# Referee Discipline Rate Calculator AI Agent Connect

> Referee Discipline Rate Calculator MCP gives your AI agent the ability to audit football officiating. It calculates disciplinary rates, measures how often fouls lead to cards, and detects home or away bias in refereeing patterns. Use it to pull high-level summaries or raw disciplinary counts directly into your analysis workflow.

## Overview
- **Category:** analytics
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_G3l4W1Vy1dxlBedBsQLaZk0SvwGPEhuweVRM5rzh/ai-agent-connect
- **Tags:** referee, discipline, football, statistics, match-analysis

## Description

You can use this MCP to dig into the data behind football officiating. Instead of manually checking match reports, you can ask your AI client to pull specific disciplinary metrics for any referee. It handles the heavy lifting of calculating how frequently a ref penalizes fouls with cards or whether they show a statistical tendency to favor the home team. You can pull high-level summaries to get a quick sense of a referee's impact on a match, or you can request raw, non-normalized totals if you need to perform a deep audit of specific disciplinary categories. It's built for anyone who needs to turn raw officiating data into actionable insights about match fairness and disciplinary trends.

## Tools

### get_referee_exact_counts
This tool provides raw, non-normalized totals for all disciplinary categories. Use it when you need to audit specific counts without any statistical normalization.

### get_referee_impartiality_metrics
This tool determines if a referee shows a tendency to favor or penalize home or away teams. It's your primary way to check for officiating bias.

### get_referee_discipline_summary
This tool provides a high-level overview of a referee's disciplinary impact per match. It's best for getting a quick snapshot of a ref's style.

### get_referee_foul_punishment_rate
This tool measures how frequently a referee penalizes fouls with cards. Use it to see how strict an official is regarding specific infractions.

## Prompt Examples

**Prompt:** 
```
What is the disciplinary summary for referee ID 'ref_123'?
```

**Response:** 
```
Referee ref_123 has officiated 45 matches and issued a total of 32 cards, resulting in a discipline rate of 0.71 cards per match.
```

**Prompt:** 
```
How often does referee 'ref_456' penalize fouls with cards?
```

**Response:** 
```
Referee ref_456 has a punishment rate of 12.5 cards per 100 fouls.
```

**Prompt:** 
```
Does referee 'ref_789' show any home/away bias?
```

**Response:** 
```
Referee ref_789 shows a home/away card difference of 0.05, indicating very little bias between home and away teams.
```

## Capabilities

### Bias Detection
Your agent uses this to check if a referee favors one team over another based on home or away status.

### Punishment Analysis
The AI calculates the specific frequency at which fouls are escalated to cards.

### Disciplinary Summaries
Your client generates high-level overviews of how much an official impacts match flow via cards.

### Raw Data Auditing
The agent pulls unnormalized disciplinary totals for precise data verification.

## Use Cases

### Referee Strictness Profiling
Compare how different officials handle fouls to predict card frequency in upcoming matches.

### Bias Investigation
Check if a specific official has a statistical history of favoring home teams.

### Match Preparation
Analyze a referee's disciplinary summary before a big game to understand their officiating style.

### Data Auditing
Pull exact disciplinary counts to verify the accuracy of processed datasets.

## Benefits

- Calculates card-to-foul ratios automatically.
- Identifies home and away bias through specific metrics.
- Provides raw totals for deep data auditing.
- Generates match-level disciplinary summaries instantly.

## How It Works

Connect your client to Vinkius and start querying referee data immediately.

1. Connect your MCP-compatible client to Vinkius.
2. Ask your AI agent to retrieve data for a specific referee.
3. The agent calls the necessary tool to pull metrics or raw counts.
4. The AI processes the returned data into a readable answer or report.

## Frequently Asked Questions

**What can this MCP tell me about a referee?**
It provides data on card rates, foul punishment frequency, and home or away bias metrics.

**How do I check for referee bias?**
You can use the get_referee_impartiality_metrics tool to see if an official favors one team over another.

**Can I get raw disciplinary data?**
Yes, the get_referee_exact_counts tool provides raw, non-normalized totals for auditing purposes.

**Which AI clients work with this MCP?**
It works with any MCP-compatible client including Claude, Cursor, Windsurf, and VS Code.

**Does this tool provide match summaries?**
Yes, the get_referee_discipline_summary tool gives a high-level overview of a referee's disciplinary impact per match.

**How can I check if a referee is biased towards home teams?**
You can use the `get_referee_impartiality_metrics` tool to see the difference in card rates between home and away teams.

**What does the cards per 100 fouls metric represent?**
It measures the frequency of card issuance relative to the number of fouls, which helps identify how strict a referee is regardless of match physicality.

**Can I get the exact number of yellow cards issued by a referee?**
Yes, the `get_referee_exact_counts` tool provides raw, unrounded totals for yellow cards, red cards, and other disciplinary events.