# Userback MCP

> Userback MCP Server collects visual product feedback—annotated screenshots, screen recordings, and bug reports. Connect this server to your AI agent to process user suggestions through natural conversation. Get instant access to all feedback entries, list projects, track bugs, or create new reports without leaving your chat window.

## Overview
- **Category:** developer-tools
- **Price:** Free
- **Tags:** visual-feedback, bug-reporting, user-experience, annotated-screenshots, product-development

## Description

Listen up. This Userback MCP Server hooks your visual product feedback—all those annotated screenshots, recordings, and bug reports—straight into your AI client. You'll use it to process user suggestions and track bugs through plain conversation with your agent. It lets you get instant access to every piece of feedback data without ever leaving the chat window.

**Managing Your Projects:**
You can pull a comprehensive list of every project space you’ve set up in Userback using `list_userback_projects`, keeping all your development efforts neatly separated. When you need the deep context on one specific initiative, you run `get_project_details` to pull all the full metadata and scope for that single project space.

**Tracking Feedback:**
If you wanna see what's been reported across the board, you use `list_feedbacks` to get a summary list of every bug entry or suggestion logged in your account. For deep dives, you can run `get_feedback_details` on any unique feedback entry ID; that pulls all the specific metadata, screenshots, and comments attached to that single report. When you find an issue or have a new idea, you don't gotta switch tabs—you just use `create_feedback_entry` to generate and save a brand-new bug report or suggestion directly through the chat interface.

**Knowing Your Team:**
You can run `list_account_users` anytime to get a list of every user and collaborator connected to your Userback account, so you know exactly who’s on the review team. This setup gives your agent six core functions: listing all projects, getting project details, listing feedback summaries, pulling deep feedback records, creating new reports instantly, and mapping out your entire team.

It's built to handle the raw data—the bits and pieces of info you need to actually ship something good. You tell it what you want, and your AI client pulls it off.

## Tools

### create_feedback_entry
Generates and saves a new bug report or suggestion into your Userback account for a specified project.

### get_feedback_details
Retrieves all specific metadata, screenshots, and comments associated with one unique feedback entry ID.

### get_project_details
Pulls the full details and scope of a single Userback project space.

### list_account_users
Fetches a list of all users and collaborators connected to your Userback account.

### list_feedbacks
Lists summaries for all feedback entries across the entire Userback account.

### list_userback_projects
Provides a comprehensive list of every project space currently set up in your Userback account.

## Prompt Examples

**Prompt:** 
```
List all feedback projects in my Userback account.
```

**Response:** 
```
I've retrieved your projects. You have 3 active feedback spaces: 'Marketing Site', 'Product App v2', and 'Internal Tools'. Which one would you like to see feedback for?
```

**Prompt:** 
```
Show me the latest bug reports for the 'Product App v2' project.
```

**Response:** 
```
I've fetched the entries. There are 4 recent reports including 'Login button overlap', 'Checkout error on mobile', and 'Missing icon in settings'. Shall I retrieve details for the checkout error?
```

**Prompt:** 
```
Create a new suggestion: 'Add dark mode support' to project '10293'.
```

**Response:** 
```
Success! The suggestion 'Add dark mode support' has been created for project 10293 (ID: fb_99023). I've added your notes and it is now visible in your dashboard.
```

## Capabilities

### List all available projects
The server retrieves a list of every project space you have set up for collecting user feedback.

### Get specific project details
It pulls detailed metadata for one chosen project, giving context to the ongoing development effort.

### List all bug reports and suggestions
The agent fetches a summary list of every feedback entry logged in your account.

### Get detailed feedback records
You can pull full details, including annotated screenshots and comments, for one specific bug report or suggestion.

### Create new reports instantly
The server lets you programmatically generate a brand-new feedback entry or bug report right through the chat interface.

### List team members
It lists every user and collaborator who has access to the Userback account, helping map out your review team.

## Use Cases

### Reviewing the latest checkout errors.
A QA engineer needs to review all bugs logged for 'Product App v2'. They ask their agent to list_feedbacks. The agent returns 4 recent reports, including a critical one about mobile checkout failure. The engineer then uses get_feedback_details on that specific bug ID to pull the annotated screenshot and reproduction steps.

### Onboarding a new team member.
A Product Lead needs to know who is authorized to sign off on UI changes. They ask their agent to list_account_users, which immediately returns all current collaborators. This saves them from manually checking permissions across multiple internal tools.

### Capturing a new user suggestion.
A designer talks to a client who suggests dark mode support. Instead of taking screenshots and filling out a form, the designer asks the agent to create_feedback_entry, providing the project ID and key notes—the bug report is logged instantly.

### Understanding project scope changes.
A PM wants to know if a specific feature ('Dashboard V3') has been officially scoped. They first use list_userback_projects to find the correct space, then get_project_details to read the latest defined goals and boundaries for that area.

## Benefits

- Process raw visual input fast. Instead of opening a browser to check bug reports, ask the agent to list all feedbacks or get_feedback_details for specific entries. You see the annotated screenshots right in your chat window.
- Keep development organized with project context. Use list_userback_projects and then get_project_details to confirm exactly which scope you're working on before creating a new entry via create_feedback_entry.
- Track team visibility instantly. The list_account_users tool pulls your entire review board roster, so you always know who owns the sign-off process for a given feature.
- Capture ideas without friction. When users suggest something, use create_feedback_entry. It lets you log the suggestion and notes immediately, preventing valuable user insights from getting lost in email chains.
- Contextualize everything. The combination of list_feedbacks (overview) and get_feedback_details (deep dive) allows your agent to move from a general idea to a specific, actionable bug report seamlessly.

## How It Works

The bottom line is, your AI client acts as a proxy. It handles the complex API calls so you just talk to it like normal.

1. First, subscribe to this server and provide your API token. This connects your AI agent to your Userback data.
2. Next, prompt your agent with a specific request, like 'List all projects' or 'Show me bugs for the checkout flow.'
3. Finally, the agent calls the appropriate tool, retrieves the raw data (like project names or bug IDs), and presents it back to you in conversational text.

## Frequently Asked Questions

**How does the Userback MCP Server work with annotated screenshots?**
The server is built around collecting visual context. When you use get_feedback_details, it pulls not just text, but the full metadata and the embedded annotated screenshots that show exactly where the bug occurred.

**Can I list all my projects using the Userback MCP Server?**
Yes. Use list_userback_projects to see every single feedback space you have set up in your account, which is great for knowing where to focus your efforts next.

**What if I want to track a bug that's already reported?**
You can use list_feedbacks to get an overview of all entries. Then, run get_feedback_details with the specific ID to pull up all historical context and current status updates for that bug.

**Is there a way to create feedback reports directly from my IDE?**
Yes. By connecting this server to your AI client (like Cursor), you can use create_feedback_entry right from your coding environment, streamlining the entire reporting loop.

**Before I use the Userback API tokens, where do I find the necessary credentials?**
You find your unique API Token in your account settings under the dedicated API section. This token authenticates your AI client and allows it to run tools like 'list_userback_projects'. It's crucial for connecting your agent to Userback data.

**If I try to pull a lot of entries, are there rate limits when using the Userback MCP Server?**
Yes, the server enforces standard API rate limits. If you attempt bulk operations—like listing thousands of feedbacks via 'list_feedbacks'—the connection will throttle your requests temporarily. We recommend batching calls to avoid disruption.

**What does the Userback tool handle if I try to get details for a non-existent project?**
If you use 'get_project_details' with an invalid ID, the server will return a specific HTTP error code and a descriptive message. Your AI client can then read this response and tell you exactly which Project ID needs correction.

**How can I check who is on my organization’s review team using Userback?**
You use the 'list_account_users' tool to retrieve a roster of all associated users. This lets your agent verify which team members have access and visibility into the feedback projects.

**Can I filter feedback by project ID?**
Yes! Use the `list_feedbacks` tool and provide the optional `project_id` parameter to retrieve entries only for that specific project.

**How do I see the comments on a specific feedback item?**
Run the `get_feedback_details` query with the unique Feedback ID. Your agent will retrieve the complete metadata, including any internal or user comments.

**Is it possible to create a new bug report via AI?**
Absolutely. Use the `create_feedback_entry` action. Provide the Project ID, a title, and an optional comment to log a new entry in your Userback account.