# Over/Under Goals Probability Calculator AI Agent Connect

> Over/Under Goals Probability Calculator MCP lets your AI client process scoreline matrices to determine the likelihood of specific goal totals. It handles the math for Over, Under, and Push scenarios across any goal line you set. You provide the distribution, and your agent calculates the exact probabilities for match outcomes.

## Overview
- **Category:** statistics
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_9XRmc5HGWWYJF9fyZzvrpTce0x3PVPJ5gP8ePutD/ai-agent-connect
- **Tags:** football, soccer, betting, math, analytics

## Description

This MCP is built for football analysts who need to turn raw scoreline distributions into actionable goal line data. Instead of manually summing probabilities, you feed your scoreline matrix to your AI client and let it do the heavy lifting. You can test any goal line, whether it is a standard 2.5 or a custom threshold. 

Your agent can pull statistical summaries to find expected totals or filter specific outcomes to see how they impact the overall distribution. It also acts as a mathematical safety net. If your input matrix is broken or the probabilities don't sum to one, the MCP catches the error before you rely on flawed data. It is a specialized math engine for anyone modeling soccer match outcomes.

## Tools

### calculate_over_under_probabilities
This tool calculates the exact probability of a match landing over, under, or pushing a specific goal line. It processes your provided scoreline matrix against your chosen threshold.

### filter_scorelines_by_total
Use this to isolate specific outcomes from your distribution. It returns only the scorelines that result in a specific total number of goals.

### get_distribution_summary
This tool provides a statistical overview of your goal distribution. It identifies key metrics like expected total goals and the most likely goal counts.

### validate_matrix_integrity
This tool checks your scoreline matrix for mathematical errors. It ensures your probability distributions are valid and sum to one.

## Prompt Examples

**Prompt:** 
```
Calculate the over/under probabilities for a 2.5 goal line using this matrix: [{"homeGoals": 0, "awayGoals": 0, "probability": 0.1}, {"homeGoals": 1, "awayGoals": 0, "probability": 0.2}, {"homeGoals": 0, "awayGoals": 1, "probability": 0.2}, {"homeGoals": 1, "awayGoals": 1, "probability": 0.5}]
```

**Response:** 
```
{"overProbability": 0.5, "underProbability": 0.5, "pushProbability": 0.0}
```

**Prompt:** 
```
What is the expected total goals for this distribution: [{"homeGoals": 1, "awayGoals": 0, "probability": 0.5}, {"homeGoals": 0, "awayGoals": 1, "probability": 0.5}]
```

**Response:** 
```
{"expectedTotalGoals": 1.0, "mostLikelyTotalGoals": 1, "probabilityOfZeroGoals": 0.0}
```

**Prompt:** 
```
Check if this matrix is valid: [{"homeGoals": 1, "awayGoals": 0, "probability": 0.8}]
```

**Response:** 
```
{"isValid": false, "reason": "Probabilities sum to 0.8 instead of 1.0"}
```

## Capabilities

### Goal Line Probability
Your agent calculates Over, Under, and Push odds for any specific goal threshold.

### Statistical Summaries
The MCP generates expected goal values and most likely outcomes from your data.

### Data Validation
Your AI client checks that your input matrices are mathematically sound before running calculations.

### Outcome Filtering
The tool isolates specific goal totals from a larger distribution of scorelines.

## Use Cases

### Testing Betting Lines
Compare your predicted scoreline distribution against a specific 2.5 goal line to find the probability of the Over hitting.

### Model Validation
Run a matrix through the integrity check to ensure your model's probabilities are mathematically consistent.

### Expected Value Analysis
Use the summary tool to find the expected total goals for a projected match outcome.

### Outcome Isolation
Filter a large distribution to see only the specific scorelines that result in exactly two goals.

## Benefits

- Automates the math required to convert scoreline matrices into goal line probabilities.
- Prevents errors by validating that probability distributions sum to exactly one.
- Reduces manual calculation time for custom goal thresholds.
- Provides instant statistical summaries of match outcome distributions.

## How It Works

You connect the MCP to your client and provide the data for processing.

1. Connect your preferred MCP-compatible client to Vinkius.
2. Provide a scoreline matrix containing home/away goals and their probabilities.
3. Ask your AI client to run a specific tool like calculate_over_under_probabilities.
4. Receive the calculated probabilities or statistical summaries immediately.

## Frequently Asked Questions

**What is a scoreline matrix?**
It is a distribution of possible match outcomes, where each entry includes the home goals, away goals, and the probability of that specific score occurring.

**Can I use this for leagues other than soccer?**
The tools are specifically designed for football (soccer) total-goal calculations based on scoreline matrices.

**How do I know if my probability data is correct?**
You can use the validate_matrix_integrity tool to check if your probabilities sum to one and are mathematically valid.

**What clients can I use with this MCP?**
You can use any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

**Does this MCP handle push scenarios?**
Yes, the calculate_over_under_probabilities tool provides the probability for Over, Under, and Push scenarios.

**What is a 'push' in goal probability?**
A 'push' occurs when the total goals scored exactly match the integer goal line. For half-integer lines like 2.5, a push is impossible.

**How do I format the scoreline matrix?**
The matrix should be a JSON array of objects, where each object contains `homeGoals`, `awayGoals`, and `probability` (e.g., `[{"homeGoals": 1, "awayGoals": 0, "probability": 0.4}]`).

**Can I use this with Claude Desktop?**
Yes, this server can be connected to Claude Desktop, Cursor, VS Code, Windsurf, and any other MCP-compatible client via Vinkius Edge.