# Mabl MCP for AI Agents AI Agent Connect

> Mabl MCP for AI-Powered Test Automation. This Connector lets you trigger test plans, monitor execution results in real-time, and perform deep-dive AI failure analysis directly through your AI client. It connects your Mabl account to your workspace so you can manage end-to-end testing using natural language commands.

## Overview
- **Category:** developer-tools
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_GzAfS6LnIq6mGDl04Utu0UzYyZgbblzxeJf9xvxR/ai-agent-connect
- **Tags:** test-automation, e2e-testing, quality-assurance, low-code, failure-analysis, ci-cd-integration

## Description

Mabl lets you put your end-to-end testing on autopilot through a natural conversation with your AI client. Instead of digging through complex dashboards or manually clicking through tabs to find out why a smoke test failed, you can just ask your agent to check the status of your staging environment or tell it to run a specific suite of regression tests. It handles the heavy lifting of fetching execution results, pulling down screenshots of failed steps, and explaining exactly why a test tripped up. This is a big shift for teams who want to move faster without sacrificing quality. You can find this Connector in the Vinkius catalog to get your testing suite connected to your favorite workspace. It makes the whole process of auditing environments and managing your testing grid feel like a simple chat rather than a chore. You'll be able to see your apps, environments, and test plans in one place, giving you a clear view of your quality orchestration without the usual friction of switching contexts.

## Tools

### mb.list_apps
Look up all applications on Mabl to see your web, mobile, and API testing targets. This helps you keep track of your entire testing grid.

### mb.get_app
Get full details for a specific Mabl application, including its target URLs and labels. Use this to verify specific app configurations.

### mb.list_envs
List all configured environments and their associated variables for your test runs. This ensures you have the right context for every execution.

### mb.list_plans
See all test plans, their current statuses, and the apps or environments they target. It gives you a high-level view of your run policies.

### mb.trigger_plan
Start a Mabl plan run immediately via a deployment event. Use this to kick off tests the moment a build is ready.

### mb.list_executions
Pull the latest execution results to see what passed or failed in recent runs. This is your primary way to check recent activity.

### mb.get_execution
Get specific details for a run, including durations, failure reasons, and screenshots. It provides the deep-dive data needed for debugging.

### mb.list_tests
See a list of all API tests currently configured on your Mabl account. This helps you manage your backend testing suite.

### mb.list_labels
Find all labels used to group and organize your different testing suites. Use these to filter and manage your test plans more effectively.

### mb.workspace_info
Fetch your workspace name and organization metadata from your Mabl account. This confirms your connection and account details.

## Prompt Examples

**Prompt:** 
```
Show me the status of the last 5 test executions.
```

**Response:** 
```
Here are the results from your last 5 runs:

| Run ID | Plan Name | Status | Duration |
| :--- | :--- | :--- | :--- |
| exec-101 | Smoke Test | ✅ Pass | 2m 14s |
| exec-102 | Checkout Flow | ❌ Fail | 1m 45s |
| exec-103 | API Health | ✅ Pass | 0m 45s |
| exec-104 | Smoke Test | ✅ Pass | 2m 10s |
| exec-105 | Login Flow | ❌ Fail | 1m 30s |

Would you like me to pull the failure details for exec-102?
```

**Prompt:** 
```
Trigger the 'Regression Suite' in the staging environment.
```

**Response:** 
```
I've successfully started the 'Regression Suite' run in your **Staging** environment. 

**Details:**
- **Plan:** Regression Suite
- **Environment:** Staging
- **Status:** In Progress

I'll keep an eye on this and let you know as soon as it finishes. Want me to notify you when it's done?
```

**Prompt:** 
```
What are my current testing environments?
```

**Response:** 
```
You have 3 environments configured in Mabl:

*   **Staging** (ID: env-01) - Variables loaded.
*   **Production** (ID: env-02) - Variables loaded.
*   **QA-Sandbox** (ID: env-03) - Variables loaded.

Do you want to see the specific variables for any of these?
```

## Capabilities

### Trigger test runs
Start specific test plans across different environments using a single command.

### Monitor real-time status
Get live updates on ongoing test executions and their current progress.

### Get failure screenshots
Pull visual evidence and diagnostic details for failed test steps instantly.

### Audit testing environments
View all configured environments and their associated variables for accuracy.

### Manage test labels
Organize and group your testing suites using labels for easier navigation.

## Use Cases

### Debugging a failed smoke test
A developer sees a failed build and asks their agent to show the failure details. The agent pulls the screenshot and identifies a button overlay issue.

### Verifying staging environment health
A QA engineer asks for a summary of the latest staging runs. The agent lists the pass/fail rates and identifies any lingering issues.

### Triggering regression suites
A release manager tells their agent to run the 'Checkout Regression' plan. The agent triggers the run and confirms it started successfully.

### Auditing test configurations
A DevOps lead wants to see all active environments. The agent lists every environment and its associated variables for a quick audit.

## Benefits

- No more dashboard jumping: Check the status of your latest test runs without leaving your current workspace.
- Faster debugging: Pull screenshots and specific failure reasons immediately to see exactly what broke in the UI.
- Simplified environment checks: Quickly verify your environment variables and targets to ensure tests run in the right context.
- Easier suite organization: Use labels to group and trigger specific sets of tests with natural language commands.
- Instant test execution: Start your test plans as soon as a deployment happens without manual intervention.
- Better API visibility: See all your configured API tests in one place to keep your backend quality in check.

## How It Works

The bottom line is you get a conversational interface for your entire Mabl test automation suite.

1. Subscribe to the Connector and provide your Mabl API Key.
2. Connect the Connector to your preferred AI client like Claude or Cursor.
3. Ask your agent to run tests, check results, or analyze failures.

## Frequently Asked Questions

**Can the Mabl MCP trigger test plans automatically?**
Yes, you can use your agent to start specific test plans immediately. You just need to tell your agent which plan to run and in which environment.

**How do I see screenshots of failed tests using Mabl MCP?**
When a test fails, your agent can pull the specific execution details for you. This includes the failure reason and a link to the visual screenshot for quick debugging.

**Does the Mabl MCP work with Cursor and VS Code?**
Yes, it works with any MCP-compatible client, including Cursor, Claude, and Windsurf, allowing you to manage your tests directly within your workspace.

**Can I use Mabl MCP to manage my API tests?**
Absolutely. The Connector can list all your configured API tests and help you monitor their execution results just like your web and mobile tests.

**How does Mabl MCP help with CI/CD integration?**
It simplifies the process by letting you audit environment variables and trigger test runs through natural conversation, making it easier to manage quality gates in your pipeline.

**Can I organize my Mabl tests with labels?**
Yes, you can use the Connector to list and discover all your test labels. This helps you group your suites so you can trigger specific categories of tests more easily.

**Can I see exactly why a Mabl test failed using my agent?**
Yes. Use the `mb.get_execution` tool with a specific Execution ID. Your agent will retrieve deep diagnostic information, including the failure reason, test outcomes, and visual screenshots to help you identify UI regressions instantly.

**How do I trigger a specific test plan through a conversation?**
The `mb.trigger_plan` tool allows your agent to start executions associated with a Plan ID or Label. You can also specify an optional Environment ID to target a specific stage (e.g., Staging vs Prod) for your automated tests.

**Can my agent list all available testing environments in my account?**
Absolutely. Use the `mb.list_envs` tool to identify all configured environments. Your agent will report the environment names, IDs, and any associated environment variables defined in Mabl.