# Accurate Startup Ranking and Scoring Engine AI Agent Connect

> Accelerator Selection Scoring provides a full system for ranking startup candidates. It starts by calculating a primary weighted score for any application. Then, it adjusts that score to account for potential interviewer bias. Next, it evaluates how well the startup fits the specific needs of the current cohort. Finally, it generates selection analytics, giving you percentile rankings and acceptance probabilities. This MCP gives you a data-driven way to cut through the noise and make better decisions.

## Overview
- **Category:** business
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_aqea14An4EhXYTHzQGWIoqNZxUeuxn7JbeRXLMij/ai-agent-connect
- **Tags:** startup, accelerator, scoring, selection, analytics

## Description

Need to rank a batch of startup applications? This MCP handles the heavy lifting. Instead of relying on gut feeling, you feed the data into the system, and it runs through a multi-stage scoring process. First, it calculates the core weighted score based on metrics like team strength or market size. But it doesn't stop there. It runs the scores through a bias correction layer, which is critical because human judgment varies. After that, it checks the candidate's strategic fit against the rest of the cohort. The result is a full analytics package, giving you clear percentiles and a likelihood of acceptance. It turns raw data into actionable ranking insights.

## Tools

### calculate_application_score
Calculates the primary weighted score for a single application

### evaluate_cohort_impact
Adjusts an application's score based on how well it fits the specific needs of the current cohort

### generate_selection_analytics
Provides a holistic view of an application's standing, including percentile and acceptance likelihood

### apply_bias_correction
Adjusts raw scores to mitigate the impact of individual interviewer tendencies

## Prompt Examples

**Prompt:** 
```
Calculate the score for a startup with Team: 8, Market: 9, Product: 7, Traction: 6, and weights: team=0.4, market=0.3, product=0.2, traction=0.1.
```

**Response:** 
```
The total weighted score for the application is 7.7.
```

**Prompt:** 
```
An interviewer gave a score of 7, but the cohort average is 8. What is the adjusted score?
```

**Response:** 
```
The adjusted score has been moved toward the cohort average to mitigate bias.
```

**Prompt:** 
```
What is the acceptance probability for a score of 8.5 when the historical threshold is 8.0 and the pool scores are [7.0, 7.5, 8.0, 8.5, 9.0]?
```

**Response:** 
```
The application has a high acceptance probability and ranks in the 80th percentile.
```

## Capabilities

### Calculate Weighted Scores
The AI uses this when you need a foundational score based on multiple input metrics.

### Correct for Bias
It applies this tool to neutralize subjective grading and account for individual human tendencies.

### Assess Cohort Fit
The AI runs this when you need to know if a startup aligns with the group's overall strategic needs.

### Predict Acceptance Likelihood
Use this to get a data-backed probability and percentile rank for any candidate.

## Use Cases

### Initial Application Screening
When you receive hundreds of applications, use the MCP to quickly calculate initial weighted scores and filter out low-fit candidates.

### Post-Interview Review
After interviews, run the scores through the bias correction tool to ensure the final ranking isn't skewed by one person's opinion.

### Cohort Planning
Use the cohort impact tool to ensure the next class of startups fills specific gaps in the market or industry.

### Final Selection Report
Generate a full selection analytics report that includes percentile rankings and acceptance likelihood for the board meeting.

## Benefits

- It calculates a primary weighted score using multiple metrics, giving you a solid baseline for comparison.
- It adjusts raw scores to mitigate the impact of individual interviewer tendencies, making results fairer.
- It evaluates a startup's strategic alignment against the entire group, ensuring cohort cohesion.
- It generates percentile rankings and acceptance probabilities, turning raw scores into actionable metrics.

## How It Works

Connecting this MCP to your AI client lets you run a full, multi-step scoring process with simple prompts. The AI executes the sequence of tools, providing a final, corrected score.

1. Connect your AI client (Claude, Cursor, etc.) to the Vinkius catalog and select this MCP.
2. Write a prompt detailing the candidate's metrics and the scoring weights you want to use.
3. The AI client calls the necessary tools, starting with the initial score calculation.
4. It then automatically applies bias correction and evaluates the cohort fit before presenting the final analytics.

## Frequently Asked Questions

**Does this MCP account for human bias?**
Yes. The MCP includes a specific tool to adjust raw scores. This process mitigates the impact of individual interviewer tendencies, ensuring your final ranking is more objective.

**What kind of data does it need?**
It requires structured data points, such as metrics (e.g., Team, Market, Product) and the corresponding weights you want to apply to those metrics.

**Can I just get a simple score?**
You can start by calculating the primary weighted score. However, for a complete picture, you should also run the score through the bias correction and cohort impact tools.

**Is this just a scoring tool, or does it predict success?**
It does both. It calculates a weighted score, but the final analytics tool provides acceptance probabilities and percentile rankings, giving you a prediction of standing.