# BugBug MCP for AI Agents AI Agent Connect

> BugBug MCP lets you run and manage no-code browser tests through your AI agent. It connects your QA pipeline to your agent so you can trigger regression suites, check test statuses, and pull IP addresses for allowlisting without leaving your workspace.

## Overview
- **Category:** developer-tools
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_Na0MiOd5DLIkm5F48FVbS0nJAKsJ9lCI3JIUBfdX/ai-agent-connect
- **Tags:** browser-automation, end-to-end-testing, no-code-testing, web-testing, quality-assurance, regression-testing

## Description

Connecting BugBug to your AI agent turns your chat window into a QA command center. Instead of hopping between browser tabs to check if a new deployment broke the checkout flow, you can just ask your agent to run the specific suite. You get real-time status updates and high-fidelity reports directly in the chat. It handles the heavy lifting of cloud test orchestration while you focus on shipping code. Since Vinkius hosts this Connector, it's easy to plug into your existing workflow with Claude or Cursor. You can dig into historical trends to see where regressions are popping up or grab the necessary IP addresses for your firewall rules. It takes the manual friction out of quality assurance, making it feel like you have a dedicated QA engineer sitting right next to you.

## Tools

### get_suite
View the details and configuration for a particular test suite. It helps you understand the scope of your automated tests.

### get_test_run
Retrieve the status of an individual test run. Use this for granular tracking of specific test cases.

### get_test
Pull specific details for a single test case. This is useful for deep-diving into one specific test's requirements.

### list_projects
See a full list of your projects within the BugBug platform. This helps you navigate your different environments.

### list_suite_runs
View a history of your recent suite executions. Use this to audit performance over time.

### list_suites
Browse all the test suites you have created. It gives you a bird's eye view of your total test coverage.

### list_test_runs
See a list of your most recent individual test runs. This is great for checking the latest results quickly.

### list_tests
Get a complete list of all tests in your account. Use this to verify that all your test cases are correctly registered.

### run_suite
Trigger a specific test suite to run in the cloud. This starts the automation for a group of tests immediately.

### get_ips
Get the specific IP addresses for BugBug to update your firewall allowlist. This helps you keep your infrastructure secure.

### get_suite_run
Check the current status of a specific suite execution. Use this to see if your latest tests are still running or finished.

### run_test
Execute a single test case immediately. This is the fastest way to verify a specific user flow.

## Prompt Examples

**Prompt:** 
```
Run the login flow test suite.
```

**Response:** 
```
I've started the 'Login Flow' suite in your default environment. You can see the progress here: [link]. I'll let you know when it's done.
```

**Prompt:** 
```
What's the status of the last 5 test runs?
```

**Response:** 
```
Here are the results for your latest runs:

| Run ID | Status | Duration |
|---|---|---|
| run_101 | Passed | 45s |
| run_102 | Failed | 30s |
| run_103 | Passed | 42s |
| run_104 | Passed | 44s |
| run_105 | Passed | 46s |
```

**Prompt:** 
```
Give me the BugBug IP addresses for my firewall.
```

**Response:** 
```
I've retrieved the current BugBug IP addresses for your allowlist: 192.168.1.1, 192.168.1.2, 192.168.1.3. Let me know if you need anything else.
```

## Capabilities

### Trigger browser tests
Run specific tests or entire suites in the cloud instantly.

### Monitor run status
Get live updates on whether your tests are passing or failing.

### Pull project metadata
View your list of projects and suite details to stay organized.

### Fetch firewall IPs
Retrieve BugBug IP addresses for secure allowlisting in your infrastructure.

### Review test history
Access past run records to identify recurring quality issues.

## Use Cases

### Smoke test check
A developer pushes to staging and asks the agent to run the Smoke Test suite to ensure the site is up and functional.

### Regression monitoring
A QA lead asks the agent for the status of the Checkout suite to see if the latest update caused any failures.

### Firewall configuration
A DevOps person needs to allowlist BugBug IPs and asks the agent to fetch them to update the production firewall.

### Test audit
A product manager asks the agent to list all tests to see what is currently covered by the automation suite.

## Benefits

- Run suites instantly with run_suite instead of manually navigating the BugBug dashboard to find and start them.
- Stay updated on deployment health by checking get_suite_run status directly in your chat without refreshing pages.
- Simplify security setup by using get_ips to quickly find addresses for your firewall allowlist.
- Track quality trends over time by pulling historical data with list_suite_runs to see where bugs are recurring.
- Verify specific UI components on demand using run_test without opening a new browser tab or tab.
- Keep your projects organized by using list_projects to quickly switch context between different app environments.

## How It Works

The bottom line is you get a voice-controlled QA dashboard that executes cloud tests on demand.

1. Subscribe to the BugBug MCP on Vinkius and grab your API token from the integrations tab in your BugBug dashboard.
2. Connect the Connector to your preferred AI client like Claude or Cursor.
3. Ask your agent to run a test suite or check the status of a recent deployment.

## Frequently Asked Questions

**What is the BugBug MCP?**
It is a way to connect your BugBug account to your AI agent. This lets you trigger browser tests and check QA results using natural language instead of clicking through a dashboard.

**Can I run tests from Cursor?**
Yes, once you connect this Connector to Cursor, you can ask your agent to run suites or check statuses directly from your code editor.

**How do I get my API token?**
You can find your API token in the integrations tab of your BugBug dashboard. You'll need this to link the Connector to your AI client.

**Can it handle multiple projects?**
Yes, it can list and interact with all the projects you have set up in BugBug, making it easy to switch between different apps or environments.

**Does it show me the actual test results?**
It provides the status of your runs and can pull high-fidelity reports. You can ask your agent to summarize the results or provide a link to the full report.

**How does it help with firewall rules?**
It can automatically fetch the current BugBug IP addresses. This makes it much faster to update your firewall allowlists without having to hunt for them in documentation.

**Is it for no-code testing?**
Yes, it's designed to work with BugBug's no-code browser tests, allowing you to manage complex automation without writing scripts.

**How do I find my BugBug API Token?**
Log in to your account, navigate to the **Integrations** tab in the sidebar, and copy your unique API Token.

**Can I run tests in a specific environment?**
Yes! Both `run_test` and `run_suite` tools accept an optional `environmentId` parameter to target specific deployment stages.

**How do I get the IP addresses for allowlisting?**
Use the `get_ips` tool to retrieve the list of high-fidelity IP addresses used by BugBug's cloud infrastructure programmatically.