Skip to main content
Glama

Gaggiuino MCP Server

加吉诺-MCP

Gaggiuino MCP 服务器:这是为Gaggiuino构建的轻量级模型上下文协议 (MCP) 服务器。Gaggiuino 是 Gaggia Classic 的开源意式浓缩咖啡机控制器。它旨在轻松集成需要实时显示或分析 Gaggiuino 系统数据的 AI 客户端。

这是我写的关于这个项目的一篇文章https://medium.com/@a.klement.w/dialing-in-espresso-using-mcp-server-0207819fe93a

允许连接的客户端:

  • 检索当前机器状态
  • 获取最新镜头 ID
  • 获取指定 ID 的镜头数据

特征

📊 实时访问镜头遥测

🌐 专为本地网络访问而设计

如何使用

使用 Claude Desktop

{ "mcpServers": { "gaggiuino": { "command": "uv", "args": [ "--directory", "/ABSOLUTE/PATH/TO/PARENT/FOLDER/gaggiuino-mcp", "run", "gaggiuino.py" ] } } }

可用工具集

工具集描述
getLatestShotId获取最新的浓缩咖啡冲泡 ID
getShotData获取指定 ID 的浓缩咖啡冲泡数据。参数:id:冲泡 ID
getStatus获取浓缩咖啡机状态

例子

用户:

分析最新的浓缩咖啡数据

克劳德:

我将为您检索并分析最新的浓缩咖啡冲泡数据。首先,我会检查您的浓缩咖啡机的状态,然后获取最新的冲泡信息。getStatus 现在,我将获取最新一杯浓缩咖啡的 ID: getStatus让我检索第 188 getLatestShotId咖啡的数据: getShotData根据检索到的数据,我现在将分析您最新的一杯浓缩咖啡(ID 为 188)。以下是我的分析:

机器状态和镜头概览:您的机器当前处于闲置状态,温度为 57.2°C,压力为 -0.1 bar。分析的镜头拍摄于 2025 年 4 月 19 日(基于时间戳),总时长为 26.5 秒(265 个数据点,间隔为 0.1 秒)。

配置文件信息您使用了“Leva 9 LR v0.5”配置文件,这是一个多相配置文件,压力逐渐下降,目标输出量为 40g。该配置文件具有

  1. 7 ml/s 的流量控制预注入
  2. 流量降至 3.5 ml/s
  3. 以 1.5 ml/s 的流速进行预萃取,压力限制为 3 bar
  4. 压力在 2 秒内上升至 9 bar
  5. 一系列逐渐下降的压力步骤(8.8→6.0 bar)

预浸和萃取阶段的分析

  • 预浸泡(0-5 秒):以高流速(6-7 毫升/秒)和最小压力(0.3-0.6 巴)开始,使咖啡饼饱和。
  • 第一次压力上升(5-10 秒):压力逐渐增至约 2.5 巴,而流量下降至约 1.5 毫升/秒。
  • 压力曲线阶段(10-15秒):压力保持在3巴左右,流量减少至约0.8毫升/秒。
  • 压力斜坡(15-20 秒):按照编程的曲线,压力在约 5 秒内从 3 巴增加到 8.9 巴。
  • 压力下降阶段(20-26.5秒):压力按照剖面步骤逐渐从~8.5巴下降到6.4巴。

关键测量

  • 最终产量:38克(基于最终射击重量)
  • 冲泡比例:无法确定(未提供咖啡剂量)
  • 温度稳定性:极佳 - 整个提取过程保持在 92.8-94.1°C
  • 第一滴:出现约 11-12 秒(预浸泡约 75%)
  • 峰值流速:7.2 ml/s(开始时)
  • 峰值压力:8.9 巴(约 20 秒)

萃取动力学

  1. 流速:开始时较高(7 ml/s),按照程序在预浸泡期间降至 3.5 ml/s,然后降至 1.5 ml/s,然后在提取期间稳定在 ~2.8 ml/s。
  2. 供水量:泵送的总水量为 87.7 毫升,其中杯中水量为 38 克,表明冰球中保留了大量水分。
  3. 压力曲线:压力曲线显示出从预浸泡到萃取的良好进展,并平稳过渡到压力下降。

性能评估这似乎是一次技术上执行良好的射击,并且很好地遵循了编程的配置文件:

  • 温度控制:93-94°C 左右稳定性极佳
  • 压力曲线:遵循编程的曲线,过渡平稳
  • 提取流程:在主要提取阶段保持一致
  • 重量输出:达到38克(接近40克的目标)

您希望我针对此镜头的任何方面提供更具体的建议吗?或者您希望我更详细地分析某个特定参数吗?

Install Server
A
security – no known vulnerabilities
A
license - permissive license
A
quality - confirmed to work

local-only server

The server can only run on the client's local machine because it depends on local resources.

轻量级服务器,使 AI 客户端能够通过简单的 HTTP API 访问和分析来自 Gaggiuino 浓缩咖啡机控制器的实时数据。

  1. 允许连接的客户端:
    1. 特征
      1. 如何使用
        1. 使用 Claude Desktop
        2. 可用工具集
        3. 例子

      Related MCP Servers

      • A
        security
        A
        license
        A
        quality
        This server enables AI systems to integrate with Tavily's search and data extraction tools, providing real-time web information access and domain-specific searches.
        Last updated -
        2
        9,397
        468
        JavaScript
        MIT License
        • Apple
        • Linux
      • A
        security
        A
        license
        A
        quality
        An unofficial server that allows AI assistants to access Fathom Analytics data, enabling users to retrieve account information, site statistics, events, aggregated reports, and real-time visitor tracking.
        Last updated -
        5
        13
        1
        TypeScript
        MIT License
      • -
        security
        F
        license
        -
        quality
        A server that enables AI systems to browse, retrieve content from, and interact with web pages through the Model Context Protocol.
        Last updated -
      • -
        security
        A
        license
        -
        quality
        A server that enables AI assistants like Claude to perform web searches using the Exa AI Search API, providing real-time web information in a safe and controlled way.
        Last updated -
        1,964
        MIT License
        • Apple

      View all related MCP servers

      MCP directory API

      We provide all the information about MCP servers via our MCP API.

      curl -X GET 'https://glama.ai/api/mcp/v1/servers/AndrewKlement/gaggiuino-mcp'

      If you have feedback or need assistance with the MCP directory API, please join our Discord server