Skip to main content
Glama
enesjakozh
AndrewKlement

Gaggiuino MCP Server

by AndrewKlement
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

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.

This is an article I wrote about this project https://medium.com/@a.klement.w/dialing-in-espresso-using-mcp-server-0207819fe93a

Allows connected clients to:

  • Retrieve the current machine status

  • Access the latest shot ID

  • Fetch shot data for a specified id

Related MCP server: meticulous-mcp

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"
          ]
      }
  }
}

Installing via Smithery

To install Gaggiuino Espresso Machine Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @AndrewKlement/gaggiuino-mcp --client claude

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

  1. A flow-control preinfusion at 7 ml/s

  2. Step-down to 3.5 ml/s flow

  3. Pre-extraction at 1.5 ml/s flow with 3 bar pressure restriction

  4. Pressure ramp to 9 bar over 2 seconds

  5. 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

  1. 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.

  2. Water Delivery: Total water pumped was 87.7 ml, with 38g in the cup, suggesting significant water retention in the puck.

  3. 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?

Available Tools

3 tools
getLatestShotIdB

Get latest espresso shot id.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states what the tool does but doesn't add context on traits like whether it's read-only, requires authentication, has rate limits, or what the return format might be. This leaves significant gaps for an agent to understand how to invoke it correctly.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence with zero waste, front-loading the essential information. It's appropriately sized for a simple tool with no parameters, making it highly efficient and easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of annotations and output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., the format of the shot ID or any error cases), which is crucial for an agent to use it effectively. For a tool with no structured output documentation, more context is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters, and schema description coverage is 100%, so there's no need for parameter details in the description. The baseline for this scenario is 4, as the description doesn't need to compensate for any parameter gaps, and it efficiently avoids unnecessary information.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Get') and resource ('latest espresso shot id'), making the purpose specific and understandable. However, it doesn't differentiate from sibling tools like 'getShotData' or 'getStatus', which might retrieve related information, so it doesn't reach the highest score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives like 'getShotData' or 'getStatus'. The description implies it's for retrieving the latest shot ID, but there's no explicit context, exclusions, or comparisons to help an agent choose appropriately.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

getShotDataC

Get espresso shot data for an id.

Args:
    id: Shot id
ParametersJSON Schema
NameRequiredDescriptionDefault
idYes

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It mentions 'Get' which implies a read operation, but doesn't disclose behavioral traits such as error handling, data format, permissions needed, or rate limits. This is a significant gap for a tool with no annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is brief and front-loaded with the main purpose, followed by a parameter explanation. It avoids unnecessary words, but the structure could be improved by integrating the parameter info more seamlessly or adding context in a single coherent sentence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations, no output schema, and low schema coverage, the description is incomplete. It lacks details on return values, error cases, or how it interacts with sibling tools. For a tool with one parameter but undefined behavior, this is inadequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 0%, but the description adds meaning by specifying that 'id' is a 'Shot id'. This clarifies the parameter's purpose beyond the schema's basic type. However, it doesn't detail format, constraints, or examples, so it only partially compensates for the low coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Get espresso shot data') and the resource ('for an id'), making the purpose understandable. However, it doesn't differentiate from sibling tools like 'getLatestShotId' or 'getStatus', which might retrieve related data, so it doesn't reach the highest score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives like 'getLatestShotId' or 'getStatus'. The description only states what it does, without context on prerequisites, scenarios, or exclusions, leaving the agent to infer usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

getStatusB

Get espresso machine status.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action ('Get') but doesn't clarify what 'status' entails (e.g., operational state, error codes, maintenance info), response format, or any side effects like rate limits or authentication needs. This leaves significant gaps for a tool with no structured safety hints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise—a single sentence with no wasted words. It front-loads the core purpose ('Get espresso machine status') effectively, making it easy to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of annotations and output schema, the description is incomplete. It doesn't explain what the 'status' return value includes (e.g., JSON structure, possible states), which is critical for an agent to use the tool correctly. For a tool with no structured output, more context is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description doesn't add parameter details, which is appropriate here, and it implies no inputs are required, aligning with the schema. A baseline of 4 is given since no parameters exist.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Get') and resource ('espresso machine status'), making the purpose specific and understandable. It doesn't explicitly distinguish from sibling tools like 'getLatestShotId' or 'getShotData', but the resource focus is clear enough for basic differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'getLatestShotId' or 'getShotData'. It lacks context about prerequisites, timing, or exclusions, leaving the agent to infer usage based on tool names alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 3 tool updatesv1.0.0
    • First observedgetLatestShotId
    • First observedgetShotData
    • First observedgetStatus
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.1/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: getLatestShotId retrieves the most recent shot identifier, getShotData fetches detailed data for a specific shot ID, and getStatus provides machine status information. There is no overlap or ambiguity between these functions.

Naming Consistency5/5

All three tools follow a consistent verb_noun pattern with camelCase naming (getLatestShotId, getShotData, getStatus). The naming is predictable and uniform throughout the set.

Tool Count2/5

With only 3 tools, the set feels thin for an espresso machine control server. There are obvious gaps in functionality, such as tools to start/stop shots, adjust settings, or manage profiles, which limits the server's utility for comprehensive machine interaction.

Completeness2/5

The tool surface is severely incomplete for an espresso machine domain. It only provides read-only operations (getLatestShotId, getShotData, getStatus) with no ability to control the machine (e.g., start_shot, set_temperature), update configurations, or manage other critical aspects like brewing profiles or maintenance.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers