# Repair or Replace Scorecard MCP. AI Agent Connect

> Repair or Replace Scorecard MCP gives your AI agent a mathematical framework for facilities management. It evaluates whether to maintain existing equipment or invest in new assets by weighing repair costs, expected lifespan, energy factors, and material needs. Instead of guessing, you get ranked options based on your specific priority weights.

## Overview
- **Category:** sustainability
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_LNRim3uSFfgUU24uP76KjwG8uOcdkGHVxIX8m5q7/ai-agent-connect
- **Tags:** asset-management, lifecycle, scoring, optimization, maintenance

## Description

You can stop debating whether an old piece of equipment is worth one more repair or if it's time to pull the trigger on a replacement. This MCP turns your AI client into a strategic asset manager. It uses a weighted scoring system to compare candidates across several dimensions, including repair costs, new item costs, and energy efficiency. You define what matters most to your budget or sustainability goals by setting weights, and the MCP handles the math. It ensures your priorities are logically sound before it generates a ranked list of your best options. Whether you are managing a fleet of HVAC units or industrial machinery, this tool provides the quantitative backbone needed for lifecycle planning. You can even filter results to stay within strict budget or longevity requirements, making it easy to present clear, defensible recommendations to stakeholders.

## Tools

### filter_options
This tool narrows your list of potential assets based on specific budget limits or required lifespans.

### summarize_decision
This tool generates a qualitative recommendation based on the calculated rankings.

### validate_weights
This tool checks your priority settings to ensure they are mathematically consistent and sum to 1.0.

### calculate_scores
This tool produces a ranked list of candidates by applying your custom weights to repair costs, life expectancy, and other factors.

## Prompt Examples

**Prompt:** 
```
Rank these options: Option A (Repair: 500, Life: 5, New: 2000, Material: 0.8, Energy: 0.7) and Option B (Repair: 1500, Life: 8, New: 2200, Material: 0.9, Energy: 0.9) with weights: {repairCost: 0.2, expectedLife: 0.3, newItemCost: 0.2, materialFactor: 0.15, energyFactor: 0.15}.
```

**Response:** 
```
Option B is the recommended choice with a total score of 0.78, outperforming Option A which scored 0.62.
```

**Prompt:** 
```
I have a budget of $1000. Which of these options are available: Option 1 (Repair: 800, Life: 3), Option 2 (Repair: 1200, Life: 4), Option 3 (New: 1500, Life: 10)?
```

**Response:** 
```
The available option within your $1000 budget is Option 1.
```

**Prompt:** 
```
Are these weights valid: {repairCost: 0.5, expectedLife: 0.5}?
```

**Response:** 
```
Yes, the weights are valid as they sum to 1.0.
```

## Capabilities

### Weighted Scoring
Your agent uses this to rank assets based on custom priorities like cost or energy use.

### Constraint Filtering
The AI uses this to remove any options that exceed your budget or fail to meet life expectancy needs.

### Weight Validation
Your agent runs this to confirm that your priority settings are mathematically sound.

### Decision Summarization
The AI uses this to turn raw scores into a clear, qualitative recommendation.

## Use Cases

### HVAC Lifecycle Planning
Compare the cost of repairing an aging chiller against the long-term energy savings of a new model.

### Fleet Maintenance
Decide which vehicles in a fleet need immediate replacement based on repair costs and expected life.

### Budget-Constrained Repairs
Filter potential maintenance tasks to only those that fit within a specific quarterly budget.

### Sustainability Audits
Prioritize new equipment purchases by weighting energy efficiency factors more heavily.

## Benefits

- Removes guesswork by using weighted math instead of intuition.
- Ensures mathematical accuracy in priority settings through weight validation.
- Provides a defensible ranking for budget approvals.
- Filters out unfeasible options before you waste time analyzing them.

## How It Works

Connect your client to Vinkius and start running calculations immediately.

1. Connect your MCP-compatible client to the Vinkius hosted MCP.
2. Provide your asset data and the weights you want to use for decision making.
3. The agent validates your weights to ensure they sum to 1.0.
4. The MCP calculates scores and ranks your options.
5. Your agent presents the final recommendation or filtered list.

## Frequently Asked Questions

**How does the scoring work?**
The MCP uses a weighted multi-factor scoring system. It applies your custom weights to variables like repair cost, expected life, and energy factors to rank each candidate.

**Can I limit results to a specific budget?**
Yes, you can use the filter_options tool to narrow down your candidates based on budget or longevity constraints.

**What happens if my weights don't sum to 1.0?**
The validate_weights tool is designed to ensure your priority settings are mathematically sound and consistent.

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

**Do I need to host this myself?**
No, Vinkius hosts and manages the MCP for you, so it is ready to use as soon as you connect.

**How do I ensure my priority weights are correct?**
You can use the `validate_weights` tool to verify that your priority multipliers are non-negative and sum exactly to 1.0.

**Can I filter options by a specific budget?**
Yes, the `filter_options` tool allows you to narrow down candidates based on a maximum budget or a minimum required expected life.

**What does the final recommendation tell me?**
The `summarize_decision` tool provides a qualitative recommendation and a confidence level based on the gap between the top-ranked option and the next best choice.