
Gaggiuino MCP Server
A lightweight server that enables AI clients to access and analyze real-time data from Gaggiuino espresso machine controllers through a simple HTTP API.
README
gaggiuino-mcp
Gaggiuino MCP Server This is a lightweight Model Context Protocol (MCP) server built for Gaggiuino, the open-source espresso machine controller for the Gaggia Classic. It is designed to integrate easily AI clients that want to display or analyze data from the Gaggiuino system in real time.
The MCP server exposes a simple HTTP API that allows connected clients to:
-
Retrieve the current machine status
-
Access the latest shot ID
-
Fetch shot data for a specified id
Features
📊 Real-time access to shot telemetry
🌐 Designed for local network access
How to use
Using Claude Desktop
{
"mcpServers": {
"gaggiuino": {
"command": "uv",
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/PARENT/FOLDER/gaggiuino-mcp",
"run",
"gaggiuino.py"
]
}
}
}
Available Toolsets
Toolset | Description |
---|---|
getLatestShotId |
Get latest espresso shot id |
getShotData |
Get espresso shot data for an id. Args: id: Shot id |
getStatus |
Get espresso machine status |
Example
User:
analyze the latest espresso shot data
Claude:
I'll retrieve and analyze the latest espresso shot data for you. Let me first check the status of your espresso machine and then get the latest shot information.
getStatus
Now I'll get the ID of the latest espresso shot:
getLatestShotId
Let me retrieve the data for shot #188:
getShotData
Based on the data retrieved, I'll now analyze your latest espresso shot (ID #188). Here's my analysis:
Machine Status and Shot Overview Your machine is currently idle at 57.2°C with -0.1 bar pressure. The shot analyzed was taken on April 19, 2025 (based on the timestamp), with a total duration of 26.5 seconds (265 datapoints at 0.1s intervals).
Profile Information You used the "Leva 9 LR v0.5" profile, which is a multi-phase profile with declining pressure targeting 40g of output. The profile has
- A flow-control preinfusion at 7 ml/s
- Step-down to 3.5 ml/s flow
- Pre-extraction at 1.5 ml/s flow with 3 bar pressure restriction
- Pressure ramp to 9 bar over 2 seconds
- A series of gradually declining pressure steps (8.8→6.0 bar)
Shot Analysis Preinfusion and Extraction Phases
- Preinfusion (0-5s): Started with a high flow rate (6-7 ml/s) with minimal pressure (0.3-0.6 bar), allowing the puck to saturate.
- First Pressure Rise (5-10s): Pressure gradually built to ~2.5 bar while flow decreased to ~1.5 ml/s.
- Pressure Profile Phase (10-15s): Pressure held around 3 bar with flow reduced to ~0.8 ml/s.
- Pressure Ramp (15-20s): Pressure increased from 3 to 8.9 bar over ~5 seconds following the programmed profile.
- Declining Pressure Phase (20-26.5s): Pressure gradually declined from ~8.5 to 6.4 bar following the profile steps.
Key Measurements
- Final Yield: 38g (based on final shot weight)
- Brew Ratio: Unable to determine (coffee dose not provided)
- Temperature Stability: Excellent - maintained at 92.8-94.1°C throughout extraction
- First Drops: Appeared around 11-12 seconds (~75% into preinfusion)
- Peak Flow Rate: 7.2 ml/s (at the beginning)
- Peak Pressure: 8.9 bar (at ~20 seconds)
Extraction Dynamics
- Flow Rate: Started high (7 ml/s), stepped down to 3.5 ml/s then 1.5 ml/s during preinfusion as programmed, then stabilized at ~2.8 ml/s during extraction.
- Water Delivery: Total water pumped was 87.7 ml, with 38g in the cup, suggesting significant water retention in the puck.
- Pressure Profile: The pressure curve shows excellent progression from preinfusion through extraction, with a smooth transition to declining pressure.
Performance Assessment This appears to be a technically well-executed shot with good adherence to the programmed profile:
- Temperature Control: Excellent stability around 93-94°C
- Pressure Curve: Follows the programmed profile with smooth transitions
- Extraction Flow: Consistent during main extraction phase
- Weight Output: Achieved 38g (close to the 40g target)
Would you like me to provide more specific recommendations about any aspect of this shot, or is there a particular parameter you'd like me to analyze in more detail?
推荐服务器

Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。