by hessius
Automatically creates espresso profiles, analyzes shot data, and provides AI coaching through a web interface, REST API, and MQTT bridge, all packaged in a single Docker container.
Metic provides an all‑in‑one toolkit that automatically creates espresso profiles, analyses shot data and offers AI coaching for the Meticulous Espresso machine. It combines a web UI, REST API, MQTT bridge and optional Home Assistant integration, all delivered as a single Docker container.
docker pull ghcr.io/hessius/meticai:v2.0.6) or run the one‑line installer script.http://<SERVER_IP>:3550 in a browser./api/analyze_and_profile endpoint via curl or integrate through MQTT/Home Assistant.Q: What hardware is required? A: A Meticulous Espresso machine on the same network and any device that can run Docker (Raspberry Pi, PC, Mac, etc.).
Q: Is an internet connection needed? A: Only for contacting the Google Gemini API; the core services run locally.
Q: Can I run Metic without Docker? A: The project is distributed as a Docker image; running it directly would require replicating the internal services manually.
Q: How are updates applied?
A: With Watchtower enabled updates are pulled every 6 hours; otherwise run docker compose pull && docker compose up -d.
Q: Where is my data stored? A: All profile data lives in Docker volumes on the host, keeping it private unless you expose it.
Create, profile and understand your espresso. 1. Take a photo or describe your coffee. Get a perfect espresso profile. Automatically. 2. Understand your profiles, shot graphs by enabling shot comparison, analysis and AI-coaching
Get Started • Features • Web Interface • API
When I got my Meticulous, after a loooong wait, I was overwhelmed with the options — dialing in was no longer just adjusting grind size, the potential was (and is) basically limitless — my knowledge and time not so.
Metic is a growing set of AI tools to help you get the most out of your Meticulous Espresso machine. Among other things it lets you:
Prerequisites: Docker and Docker Compose (Get Docker)
Linux / macOS:
Quick Install:
curl -fsSL https://raw.githubusercontent.com/hessius/Metic/main/scripts/install.sh | bash
Docker:
docker pull ghcr.io/hessius/meticai:v2.0.6
Upgrading from v1.x:
curl -fsSL https://raw.githubusercontent.com/hessius/Metic/main/scripts/migrate-to-unified.sh | bash
macOS / Windows: Docker Desktop is required. See Docker Desktop for Mac or Docker Desktop for Windows.
Note: The macOS .app installer and Windows PowerShell installer were deprecated in v2.4.0. Use the Docker-based installation above for all platforms.
Open http://YOUR_SERVER_IP:3550 in any browser to access the web interface!
The web interface is the easiest and most powerful way to use Metic. Simply open http://YOUR_SERVER_IP:3550 in any browser.
Create a profile in 3 steps:
The web interface shows real-time status, analysis results, and generated profiles with full details. It works perfectly on mobile browsers too!
For automation and integration:
With a photo:
curl -X POST http://YOUR_IP:3550/api/analyze_and_profile \
-F "file=@coffee_bag.jpg"
With text preferences:
curl -X POST http://YOUR_IP:3550/api/analyze_and_profile \
-F "user_prefs=Bold and chocolatey"
With both:
curl -X POST http://YOUR_IP:3550/api/analyze_and_profile \
-F "file=@coffee_bag.jpg" \
-F "user_prefs=Traditional extraction"
For power users who want one-tap brewing from their iPhone, you can create custom shortcuts.
Metic includes a real-time Control Center powered by the meticulous-addon MQTT bridge:
The Control Center appears as a side panel on desktop and a full page on mobile. Enable it in Settings → Control Center → MQTT Bridge.
When the MQTT bridge is enabled, your Meticulous machine is automatically discoverable in Home Assistant.
docker compose -f docker-compose.yml -f docker-compose.homeassistant.yml up -d
→ Full Home Assistant integration guide
cd ~/Metic
docker compose pull
docker compose up -d
With Watchtower enabled, updates happen automatically every 6 hours.
You can enable or disable optional addons at any time (Watchtower, Tailscale, Home Assistant MQTT) without re-running the full installer.
Linux/macOS:
cd ~/Metic
bash scripts/addons.sh
Windows PowerShell:
cd $HOME/Metic
powershell -ExecutionPolicy Bypass -File .\scripts\addons.ps1
Remote one-liner (Linux/macOS):
curl -fsSL https://raw.githubusercontent.com/hessius/Metic/main/scripts/addons.sh | bash
→ Full update guide, migration from v1.x, and troubleshooting
cd ~/Metic
docker compose down -v # -v removes all volumes and data
rm -rf ~/Metic
Note: To verify volume names before removal, use docker volume ls
Access Metic from anywhere using Tailscale:
cd ~/Metic
echo "TAILSCALE_AUTHKEY=your_key_here" >> .env
docker compose -f docker-compose.yml -f docker-compose.tailscale.yml up -d
Important: Both your Metic server and the device you're accessing it from must have Tailscale installed and connected to the same account. See the full Tailscale setup guide for HTTPS setup, troubleshooting, and more.
Metic v2.0 runs as a single unified container with five internal services managed by s6-overlay:
┌──────────────────────────────────────────────────────────────┐
│ Metic Container │
│ ┌────────────────────────────────────────────────────────┐ │
│ │ nginx (:3550) │ │
│ │ Web UI + API Reverse Proxy │ │
│ └────────────────────────────────────────────────────────┘ │
│ │ │
│ ┌───────────────────┼───────────────┐ │
│ ▼ ▼ ▼ │
│ ┌──────────┐ ┌─────────────┐ ┌─────────────┐ │
│ │ Server │ │ MCP Server │ │ Gemini CLI │ │
│ │ (FastAPI) │ │(Meticulous) │ │ (AI) │ │
│ │ :8000 │ │ :8080 │ │ │ │
│ └──────────┘ └─────────────┘ └─────────────┘ │
│ │ │
│ │ MQTT │
│ ▼ │
│ ┌──────────┐ ┌─────────────────┐ │
│ │Mosquitto │◄─│Meticulous Bridge│◄── Machine (Socket.IO) │
│ │ :1883 │ │ (MQTT Bridge) │ │
│ └──────────┘ └─────────────────┘ │
└──────────────────────────────────────────────────────────────┘
Real-time telemetry: The meticulous-addon bridge connects to your machine via Socket.IO and publishes live sensor data (pressure, flow, weight, temperature) to the internal MQTT broker. The FastAPI server subscribes and pushes updates to the web UI via WebSocket.
Optional sidecars:
# Container logs (stdout)
docker logs meticai -f
# Structured logs via API (last 100 entries, filterable by level)
curl http://<SERVER_IP>:3550/api/logs
curl "http://<SERVER_IP>:3550/api/logs?level=ERROR&lines=200"
# Restart a single service
docker exec meticai s6-svc -r /run/service/server
# Check logs
cd ~/Metic && docker compose logs -f
# Check container status
docker compose ps
.env filemeticulous.local# Check relay logs specifically
docker compose logs meticai | grep -i error
cd ~/Metic
docker compose down -v # -v removes volumes
docker compose pull
docker compose up -d
MIT License - see LICENSE for details.
Runs on pyMeticulous, meticulous-mcp, meticulous-addon, and caffeine ☕
Made with ❤️ by @hessius
Please log in to share your review and rating for this MCP.
Explore related MCPs that share similar capabilities and solve comparable challenges
by robotmcp
Enables bidirectional integration of large language models with ROS‑enabled robots, allowing natural language commands and real‑time access to robot state, topics, services and parameters.
by sunsetcoder
Track flights in real time, retrieve arrival and departure times, view airport status, and monitor emergency situations using Flightradar24 data via a Model Context Protocol server.
by EduBase
Enables Claude and other LLMs to interact with the EduBase e‑learning platform via the Model Context Protocol, allowing automated quiz creation, exam scheduling, and result analysis.
by gNucleus
Generate editable CAD parts or assemblies directly from natural‑language prompts by leveraging gNucleus generative AI models through a lightweight MCP server.
by jyjune
Provides control and access to a video surveillance system, allowing retrieval of live and recorded video streams, channel status queries, PTZ camera positioning, and playback dialog management.
by Casys-AI
Provides a Model Context Protocol server that connects AI agents to ERPNext instances, exposing 120 tools across 14 functional categories and seven interactive UI viewers for seamless data exploration and actions.
by litmusautomation
Enables LLMs and other intelligent agents to configure, monitor, and manage Litmus Edge devices through real‑time Model Context Protocol communication.
by NonicaTeam
Enables AI desktop applications to read and select Revit model elements through a set of predefined micro‑tools, integrated directly into the Nonicatab toolbar.
by zaiwork
MCP Server for ZIZAI Recruitment API.