# Katalon TestOps MCP

> Katalon TestOps (AI Test Management) lets you manage your entire quality pipeline using natural conversation. Connect your existing Katalon TestOps account to any AI client, and your agent handles everything from listing test runs to auditing complex software releases, letting you get immediate visibility into build health without clicking through dashboards.

## Overview
- **Category:** ship-it
- **Price:** Free
- **Tags:** test-orchestration, quality-assurance, test-automation, software-testing, ci-cd-pipeline, test-analytics

## Description

You can treat your quality assurance process like a conversation with an expert teammate. This MCP connects directly to your Katalon TestOps account, giving your AI client full control over test management and quality orchestration. Instead of jumping between tabs or writing complex scripts, you just talk to your agent. It handles listing all available projects so you know exactly what's being tested, and it lets your agent trigger immediate re-executions of specific suites when a fix is ready for verification. Need deep details? Your agent pulls detailed test outcome summaries, including pass/fail rates and error stack traces. You can even audit the entire deployment process by listing configured execution environments or tracking defined software releases. If you're used to finding these connections piecemeal, Vinkius makes it simple: connect once from any MCP-compatible client and gain access to all your critical test data in one place.

## Tools

### list_projects
Retrieves a list of all configured projects, including their names, IDs, and descriptions on Katalon TestOps.

### get_project
Fetches full details about a specific Katalon project by its ID or name.

### list_test_runs
Lists all test runs for a given project, showing their IDs, pass/fail status, total counts, and duration.

### get_test_run
Retrieves the complete details for one specific Katalon test run.

### rerun_test_run
Initiates a fresh execution of an existing test run, returning the ID of the new active session.

### list_test_results
Lists detailed results for a specific test run, showing statuses and error messages.

### get_test_result
Gets comprehensive information about a single recorded test result instance.

### list_execution_environments
Lists all configured operating system, browser, and device environments available for testing within a project.

### list_project_releases
Returns information about defined software releases, including their scheduled dates and aggregate test run metrics.

### list_project_builds
Lists all associated software builds within a project, providing identifiers and the total count of linked test runs.

## Prompt Examples

**Prompt:** 
```
List the last 5 test runs in project 'E-commerce API' (ID: 123)
```

**Response:** 
```
I've retrieved the latest 5 test runs for project 123. Highlights: Run #987 (Passed), Run #986 (Failed - 2 errors), Run #985 (Passed). Would you like to inspect the results for the failed run?
```

**Prompt:** 
```
Rerun test run ID 986
```

**Response:** 
```
Rerunning test run 986… New active execution started. New Run ID: 988. I'll let you know once the results are available. Would you like me to notify you if it fails again?
```

**Prompt:** 
```
What are the active releases defined in project 123?
```

**Response:** 
```
I've identified 2 active releases in project 123: 'Q1 Spring Update' (v1.2.0) and 'Hotfix Security' (v1.2.1). Release v1.2.0 has 45 associated test runs with a 98% pass rate. Would you like a detailed build report?
```

## Capabilities

### Orchestrate Test Runs
Tell the agent which tests failed and have it automatically trigger a re-run of that specific suite.

### Audit Software Releases
Get an overview of defined software releases, tracking aggregated test run statistics to verify build quality before deployment.

### Inspect Test Results
Retrieve detailed pass/fail rates, execution durations, and even extract application logs or visual screenshots from individual tests.

### Track Project Status
List all projects within your Katalon account to understand team assignments and suite counts across multiple repositories.

### Manage Build History
Review defined software builds, seeing their unique identifiers and how many associated test runs they contain.

## Use Cases

### Investigating an intermittent failure
A QA Engineer notices a bug only appears on specific devices. They ask their agent to list execution environments, confirming if the issue is confined to Android 12 or if it's widespread across multiple target OS settings.

### Checking release readiness quickly
A QA Manager needs a quick sign-off. They prompt their agent to list project releases, instantly seeing that the 'Q3 Beta' build has 95% pass rates but also flagging two specific critical tests that failed.

### Auditing CI/CD pipeline integrity
A DevOps Engineer wants to verify if a recent deployment impacted stable builds. They use list_project_builds to see the last ten builds and then ask the agent to get details on the most recent one, checking its associated test runs.

### Verifying a hotfix
The development team pushes an urgent fix. The engineer uses list_test_runs to identify the failing run ID and then tells the agent to rerun_test_run, immediately getting a new session ID for monitoring.

## Benefits

- You save time by getting immediate status updates. Instead of manually checking the dashboard, you can ask your agent to list test runs and instantly see which ones passed or failed.
- Debugging gets faster. If a run fails, your agent doesn't just give you 'Fail.' It pulls detailed test results so you get error messages and stack traces right away.
- You maintain full visibility over deployments. You can check the status of defined software releases using list_project_releases to ensure the build is ready before going live.
- Never forget which environment a bug appeared in. By listing execution environments, you can confirm if the issue only happens on Safari or only on Windows 10.
- Rerunning tests becomes instant. Instead of clicking through menus to re-trigger a failed test, your agent handles it using rerun_test_run and gives you the new session ID.

## How It Works

The bottom line is you get full visibility into your test suite's health by simply talking to your AI client instead of navigating complex web dashboards.

1. Subscribe to this MCP and provide your Katalon Email and API Key credentials.
2. Connect the MCP to your preferred AI client (like Claude or Cursor).
3. Ask your agent questions like, 'What are the latest 5 test runs for project X?' and receive instant, structured data.

## Frequently Asked Questions

**How do I find out what projects are available using Katalon TestOps (AI Test Management) MCP?**
You use list_projects. This tool immediately retrieves a complete list of all projects associated with your account, giving you the names and IDs needed to focus your queries.

**Can I force a test run to re-execute after a fix?**
Yes, use rerun_test_run. This tool takes an existing run ID and kicks off a brand new execution, providing you with the ID for the fresh session so you can monitor it.

**What is the difference between list_project_builds and list_project_releases?**
list_project_builds shows granular software versions (the 'how' of the build), while list_project_releases tracks major, defined product releases that contain multiple builds. Use both to get a full view.

**Does Katalon TestOps (AI Test Management) MCP show me which browsers were used?**
Yes. You can use list_execution_environments to see all configured testing environments, including the specific OS, browser types, and device distributions you've covered.

**How do I check if a build passed quality checks?**
You first use list_project_releases to find the target release. Then, your agent can pull aggregated stats from that release, showing overall pass/fail rates and associated test runs.