination, cancellation

Part II: The Three Primitives

Chapter Title What You'll Learn
04 Tools Tool definitions, schemas, annotations, discovery, invocation, result types, error handling, best practices
05 Resources URIs, resource templates, subscriptions, binary data, audience annotations, resources vs. tools
06 Prompts Prompt templates, arguments, multi-message prompts, embedded resources, practical patterns

Part III: Transport and Communication

Chapter Title What You'll Learn
07 Transports stdio, Streamable HTTP, legacy SSE, the proxy pattern, transport security, debugging transports

Part IV: Building Things

Chapter Title What You'll Learn
08 Building Servers in TypeScript McpServer API, Zod schemas, weather server example, HTTP transport, publishing to npm
09 Building Servers in Python FastMCP, decorators, type hints, SQLite explorer example, uvx, publishing to PyPI
10 Building Clients TypeScript and Python clients, building a host, managing multiple servers, the full agentic loop

Part V: The Ecosystem

Chapter Title What You'll Learn
11 The SDK Landscape All 10 official SDKs (TypeScript, Python, Go, C#, Java, Kotlin, Swift, Rust, Ruby, PHP), choosing an SDK
12 Configuration Setting up MCP in Claude Desktop, Claude Code, VS Code, Cursor, and Windsurf

Part VI: Security and Advanced Topics

Chapter Title What You'll Learn
13 Authentication and Security OAuth 2.1, trust boundaries, threat modeling, security best practices for servers and hosts
14 Advanced Features Sampling, elicitation, roots, completion, logging, progress reporting

Part VII: Production and Beyond

Chapter Title What You'll Learn
15 Testing and Debugging MCP Inspector, manual testing, common problems, testing strategies, debugging tips
16 Production Patterns Deployment models, Docker/K8s, serverless, gateways, multi-tenancy, monitoring, scaling
17 The Ecosystem Official servers, community servers, registries, discovery, evaluating and building for the ecosystem
18 The Future of MCP Stateless protocol, server cards, transport evolution, agent convergence, the road ahead

How to Read This Book

Linear path: Read chapters 1-18 in order for the complete journey from concepts to production.

Quick start: Read chapters 1-2 for the concepts, then jump to chapter 8 (TypeScript) or 9 (Python) to start building.

Reference: Each chapter is self-contained. Jump to whatever topic you need.

Architecture deep-dive: Chapters 2, 3, 7, and 13 cover the protocol in detail.

Practical guide: Chapters 8, 9, 10, 12, and 15 are hands-on with code and configuration.


About the Protocol

The Model Context Protocol was created by Anthropic and released as an open standard in November 2024. The specification is maintained at modelcontextprotocol.io and the source code is at github.com/modelcontextprotocol.

The current specification revision at time of writing is 2025-11-25.


Contributing

Found an error? Have a suggestion? Open an issue or pull request.


License

This book is available under the license specified in the LICENSE file.

About

A developer's guide to the Model Context Protocol — the open standard connecting AI apps to tools and data. Covers architecture, wire protocol, building servers (TypeScript & Python) and clients, all 10 SDKs, configuration, security, testing, production patterns, and the ecosystem.

Topics

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Contributors 2

  •  
  •