# Loop MCP

> Loop brings e-commerce returns management and customer feedback collection together. Use this MCP to track product exchanges, monitor refunds, and gather actionable sentiment data via micro-surveys—all without disrupting the user experience. Connect your AI agent to Loop for comprehensive insights into why customers are leaving or what they want next.

## Overview
- **Category:** ecommerce
- **Price:** Free
- **Tags:** returns-management, refund-automation, exchange-tracking, customer-feedback, nps-surveys

## Description

When a product fails or a customer changes their mind, you need immediate answers. This MCP connects your AI client directly to your e-commerce return and feedback data. You can manage entire lifecycles—from tracking an initial return request to analyzing the root cause of dissatisfaction. Instead of jumping between separate systems for order status, refund history, and NPS scores, your agent handles it all in a single conversation. Need to figure out if 'wrong size' is costing you more than 'late delivery'? You just ask. The system pulls together the raw feedback, calculates overall sentiment metrics, and even helps build developer tickets based on recurring product issues. By connecting through Vinkius, your AI agent gets immediate access to this entire operational suite, making complex logistics management simple enough for a chat window.

## Tools

### list_projects
Retrieves a list of active projects managed within Loop.

### list_feedback_sources
Lists all the external sources where customer feedback is gathered.

### list_feedback_themes
Retrieves a list of common, recurring themes found in customer comments.

### list_dev_tickets
Lists developer tickets that were automatically generated from feedback data for tracking.

### add_internal_note
Attaches a private internal note to any specific piece of customer feedback for team context.

### get_feedback_details
Retrieves all detailed information about one specific piece of submitted customer feedback.

### get_me
Pulls basic account and user profile information for the connected service.

### get_sentiment_metrics
Calculates and retrieves overall sentiment analytics across all collected customer feedback.

### get_ticket_details
Retrieves the full details for a specific developer ticket created from product issues.

### list_feedback
Lists multiple customer feedback submissions, allowing review of recent activity.

## Prompt Examples

**Prompt:** 
```
Show return requests from this week and top return reasons.
```

**Response:** 
```
This week: 23 returns. Pending: 8, Approved: 12, Rejected: 3. Exchanges: 6 (26%). Refunds: 14 (61%). Store credit: 3 (13%). Top reasons: 'Wrong size' (9, 39%), 'Not as described' (5, 22%), 'Defective' (4, 17%), 'Changed mind' (3, 13%), 'Late delivery' (2, 9%). Return rate: 4.2%.
```

**Prompt:** 
```
Show return analytics and products with highest return rates.
```

**Response:** 
```
Return analytics (30 days): 89 returns, 4.2% rate. Exchange rate: 28% (25 exchanges saved $2,100 in revenue). Top return products: 'Slim Fit Shirt M' (12 returns, 15% rate ⚠️). 'Running Shoes 10' (8, 8%). 'Wireless Headphones' (6, 3%). Refund total: $4,580. Average processing: 2.1 days. Customer retention post-return: 72%.
```

**Prompt:** 
```
Show return history for customer sarah@company.com and pending refunds.
```

**Response:** 
```
sarah@company.com: 2 returns (last 6 months). 1) 'Slim Fit Shirt L' — exchanged for XL ✅ (Mar 15). 2) 'Wireless Mouse' — refunded $45 ✅ (Feb 8, defective). Lifetime orders: 12 ($890). Return rate: 17% (above avg ⚠️). Pending refunds (all customers): 5 total, $234. Oldest: 3 days (Sarah, $45). Processing: automatic.
```

## Capabilities

### Analyze Customer Sentiment
Get overall sentiment analytics from customer feedback data.

### Process Returns and Exchanges
Track specific return requests, monitor product exchanges, and manage new order creation based on returns.

### Audit Refund Status
View refund history, including amounts processed and current status for accounting reconciliation.

### Identify Problematic Products
Access return rates, top reasons for returns, and trend data to spot product weaknesses.

### Review Feedback Sources
List all integrated sources where customers provide feedback (e.g., surveys, checkout forms).

## Use Cases

### Investigating a high-value customer's complaint
A support agent needs to know why Sarah returned an item. They ask their AI client, and it pulls up her entire return history using `list_feedback`, checks for any pending refunds, and identifies if the product she bought is also showing a high return rate across other customers.

### Quarterly operations review
The Ops Manager needs to know the biggest cost driver. They prompt their agent to show top return reasons and calculate total refunds processed last quarter, allowing them to present clear, data-backed arguments for logistics changes.

### Product team identifying a flaw
The Product Manager wants to know if the new shirt design is bad. They ask their agent to list recurring feedback themes and check the general sentiment metrics, immediately confirming that 'Wrong size' is the dominant complaint.

### Handling an exchange request
A customer calls about a damaged item. The support agent uses the MCP to track the product exchange status and confirm if the initial return was processed correctly, guiding the customer through creating the new order immediately.

## Benefits

- Stop manually cross-referencing order logs. Your agent checks the refund history and return status instantly, giving you a single source of truth for customer accounts.
- Analyze why products are failing. The MCP lets you pull detailed return analytics to pinpoint top failure reasons or most returned items, guiding product improvements.
- Turn feedback into action. Instead of just reading comments, your agent can generate developer tickets based on recurring themes found in the data.
- Understand customer sentiment immediately. By using `get_sentiment_metrics`, you get a quantified measure of customer satisfaction that goes far beyond simple star ratings.
- Keep support history clean. You can use the ability to add an internal note directly to any feedback item, giving context to your team without modifying the public record.

## How It Works

The bottom line is, your AI client turns complex operational questions into simple conversational queries.

1. Subscribe to this MCP and enter your Loop API key.
2. Your AI agent accesses the connection via Vinkius.
3. You prompt the agent with a task (e.g., 'Show all pending refunds for Q3'), and it executes the required data retrieval.

## Frequently Asked Questions

**How does the Loop MCP help with refund tracking?**
The MCP allows your agent to monitor refunds by accessing specific amounts and processing status. You can quickly confirm if a customer's money has been fully returned or is still pending.

**Can I use the Loop MCP to find out why customers are returning things?**
Yes, you can. The tool provides return analytics and top reasons for returns, giving you quantifiable data on what's driving your product returns.

**Does this MCP handle sentiment analysis from surveys?**
It does. You can call `get_sentiment_metrics` to get an overall numerical score of customer satisfaction across all collected feedback sources.

**What is the difference between listing feedback and getting details?**
Listing feedback shows you a summary view of multiple submissions. Getting feedback details pulls every single piece of information for just one specific item, giving deep context.

**How do I track exchanges using the Loop MCP?**
The MCP enables tracking product exchanges and can even help with creating new orders based on those exchange records, streamlining the fulfillment process.