Blog / Agent engineering
The Scalably blog

Agent engineering

Working code, agent workflows, tool boundaries and local model serving.

23 articles · 13–23

Claude·Guide

Claude Code MCP: how to add an MCP server

The claude mcp add command, the three scopes and which file each writes to, the .mcp.json your team commits, and how project servers get approved before they run.

Read article →
Claude·Guide

Claude Code settings.json: the configuration guide

The files that merge into one config, the permissions rules that decide what runs, env, MCP servers, and the multi-tenant default-deny setup we run across client accounts.

Read article →
Claude·Guide

The Claude Agent SDK: build your own agent

The same engine that powers Claude Code, driven from your own program. What the SDK gives you in production, how tools and MCP servers plug in, and when to reach for it.

Read article →
Claude·Guide

Claude Code hooks: a practical guide

Hooks are shell commands that run at lifecycle events. The settings.json schema, exit-code behavior, a real guard example, and the gotchas worth knowing.

Read article →
Claude·Guide

Claude Code subagents: how and when to use them

Subagents get their own context window and tool scope. How to define one, why the separate context matters, and the honest case for when not to bother.

Read article →
Claude·Comparison

Claude Code vs Cursor: an honest 2026 comparison guide

Two strong tools that have grown into each other's lanes. Where each genuinely wins, the real pricing, and which one to reach for when.

Read article →
MCP·Guide

How to build an MCP server in Python (from one running in production)

A working guide built around a real, open-source read-only Shopify server. Tools, annotations, the safety boundary tutorials skip, and five mistakes worth avoiding.

Read article →
MCP·Guide

MCP Inspector: how to debug and test your MCP server

The official MCP debugging tool, end to end. How to run it, what each panel does, and the silent failures it catches before a client ever sees them.

Read article →
MCP·Guide

How to build an MCP server in TypeScript

A minimal MCP server with the official TypeScript SDK, using the current stable API and the zod schema shape that trips most people up.

Read article →
MCP·Explainer

MCP vs function calling: what's the difference?

They're not competitors. Function calling is the model deciding when to use a tool; MCP is the standard for how tools are delivered. How they fit together.

Read article →
MCP·Explainer

What is an MCP server? A clear explainer for developers

The Model Context Protocol without the jargon: what an MCP server is, the client-server model, tools vs resources vs prompts, and why it exists.

Read article →