# Photo Library Deduplication Plan AI Agent Connect

> Photo Library Deduplication Plan MCP uses technical metadata like file hashes, capture times, and dimensions to find exact photo duplicates. It helps you identify redundant files, pick the best version to keep, and calculate exactly how much storage you'll win back without risking your unique images.

## Overview
- **Category:** storage
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_4g8T0vvzaXCkGU4pJrJEnxg5RjZ2zcricTICmFNI/ai-agent-connect
- **Tags:** photos, deduplication, metadata, storage-management, image-processing

## Description

Managing massive photo collections often means dealing with a mess of redundant files that eat up drive space. This MCP gives your AI client the ability to scan through photo records and pinpoint exact duplicates by looking at file hashes and dimensions rather than just filenames. You can use it to build a cleanup plan that picks the highest quality master file for every duplicate group. It includes built-in safety checks to ensure you don't accidentally delete unique shots. Instead of manually hunting for copies, you can just ask your agent to find the duplicates and tell you how much space you can save.

## Tools

### select_master_files
This tool determines which specific file in a duplicate group is the best one to keep.

### analyze_recovery_impact
This tool calculates the total storage space you will gain by following a deduplication plan.

### find_duplicate_groups
This tool identifies sets of photo records that are exact duplicates. It groups files based on matching technical metadata.

### validate_deduplication_safety
This tool runs a check to make sure your proposed cleanup won't delete unique images.

## Prompt Examples

**Prompt:** 
```
Find all duplicate photo groups in this list: [{'hash': 'abc123', 'captureTime': '2023-01-01T12:00:00Z', 'dimensions': '4000x3000', 'size': 5000000, 'storagePath': '/photos/img1.jpg'}, {'hash': 'abc123', 'captureTime': '2023-01-01T12:00:00Z', 'dimensions': '4000x3000', 'size': 5000000, 'storagePath': '/photos/copy_img1.jpg'}]
```

**Response:** 
```
{ "groups": [{ "masterFile": { "hash": "abc123", "captureTime": "2023-01-01T12:00:00Z", "dimensions": "4000x3000", "size": 5000000, "storagePath": "/photos/img1.jpg" }, "duplicates": [{ "hash": "abc123", "captureTime": "2023-01-01T12:00:00Z", "dimensions": "4000x3000", "size": 5000000, "storagePath": "/photos/copy_img1.jpg" }], "recoverableBytes": 5000000 }] }
```

**Prompt:** 
```
How much space can I recover from these duplicate groups?
```

**Response:** 
```
You can recover a total of 5,000,000 bytes by deleting the redundant files.
```

**Prompt:** 
```
Which file should I keep for the duplicate group with hash 'xyz789'?
```

**Response:** 
```
The file at '/photos/img_main.jpg' should be kept as the master file.
```

## Capabilities

### Duplicate Detection
Your agent uses file hashes and dimensions to find identical photo records.

### Storage Calculation
The AI calculates the exact amount of bytes you can reclaim from redundant files.

### Master File Selection
Your agent picks the best version of a photo to keep based on metadata.

### Data Loss Prevention
The MCP runs safety checks to ensure unique photos aren't included in the deletion plan.

## Use Cases

### Massive Photo Cleanup
Identify and remove thousands of duplicate images from a single backup drive.

### Storage Optimization
Calculate how much space you'll get back before clearing out redundant files.

### Media Library Auditing
Check a list of photo metadata to find exact duplicates across different folders.

### Safe Deduplication
Verify that a cleanup plan won't delete important, unique photos.

## Benefits

- Identifies duplicates using file hashes instead of just names.
- Calculates exact storage savings before you delete anything.
- Prevents accidental loss of unique images through safety validation.
- Automates the selection of high-quality master files.

## How It Works

Connect the MCP to your client and let your agent handle the metadata analysis.

1. Connect the MCP to your AI client like Claude or Cursor.
2. Provide a list of photo metadata to your agent.
3. Ask the agent to find duplicate groups using the metadata.
4. Run a safety check to confirm the plan won't delete unique files.
5. Execute the plan to reclaim your storage space.

## Frequently Asked Questions

**How does this MCP find duplicates?**
It uses technical metadata like file hashes, capture times, and dimensions to find exact matches.

**Can I use this with Claude?**
Yes, you can connect this MCP to any MCP-compatible client including Claude, Cursor, and Windsurf.

**Will I lose unique photos?**
The MCP includes a validation tool specifically designed to check that your plan won't result in the loss of unique files.

**How much space can I save?**
You can use the analyze_recovery_impact tool to see the exact amount of storage space you will recover.

**Does it pick the best photo to keep?**
Yes, the select_master_files tool determines which file in a duplicate group is the best one to keep.

**How does the system identify a duplicate?**
A photo is considered an exact duplicate if it shares the same file hash, capture time, and dimensions.

**How is the master file chosen?**
The system uses deterministic rules: it prioritizes the file with the shortest storage path. If paths are equal, it selects the one with the most recent timestamp.

**Is it safe to run the deduplication plan?**
Yes, you can use `validate_deduplication_safety` to verify that the proposed deletions will not result in the loss of any unique files.