#mcp

On Tuesday you told the assistant that the migration script must never touch the staging database. It...

📖 TL;DR An MCP agent is four things: a model, two or three MCP servers, a system prompt, and a...

Quick bit of context first, since this is a small project and there's a decent chance you're reading...

The task was small. An agent in Claude Code that, given "two-bedroom rentals in Denver under $2,500",...

Most "we migrated a website" posts skip the part where something breaks. This one doesn't, because...

Meta description: Configure TickDB MCP to give Claude access to live market data with millisecond...

MCP security is the practice of treating every MCP (Model Context Protocol) server as untrusted code:...

AI agents tend to write functional but unprincipled Python code filled with technical debt. Discover how the Python Excellence Prover MCP tool uses structured reasoning across five pillars—type safety, idiomatic patterns, error handling, architecture, and async performance—to enforce senior-level coding standards.

Context engineering for AI agents: why building an agent is now trivial, why agents still fail in production, and how to fix the context layer in 2026

Introduction The open-source AI safety ecosystem includes mature tools for...

An MCP server breaks at three seams: the SDK class name, the upstream request shape, and each CLI's...

Disclosure: I'm part of BackBond, which maintains Agent Scan. This tutorial was drafted by an AI...