# Wine Quality Score Analysis AI Agent Connect

> Statistical analysis of sensory evaluation scores for wine quality.

## Overview
- **Category:** statistics
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_DPoropZD7g6DLt6dfJv010NTp3tvSczFNRGreRGd/ai-agent-connect
- **Tags:** wine, sensory-evaluation, anova, quality-control, statistics

## Description

This MCP server provides statistical tools to analyze sensory evaluation data from wine tasting panels. It helps researchers and quality control teams understand wine quality through mean scores, assess panel reliability via agreement metrics, and verify the panel's ability to distinguish between samples. Use `get_wine_summary` to see average scores, `evaluate_panel_consistency` to check panelist agreement, `detect_discriminant_capability` to verify sample distinction, and `identify_panelist_outliers` to find biased scorers.

## Tools

### identify_panelist_outliers
Finds panelists whose scoring behavior deviates significantly from the group norm

### detect_discriminant_capability
Checks if the panel is actually capable of telling the wines apart

### evaluate_panel_consistency
Determines how well the panelists agree with one another

### get_wine_summary
Provides a high-level overview of the mean quality scores for all wines in the dataset

## Prompt Examples

**Prompt:** 
```
Show me the average quality scores for all the wines in this dataset.
```

**Response:** 
```
The average scores are: Cabernet Sauvignon: 8.2, Merlot: 7.5, and Pinot Noir: 7.9.
```

**Prompt:** 
```
Is the tasting panel capable of distinguishing between these different wines?
```

**Response:** 
```
Yes, the panel has high discriminant power, showing significant differences between the wine varieties.
```

**Prompt:** 
```
Are there any panelists providing biased scores?
```

**Response:** 
```
Panelist ID P-402 has been identified as an outlier due to a high deviation score.
```

## Frequently Asked Questions

**What kind of data does this server process?**
It processes sensory evaluation scores, including wine IDs, panelist IDs, and numerical scores assigned during tastings.

**How can I identify if my tasting panel is reliable?**
You can use the `evaluate_panel_consistency` tool to calculate agreement coefficients and determine if the panel's scoring is consistent.

**Can I find panelists who are scoring inconsistently?**
Yes, the `identify_panelist_outliers` tool detects panelists whose scoring behavior deviates significantly from the group norm.