Build Your First MCP Server: Step-by-Step Tutorial

In this hands-on tutorial, you will build an MCP server from scratch that extends Claude capabilities with custom tools and resources.

Prerequisites

Node.js 18+
npm
Claude Desktop
Basic TypeScript knowledge

Project Setup

mkdir mcp-project-manager
cd mcp-project-manager
npm init -y
npm install @modelcontextprotocol/sdk
npm install --save-dev typescript @types/node
npx tsc --init

Update package.json with type module and build scripts. Then create src/index.ts with your server implementation.

Creating the Server

Import the MCP SDK and create a server instance with tools capability. Implement ListToolsRequestSchema to expose your tools, and CallToolRequestSchema to handle tool invocations.

Testing with Claude Desktop

Add your server to claude_desktop_config.json and restart Claude Desktop.

Next Steps

In Part 4, we cover security best practices for production deployments.

How This Article Was Made

This article is a live example of the AI-enabled content workflow we build for clients.

Stage	Who	What
Research	Claude Opus 4.5	Analyzed current industry data, studies, and expert sources
Curation	Tom Hundley	Directed focus, validated relevance, ensured strategic alignment
Drafting	Claude Opus 4.5	Synthesized research into structured narrative
Fact-Check	Human + AI	All statistics linked to original sources below
Editorial	Tom Hundley	Final review for accuracy, tone, and value

The result: Research-backed content in a fraction of the time, with full transparency and human accountability.

Why We Work This Way

Were an AI enablement company. It would be strange if we didnt use AI to create content. But more importantly, we believe the future of professional content isnt AI vs. Human—its AI amplifying human expertise.

Every article we publish demonstrates the same workflow we help clients implement: AI handles the heavy lifting of research and drafting, humans provide direction, judgment, and accountability.

Want to build this capability for your team? Lets talk about AI enablement →