# Repair Quality Review AI Agent Connect

> Repair Quality Review MCP acts as an automated quality assurance engine for repair services. It pulls data from repair scopes, completion reports, functional tests, and photos to catch missed tasks or performance issues. Your AI client uses this data to build pickup checklists and customer reports, ensuring the physical work actually matches what was promised.

## Overview
- **Category:** quality-assurance
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_HH56K1WWPp7kDE017wNIVHEdRT8kpchmdn6JUvgY/ai-agent-connect
- **Tags:** repair, inspection, qa, automation, verification

## Description

You can stop manually cross-referencing repair logs with work orders. This MCP automates the heavy lifting of quality assurance by synthesizing data from your repair scopes and completion reports. It looks at functional test results and visual evidence to make sure nothing was missed. 

When a technician submits a job, your AI client can immediately check if the work satisfies the original requirements. It compares performance tolerances to ensure everything functions as intended and uses photos to confirm the physical work matches the documentation. Instead of hunting through files, you get clear, actionable outputs like pickup checklists for customers or summaries of unresolved issues. It turns raw repair data into a reliable verification layer for your service workflow.

## Tools

### analyze_repair_completeness
This tool checks if the work documented in a completion report actually meets the requirements set in the original repair scope.

### evaluate_visual_compliance
This tool uses provided photos to confirm that the physical work performed matches what was reported in the documentation.

### generate_quality_summary
This tool pulls all inspection findings together into a single report for your customers.

### verify_functional_integrity
This tool compares post-repair performance test results against the required standards to ensure everything works correctly.

## Prompt Examples

**Prompt:** 
```
Check if the repair was completed according to the scope.
```

**Response:** 
```
The repair is complete. All requested items in the scope were found in the completion report, and all functional tests passed.
```

**Prompt:** 
```
Generate a quality summary for the customer.
```

**Response:** 
```
Pickup Checklist: 1. Verify new brake pads installation. 2. Confirm fluid levels. Follow-up Issues: 1. Visual: Minor scratch on left fender.
```

**Prompt:** 
```
Verify if the visual evidence matches the reported work.
```

**Response:** 
```
The visual evidence confirms the installation of the new component as reported.
```

## Capabilities

### Scope Verification
Your agent compares completion reports against the initial work order to find missing tasks.

### Visual Inspection
The AI uses uploaded photos to validate that the physical repairs match the written reports.

### Performance Checking
Your agent reviews functional test data to ensure all performance tolerances are met.

### Customer Reporting
The AI aggregates all QA findings into a clear summary for the end user.

### Issue Identification
Your agent flags unresolved issues or visual discrepancies found during the review process.

## Use Cases

### Automated Post-Repair Audit
Compare a completed automotive repair against the original work order to ensure every part was replaced.

### Visual Work Validation
Use photos of a finished repair to confirm the technician actually installed the parts they claimed to.

### Functional Testing Review
Check if a machine's post-repair performance meets the required technical specifications.

### Customer Handover Preparation
Create a final quality summary and pickup checklist once a repair is verified as complete.

## Benefits

- Automates the comparison of repair scopes against completion results.
- Uses visual evidence to catch discrepancies between reports and physical work.
- Generates ready-to-use pickup checklists for customers.
- Identifies unresolved issues through functional test analysis.

## How It Works

Connect your AI client to the MCP and start feeding it repair data.

1. Connect your preferred MCP-compatible client to Vinkius.
2. Provide the repair scope and completion report data to your agent.
3. Upload photos or functional test results for the AI to review.
4. Run the analysis tools to verify completeness and compliance.
5. Generate the final quality summary for the customer.

## Frequently Asked Questions

**What does this MCP actually do?**
It automates quality assurance for repairs by comparing what was supposed to be done against what was actually reported and photographed.

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

**How does it verify visual work?**
It uses the evaluate_visual_compliance tool to check uploaded photos against the written completion reports.

**Can it help with customer communication?**
Yes, it uses the generate_quality_summary tool to create checklists and reports for customers.

**Do I need to host the MCP myself?**
No, Vinkius hosts and manages the MCP for you. You just connect your client and start using the tools.

**What does this server do?**
It automates the comparison between what was planned in a repair scope and what was actually performed, providing a final checklist for customers.

**How can I use the visual verification tool?**
You can use `evaluate_visual_compliance` by providing a photo set ID and the specific work item ID to verify if the physical repair matches the report.

**Does it support functional testing?**
Yes, `verify_functional_integrity` allows you to check if post-repair measurements fall within your required performance thresholds.