# Loop MCP

> Loop manages e-commerce operations by letting your AI agent handle complex customer interactions. It connects to your feedback loop and order history to process returns, analyze sentiment, and track product issues using natural conversation.

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

## Description

You connect Loop to your AI client and manage every corner of your e-commerce lifecycle—from initial customer feedback through product returns and refunds. Your agent uses these tools so you don't gotta jump between dashboards just to figure out what went wrong or how much money is owed. It pulls actionable data, analyzes sentiment, tracks specific product issues, and lets you document findings right inside the conversation.

### Customer Feedback Analysis

You can pull a list of all customer submissions using `list_feedback`, letting you filter those records by date range or even by where they came from. To see every channel that feeds data into the system—like chat widgets or survey forms—you run `list_feedback_sources`. You'll find recurring complaints and topics instantly when you use `list_feedback_themes`, which groups feedback submissions by common issues, for instance, 'sizing issues' or 'missing parts.' Need to know what people think overall? Running `get_sentiment_metrics` gives you the high-level numbers, like NPS and CSAT scores. When you need the full story on a single piece of input, `get_feedback_details` retrieves all available data points for that item—the text, its original source, and all associated metadata.

### Issue Tracking & Project Management

When things break, your agent handles it. You can pull a list of every open or closed developer ticket generated from feedback using `list_dev_tickets`. If you need the complete context for one specific bug report, `get_ticket_details` fetches everything—the status, who owns the ticket, and its entire history. To keep your operations organized, you'll also find `list_projects`, which retrieves a list of active projects within the Loop system, giving you scope context when dealing with a particular issue.

### Operational Documentation & Context

When an agent identifies something critical during a review, it can attach private notes directly to that feedback record using `add_internal_note`. This keeps your team visible on key records for follow-up. For basic account verification or context checks, `get_me` pulls essential user information. You'll also find the ability to list all active projects within the Loop system via `list_projects`, which helps keep you grounded in the current scope of work.

### Running Returns and Refunds

Your agent tracks return requests by status or reason code, handling the entire process from initial report through final resolution. It monitors your refund flow, letting you track all refunds, checking both the amount claimed and the current processing status for every single claim. When an exchange is needed, it even manages new order creation to make sure the replacement gets processed correctly.

## Tools

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

### get_feedback_details
Retrieves all available data points—text, source, and metadata—for one particular feedback item.

### get_me
Pulls basic account information to confirm the user context for operations.

### get_sentiment_metrics
Calculates and retrieves overall sentiment analytics (NPS, CSAT scores) from the feedback data pool.

### get_ticket_details
Fetches all context—including status, owner, and history—for a developer-assigned ticket.

### list_dev_tickets
Lists all currently open or closed developer tickets generated from feedback data.

### list_feedback
Retrieves a list of customer feedback items, allowing filtering by date range or source.

### list_feedback_sources
Shows every integrated channel—like chat widgets or surveys—that feeds data into the system.

### list_feedback_themes
Lists recurring themes identified in feedback, helping group complaints by topic (e.g., 'sizing issues').

### list_projects
Retrieves a list of active projects within the Loop system for context.

## 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 feedback sentiment
Get overall sentiment analytics from collected feedback to gauge product perception.

### List and filter customer submissions
Retrieve lists of all customer feedback items, allowing you to see the source or theme of each submission.

### Track specific developer tickets
Fetch detailed information on specific development tickets related to product issues.

### Monitor return and refund status
Access the current state of returns, including pending refunds, approved exchanges, and associated amounts.

### Manage internal notes on records
Attach private, actionable notes to specific feedback items for team visibility.

## Use Cases

### A customer complains about a damaged item and asks for next steps.
The agent first calls `get_feedback_details` to pull the original complaint text. Then, it checks the return status using the built-in refund tracking logic. Finally, it uses `add_internal_note` to flag the issue for Quality Control before confirming a replacement order.

### The team needs to know if 'sizing' is actually a major problem.
A PM asks the agent to run `list_feedback`, filtering by text containing 'size'. The tool returns results, and then the agent runs `list_feedback_themes` to confirm that 'wrong size' is indeed the top recurring theme. This data dictates the next product batch change.

### An existing bug report needs to be escalated to development.
A support rep reviews a ticket via `get_ticket_details`, sees it’s stalled, and then uses `list_dev_tickets` to see if similar issues were reported last week. This helps them add context using `add_internal_note` before escalating.

### The CEO needs a quick pulse check on overall product health.
The agent calls `get_sentiment_metrics` to get the current NPS/CSAT score. It then follows up by running `list_projects` to show which specific product line is dragging down that metric.

## Benefits

- See total return rates instantly. By calling `list_feedback` and then analyzing the results, you get a clear picture of operational health across all products.
- Stop guessing why customers complain: Use `list_feedback_themes` to group thousands of comments into actionable topic buckets (e.g., 'shipping' or 'poor instructions').
- Know exactly what needs fixing: Instead of general notes, use `get_ticket_details` and `list_dev_tickets` to trace feedback directly into an assigned development sprint.
- Process complex customer histories in one shot. You can check a refund's status via return tracking and then cross-reference the original product complaint using `get_feedback_details`.
- Get immediate performance scoring: Running `get_sentiment_metrics` gives you quick, quantifiable data (NPS/CSAT) without manual spreadsheet aggregation.

## How It Works

The bottom line is, you get a single chat window that pulls together data from your feedback collection, returns management, and ticket systems.

1. Subscribe to the Loop server and connect your API key.
2. Your AI client calls the necessary tools (e.g., `list_feedback`, `get_sentiment_metrics`).
3. The server returns structured data, which your agent then summarizes into plain English for you.

## Frequently Asked Questions

**How do I use list_feedback to find issues by theme?**
You should run `list_feedback` first to see available data. Then, you can follow up with the agent asking it to cross-reference those results against `list_feedback_themes`. This lets you narrow down complaints that share a topic.

**What is the difference between list_dev_tickets and get_ticket_details?**
`list_dev_tickets` shows you an overview—it lists all tickets. `get_ticket_details` requires a specific ticket ID, giving you the full history and context for just that one issue.

**Can I track returns using get_feedback_details?**
Yes. While `get_feedback_details` retrieves feedback data, the server's core functionality allows it to cross-reference this complaint with refund history and return status, giving you a complete view.

**How do I get overall sentiment metrics using get_sentiment_metrics?**
You simply prompt your agent to run `get_sentiment_metrics`. It calculates the NPS and CSAT scores across all available feedback data points for you instantly.

**What information does using `get_me` require for authentication?**
It requires your API Key and associated account credentials. This tool validates your connection, confirming which user profile is running the agent's actions.

**How do I use `list_feedback_sources` to check where feedback is coming from?**
It lists all integrated channels that contribute data to Loop. If you see missing feedback, checking this list helps confirm if a source (like an app or specific website page) is properly connected.

**When should I use `add_internal_note` instead of updating the record?**
Use it when your team needs to track context without changing the customer-facing data. Internal notes are for private discussions, follow-up assignments, or adding background details visible only to administrators.

**How does `list_projects` help me segment my return and feedback data?**
It groups your operational data under specific project identifiers. This lets you run targeted reports that analyze performance, sentiment, or returns for a single initiative, like 'Q3 Website Redesign.'

**Can I track return requests and process exchanges?**
Yes. Browse all return requests with status, reason codes, and product details. Track exchanges and new order fulfillment.

**Can I analyze return trends and reasons?**
Yes. Access return rates, top return reasons, product-level return analytics, and trend data over time.

**What API does Loop use?**
Bearer authentication against `loop.solve-studio.co/api/v1`.