MCP Server in an Evening: Letting AI Manage Our Office Parking

MCP Server in an Evening: Letting AI Manage Our Office Parking

What if you could just say “reserve parking for tomorrow” to your AI tool and have it actually happen? We built a MCP server in one Python file (~650 lines, zero frameworks) that does exactly that. Setup time: under 5 minutes. Dependencies: two pip packages. And now any MCP-compatible AI tool — OpenCode, Claude Desktop, whatever — can check, create, and cancel our office parking reservations through natural language.

E-Ink Dashboard: Repurposing an Old Kindle Paperwhite with RPi5

Don’t throw away that old Kindle gathering dust in your drawer. With its high-contrast E-ink display and incredible battery life, it is the perfect candidate for a low-power home dashboard. In this post, I’ll show you how I turned a Kindle Paperwhite 2 into a 2-hour refreshing dashboard powered by a Raspberry Pi 5.

ESP32 BLE Voltage Monitor: End-to-End in 6 Hours

A complete Bluetooth voltage monitoring system — ESP32 reads voltage via ADS1115 ADC, broadcasts over BLE GATT, and an Android app displays live readings in real time. Built end-to-end in ~6 hours across 3 platforms.

The goal: measure voltage wirelessly and display it on your phone. Simple enough, but it means touching embedded C++, Bluetooth protocols, and Android Kotlin — all in one session. Here’s how the 6 hours broke down and what we learned along the way.

Building a Voice AI Agent: Twilio + OpenAI TTS + OpenClaw in One Night

What happens when you try to build a fully functional voice AI agent in a single evening? You get 4 hours of debugging, 7 failed calls, 3 root causes, and one very satisfying “it works” moment at 1 AM. Total API cost: $0.03.

The goal: call a phone number, have an AI agent answer, listen to you, understand you, and respond in natural language — in Slovak and English. The stack: Twilio for telephony, OpenAI for text-to-speech and speech-to-text, and OpenClaw as the AI agent platform.

Secure Remote Access: Connecting to Home Assistant on RPi5 via Tailscale

Secure Remote Access: Connecting to Home Assistant on RPi5 via Tailscale

In my previous post, I shared how to install Home Assistant OS (HAOS) inside a KVM on a Raspberry Pi 5. While having a powerful local server is great, it brings up a major question: How do you access it securely from the outside?

For this setup, I wanted to achieve two specific goals:

  1. Enable a free and secure VPN for my mobile device (so I can surf safely on public Wi-Fi).
  2. Gain seamless remote access to Home Assistant without exposing any ports to the internet.

The answer to both is Tailscale.

Building a Hybrid Web Station: RPi5, Docker, and Cloudflare Tunnels

Building a Hybrid Web Station: RPi5, Docker, and Cloudflare Tunnels

After getting my hands on a Raspberry Pi 5, I wanted to move beyond a simple local server. My goal was to host a multi-service web station (a Go/SQLite analytics app and various static projects) while keeping my main blog on GitLab Pages.

Here is how I navigated the world of reverse proxies, containerization, and the dreaded “Protocol Errors.”

Building PACMAN with AI

Project Overview

I created a fully-playable PACMAN game for Windows 11, built with Go + Wails and a vanilla JavaScript frontend, using AI assistance throughout the process.

Home Assistant Entity & Device Naming Best Practice

Proper naming conventions in Home Assistant transform a chaotic smart home into an organized, maintainable system. Without consistent naming, you’ll struggle to find devices, create automations, and troubleshoot issues as your setup grows. Good naming conventions make your smart home scalable and intuitive for everyone in your household.

This guide provides a structured approach to naming that grows with your system, inspired by the Home Assistant Naming Convention repository maintained by the community.