MCP in Production, Part 6: Java vs Go, Measured
TL;DR Same hexagon, same tools, same k6 scenario, two runtimes. Both servers handled the agent burst with zero failures and stayed far below the SLO. Go answered with a ~5× lower p95 (2.6 ms vs 13.8
Latest articles
The Same MCP Server in Go: Hexagonal Architecture with the Official Go SDK
TL;DR Same server, same tools, same scopes, same metrics, different language. I rebuilt the hexagonal MCP server from parts 1–4 in Go, with the official MCP Go SDK, to see what changes and what doesn
Observing AI Agents: Grafana Dashboards and k6 Load Tests for MCP
TL;DR Agents don't behave like humans: they call tools in bursts, in loops and in chains. If you can't see latency, errors and auth failures per tool, you can't run an MCP server in production. ⭐ Co
Swapping Adapters: PostgreSQL Without Touching the Core
TL;DR Hexagonal architecture is a promise: you can replace an adapter without touching the core. In this part I keep that promise by swapping the in-memory repository for PostgreSQL, and I prove it w
Securing MCP Tools with OAuth 2.1: Scopes per Tool in Spring AI
TL;DR An AI agent calling your tools is a client like any other, and it needs a token. With Spring Security 7 your MCP server becomes an OAuth 2.1 Resource Server, and each tool declares the scope it
Building a Production-Ready MCP Server with Spring AI
TL;DR An MCP server is just another driving adapter. If your service follows hexagonal architecture, exposing it to AI agents is a new entry door, not a rewrite. ⭐ Full code: github.com/cbuelvasc/or