# Measure AI Feature Impact on North Star Metrics AI Agent Connect

> The AI Feature NSM Analyzer calculates how specific AI features drive your company's North Star Metric (NSM). It analyzes the relationship between feature usage and core product goals, giving product teams the data needed for accurate decision-making. Use this MCP to find the percentage of metric movement attributed to a feature, assess predictive signals, and generate a final priority ranking. This tool helps you understand which features actually move the needle.

## Overview
- **Category:** product-management
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_yFt3TdlAk1TjCAGDiKY3X5VrqTckG0etrUBdM4oM/ai-agent-connect
- **Tags:** nsm, ai-impact, metrics, product-strategy, data-analysis

## Description

This MCP provides a mathematical framework for linking AI features directly to your North Star Metric. Instead of guessing which features matter most, you analyze the actual relationship between usage and core product goals. It helps product teams move past intuition and start making decisions based on precise impact measurement. You can quickly determine how much a single feature contributes to the overall metric, check how reliable certain usage patterns are as predictive signals, and get a final, balanced priority ranking that combines both mathematical impact and strategic intent. It's the data layer your product roadmap needs.

## Tools

### evaluate_leading_indicator
Determines how predictive a specific leading indicator is for the North Star Metric

### get_feature_impact_summary
Provides a high-level overview of a feature's health and contribution status

### get_nsm_contribution
Calculates the specific percentage of the North Star Metric that is driven by a specific AI feature

### rank_feature_priority
Generates a final priority ranking for an AI feature by combining mathematical impact with strategic intent

## Prompt Examples

**Prompt:** 
```
What is the contribution of our new autocomplete feature to our Daily Active Users NSM?
```

**Response:** 
```
The autocomplete feature contributes 4.5% to the Daily Active Users NSM, with a medium impact magnitude.
```

**Prompt:** 
```
How reliable is the 'AI prompt completion' metric as a signal for our North Star Metric?
```

**Response:** 
```
The 'AI prompt completion' metric has a predictive strength of 0.85 and is considered a Stable signal.
```

**Prompt:** 
```
Should we prioritize the 'Smart Summary' feature over 'Voice Input'?
```

**Response:** 
```
Based on the current metrics, 'Smart Summary' is ranked as P0 - Immediate due to its high NSM contribution and strategic alignment, while 'Voice Input' is ranked as P2 - Backlog.
```

## Capabilities

### Calculate NSM contribution
You use this when you need to know the specific percentage of the North Star Metric a feature drives.

### Assess predictive signals
You use this to determine how reliable a usage metric is for predicting future North Star Metric growth.

### Get feature health summary
You use this when you need a quick, high-level overview of a feature's current performance and contribution.

### Prioritize feature roadmap
You use this to generate a final ranking that balances both mathematical impact and strategic importance.

## Use Cases

### Feature Comparison
You want to know if Feature A or Feature B is more valuable. Run a comparison to see which one has a higher NSM contribution percentage.

### Roadmap Planning
The team needs to decide what to build next. Use the ranking tool to get a prioritized list combining impact and strategy.

### Metric Validation
You suspect a metric might be misleading. Use the leading indicator tool to check its predictive strength for the NSM.

### Quarterly Review
You need to report on product success. Get a high-level summary of feature health to show stakeholders where the product is succeeding.

## Benefits

- You get a precise percentage showing exactly how much a feature contributes to your North Star Metric.
- You determine if a usage pattern is a reliable signal for future growth, moving beyond simple correlation.
- You receive a final priority ranking that combines both mathematical impact and strategic alignment.
- You shift product discussions from 'what if' to 'this is the measurable impact'.

## How It Works

Connect your preferred AI client to the Vinkius catalog. You prompt the agent with a specific question about a feature or metric, and the MCP runs the necessary calculations to return a precise, actionable data point.

1. Connect your AI client (Claude, Cursor, Windsurf, VS Code) to the Vinkius catalog.
2. Specify the feature or metric you want to analyze in your prompt.
3. The MCP invokes the correct tool (e.g., `get_nsm_contribution`).
4. Your agent receives the calculated percentage or priority ranking.

## Frequently Asked Questions

**Does this MCP analyze real-time data?**
The MCP processes data to calculate impact and signals. It provides the mathematical framework for measurement, helping you understand the relationship between feature usage and your North Star Metric.

**What is the difference between NSM contribution and predictive strength?**
NSM contribution calculates the percentage of the metric movement tied to a feature. Predictive strength assesses how reliable a metric is as a signal for future growth.

**Can I use this to decide what to build next?**
Yes. The MCP provides a final priority ranking that combines both mathematical impact and strategic alignment, helping you make data-backed decisions for your roadmap.

**Is this tool only for AI features?**
While it is designed for AI features, the underlying framework measures the relationship between any feature usage and your core product goals.