# Zephyr Scale MCP MCP

> Zephyr Scale (SmartBear) MCP connects your AI agent directly to your Jira quality assurance platform. You can manage entire testing workflows through conversation, pulling detailed test cases, monitoring live execution failures, and auditing entire release cycles without clicking through dozens of tabs. It gives you a single viewpoint into the health of your software.

## Overview
- **Category:** developer-tools
- **Price:** Free
- **Tags:** test-management, qa-automation, jira-integration, test-execution, software-testing, test-cycles

## Description

You're managing complex QA infrastructure, but getting a full picture means jumping between multiple dashboards—one for planning, one for environments, and another for results. This MCP lets your agent handle that coordination automatically. Need to check if a specific test case (like PROJ-T1) passed on the Staging environment? You just ask. The system pulls all that data together immediately.

It’s about building an auditable path from initial plan to final report. This MCP manages everything: listing high-level plans, checking available environments, and tracking every single test run's progress. Because this entire process flows through the secure architecture of Vinkius, your credentials pass through a zero-trust proxy; that means your keys are only used in transit, never sitting on disk. It keeps complex QA data flowing securely while giving you full visibility into what happens with every tool call.

## Tools

### get_execution
Pulls every detail about a specific test execution, including its full status report.

### get_test_case
Retrieves the complete definition and objective for any given test case.

### get_test_cycle
Shows all data related to a specific group of tests run for one release or sprint.

### list_environments
Lists every configured testing environment, such as Staging or Production, in your project.

### list_executions
Provides a list of all test executions that have occurred within the project.

### list_folders
Lists organizational folders, which can be for test cases, cycles, or plans.

### list_statuses
Shows all custom status labels used when running tests in the project.

### list_test_cases
Lists every test case available in a specific Jira project key, along with their current status.

### list_test_cycles
Provides a list of all defined test cycles for the entire Zephyr Scale project.

### list_test_plans
Lists every high-level plan that governs how testing should proceed in the project.

## Prompt Examples

**Prompt:** 
```
List all test cases in project 'PROJ'.
```

**Response:** 
```
I found 12 test cases in project PROJ. The most recent are: 1. 'User Login' (Key: PROJ-T1), 2. 'Password Reset' (Key: PROJ-T2), and 3. 'Profile Update' (Key: PROJ-T3). Which one would you like to inspect?
```

**Prompt:** 
```
What are the details for test cycle 'PROJ-R42'?
```

**Response:** 
```
Cycle 'PROJ-R42' (Regression Q1): Status: In Progress, Planned Start: 2026-03-25, Planned End: 2026-04-05. It contains 25 test executions. Current progress: 15/25 complete.
```

**Prompt:** 
```
Show me the results for execution ID '12345678'.
```

**Response:** 
```
Execution 12345678 Result: FAILED. Total steps: 5. Steps 1-3 Passed, Step 4 Failed: 'Clicking submit button returned no response'. Time taken: 45s. Would you like me to pull the linked Jira issue?
```

## Capabilities

### Discover and audit test scripts
Retrieve specific test case details, including preconditions and objectives, for deep inspection.

### Map out testing scope and structure
List all defined test plans or browse the organizational folders to understand the overall project scope.

### Monitor release progress
View group test runs (test cycles) to track how many tests passed for a specific sprint or major release.

### Track live execution results
Get real-time status updates on individual test executions, showing pass/fail metrics and step-by-step progress.

### Identify available deployment targets
List the configured environments (like Staging or Production) to ensure tests run against the correct target system.

## Use Cases

### Debugging a sudden failure
A developer notices an execution failed. Instead of manually finding the run ID and clicking into it, they ask the agent to get_execution for that ID. The agent pulls the step-by-step log right up front, pinpointing exactly which assertion failed.

### Pre-release signoff
A Release Manager needs confirmation that all critical features are covered. They ask to list_test_cycles for 'Q3 Regression' and cross-reference the results with list_environments to confirm it ran on Production data.

### Assessing project scope
A Test Manager needs to know what tests exist but haven't been run yet. They ask the agent to combine list_test_cases and list_test_plans to compare the potential coverage against current cycle results.

### Auditing setup integrity
A QA Engineer needs to confirm if a new feature was tested in all necessary environments. They use list_environments to check for 'Staging' and then query list_test_cases against that environment target.

## Benefits

- Instant status checks: Instead of navigating to list_executions, you ask for the result. The agent runs get_execution and tells you if it passed or failed immediately.
- Pinpoint failures fast: When a test fails, calling get_test_case provides the full script details—preconditions, objectives—so developers don't have to hunt through documentation.
- Scope management: You can use list_test_plans and list_test_cycles together to see if a specific release has enough coverage before you even start coding.
- Environment certainty: Need to know where the test runs? Use list_environments to confirm Staging is active, preventing deployment errors before they happen.
- Contextual discovery: The agent can guide you through the structure using list_folders, helping you find specific work items without knowing their exact key.

## How It Works

The bottom line is you stop navigating complex Jira plugins and start talking directly to your QA data.

1. Subscribe to this MCP and enter your Zephyr Scale API Token.
2. Connect your preferred AI client from that single connection point in Vinkius.
3. Ask the agent a natural language question, like 'What's the status of the regression cycle?'

## Frequently Asked Questions

**How do I find out all the active environments using list_environments?**
The agent calls list_environments and gives you a clean list of every configured target environment (Staging, Production, etc.) so you know exactly where your tests are running.

**What is the difference between list_test_cases and list_executions?**
list_test_cases shows the static definition of what a test *is*. get_execution shows the live, recorded result of that test when it actually ran.

**Can I check progress using list_test_cycles?**
Yes. list_test_cycles groups related runs for major releases or sprints and tells you how many tests passed versus the total count in that specific cycle.

**Is it safe to use my API token with this MCP?**
Yes, absolutely. When running through Vinkius, your credentials pass through a zero-trust proxy; they are used only for the data transfer and never stored on disk.

**How do I check the organizational hierarchy of my tests using list_folders?**
It lists all folders within your project, showing the complete structure. This allows you to navigate test cases, cycles, and plans by type (TEST_CASE, TEST_CYCLE, or TEST_PLAN) without manually browsing through Jira.

**What kind of detailed data does get_execution provide for a specific run?**
The tool pulls the full result set for an execution. You get step-by-step progress details, including success/failure status, time taken, and specific error messages from failed steps.

**How does list_test_plans help me understand project scope?**
It lists high-level test plans. This view helps you verify the overall testing strategy for a release or feature before any actual cycles begin running.

**What happens if I use get_test_case with an incorrect key?**
The MCP returns an error response indicating that the resource ID is invalid. This predictable failure structure lets your agent immediately signal that the test case key you provided doesn't exist in the project.

**Can I check the specific test steps for a case through the agent?**
Yes. The `get_test_case` tool allows your AI agent to retrieve the full script for any test key, providing the exact sequence of steps, test data, and expected results defined in Zephyr Scale.

**How do I see the progress of a specific test cycle via chat?**
Use the `get_test_cycle` tool. Provide the unique cycle key, and your agent will return the cycle status, planned dates, and high-level execution statistics to help you monitor testing progress.

**Is it possible to see the results of individual test runs?**
Absolutely. Using the `get_execution_details` tool, your agent can retrieve step-by-step results for any execution, including comments and execution time, helping you identify exactly where a test failed.