Xray Test Management MCP. Analyze and audit all your quality assurance results.

Q: How do I see every available test case using listxraytests?

Run listxraytests. This tool retrieves a complete roster of all test cases in your project, giving you their full names and unique keys. It's the fastest way to get an inventory.

Q: What is the difference between listtestexecutions and getexecutiondetails?

listtestexecutions gives you a summary of many runs (e.g., '10 tests ran, 2 failed'). getexecutiondetails, however, takes one specific run ID and provides the granular data for every single step taken during that test.

Q: Can I see if all my required tests are in a plan using gettestplandetails?

Yes. Running gettestplandetails shows you the full scope of the plan, including how many tests were expected and which ones have been executed or still need attention.

Q: If a test fails, what tool should I use to find out why?

You'll want getexecutiondetails. This tool is designed for deep dives into failures. It tells you exactly which step failed and provides the specific error message or status code.

Q: If I need to verify environment settings or field mappings, which tool should I use? (getxraysettings)

You use getxraysettings to pull the project's configuration. This confirms your agent knows exactly what status codes and environments your QA workflow uses. It prevents mapping errors when you analyze results.

Q: I need to track a single test case across multiple cycles; is getindividualtestruns the right tool? (getindividualtestruns)

Yes, use getindividualtestruns. This pulls every instance of that specific test running over time. It gives you a focused history, which is better than scrolling through general execution logs.

Q: How do I see how tests are grouped for regression or functional testing? (listtestsets)

listtestsets shows all defined groups of tests. This helps you understand the structure of your test library before running a plan, letting you focus on specific functional areas.

Q: What kind of detailed metadata does gettestdetails provide for a single test case? (gettestdetails)

gettestdetails provides the comprehensive data layer. Beyond just the title, you'll get key identifiers and prerequisites needed to fully understand that specific test step.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Just plug in your AI agents and start using Vinkius.

Xray Test Management connects your AI client directly to Xray's QA data. You can list all test cases, track entire execution runs, check plan progress, and drill down to find which specific step failed or passed in a test run.

It lets you analyze complex quality assurance results using simple chat commands.

What your AI agents can do

Get execution details

Retrieves detailed results for one specific instance of a test run.

Get individual test runs

Gets all individual instances where a single, defined test case was executed.

Get test details

Pulls full information about a specific Xray test case definition.

+ 6 more capabilities included

List all available test cases

You can pull a complete, alphabetized list of every test case configured in the Xray project.

Track overall plan status and progress

Check the scope and current completion percentage for any defined test plan.

Review granular execution steps

You get detailed results—including error codes or success messages—for a single, specific test run instance.

View historical failure patterns

The server provides the full run history for one test key across multiple execution cycles.

Identify functional groups of tests

You can list out all defined test sets, which show how individual test cases are grouped together.

Ask AI about this MCP

Ask ChatGPT

Ask Claude

Ask Perplexity

Supported MCP Clients

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

+ other MCP clients

Free for Subscribers

Retrieves a complete list of every available test case in the Xray project.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with Xray (Test Management), then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 4,700+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

What you can do with this MCP connector

This server connects your AI client directly to Xray's entire QA data set. You can analyze complex quality assurance results using simple chat commands; it’s like having a dedicated QA operations analyst right there in your agent.

To start, you can pull a complete list of every test case configured in the project by running list_xray_tests, and you'll see all their unique keys. You also get full information about any specific test case definition using get_test_details. If you need to know how tests are organized into functional groups, use list_test_sets to view every defined set that combines multiple individual test cases.

When it comes to planning, the system tracks everything. You can get a list of all currently configured test plans using list_test_plans, and for any specific plan you select, get_test_plan_details gives you its full scope and current progress percentage. To see every historical recording of tests that have run across the whole project, call list_test_executions.

This list tracks all recorded test execution records.

For deep dives into history, you’ve got options for tracking failures or successes over time. If you want to view the complete run history for a single defined test key across multiple cycles—which is great for spotting flaky tests—you use get_individual_test_runs. For any single, specific instance of a test running, get_execution_details pulls detailed results, letting you see exactly which steps passed, failed, or hit an error code.

Furthermore, to check the project's environment settings and internal field mappings in Xray itself, run get_xray_settings.

If you need to know what kinds of test sets exist beyond just listing them, remember that while list_test_sets shows the groups, list_test_executions tracks all historical runs. You can use your agent to list every defined plan with list_test_plans, and then check out the specific scope and status for any one of those plans using get_test_plan_details.

This entire connection lets you query everything from the master test inventory retrieved by list_xray_tests to the granular failure details available via get_execution_details. You won't have to manually filter through huge Jira lists again; your AI client handles all that heavy lifting.

How Xray Test Management MCP Works

1 First, subscribe to the Xray server and provide your required Client ID and Secret.
2 Your AI agent then uses natural conversation to call specific tools (like list_test_executions) based on your request.
3 The tool runs the query against the Xray API and sends back structured data—a list, a status report, or failure details—to your chat window.

The bottom line is: you ask your AI client a question about QA results, and it handles all the complex API calls to give you one clean answer.

Who Is Xray Test Management MCP For?

This server is for anyone who gets frustrated having to manually click through dashboards or run five separate reports just to know if a release candidate is stable. It targets QA Engineers, Test Managers, Product Owners, and Developers who need instant, deep access to testing data without writing code.

QA Engineer

Uses get_execution_details or list_test_executions to immediately find the specific step that failed during a test run and pull the associated error logs.

Test Manager

Calls list_test_sets and list_test_plans to verify if all required functional groups are included in the current testing scope before sign-off.

Product Owner

Uses this server to quickly check the latest execution status for a high-priority feature set, ensuring quality standards are met before confirming release readiness.

Developer

Looks up test steps and preconditions using get_test_details when a test fails in production, speeding up the initial debugging process.

What Changes When You Connect

Audit Flaky Tests: Use get_individual_test_runs to pull the entire run history for a single test key, letting you see if it's failing randomly across multiple cycles. This is critical for stability checks.
Pinpoint Failure Steps: Don't just get a 'Failure Count.' Call get_execution_details and find the exact step in the code that failed—plus any error messages returned.
Verify Scope Coverage: Need to know if all functional areas were tested? Run list_test_sets to verify how individual tests are grouped into logical regression or feature sets.
Check Release Readiness: Use get_test_plan_details to see the overall progress against a major release plan. You get the percentage complete and the status breakdown (Passed/Failed/Pending).
Validate Project Setup: Before starting, run get_xray_settings. This confirms that your AI client's context aligns with how Xray has mapped project fields and environments.
Find Test Keys Fast: Instead of clicking through Jira filters, use list_xray_tests to get a simple list of all available test keys (e.g., TST-101). This is the fastest way to start an investigation.

Real-World Use Cases

Debugging a production bug

A developer finds a reported issue and needs to replicate it in testing. Instead of manually searching, they ask their agent: 'Show me the results for TST-42.' The agent uses get_execution_details and returns the specific step that failed, telling them if it was a 500 error or a missing precondition. Debugging starts immediately.

Pre-release quality gate check

A Product Owner needs to know if 'v2.4' is ready for launch. They ask the agent to summarize the plan status. The agent uses get_test_plan_details and responds with a clear metric: 'The plan is 75% complete, with 5 failures remaining.' This gives them the necessary data point without manual report generation.

Identifying flaky tests

A QA Engineer suspects Test A fails randomly. They instruct their agent to check its history. The agent runs get_individual_test_runs and shows a timeline, proving that the test passed three times but failed on the fifth run, confirming it's unreliable.

Checking functional grouping

The Test Manager needs to confirm if all payment-related tests are included in the regression cycle. They ask the agent to list 'Payment feature tests.' The agent uses list_test_sets and provides a clean, organized list of test keys belonging to that specific set.

The Tradeoffs

Manual Jira Filtering

A user spends 20 minutes in the Jira UI, clicking through tabs: 'Test Cases' -> 'Filter by Project X' -> 'Sort by Date' to find a result from last week. This is slow and error-prone.

→ You ask your agent to list all test executions for that period. The agent uses list_test_executions, which returns the necessary data points instantly, skipping all manual clicking.

Guessing Test Keys

A developer remembers a test key was TST-XXX but can't recall the exact number. They waste time checking documentation or asking colleagues.

→ Ask your agent to run list_xray_tests. It provides the full list of keys, letting you confirm the correct ID in seconds.

Ignoring Test Plans

A team assumes all tests are covered, but forgets to check if a new feature requires an update to the formal test plan. They move forward with untested code.

→ Always check get_test_plan_details. This verifies that the testing scope is officially defined and tracked before any deployment.

When It Fits, When It Doesn't

Use this server if your primary need is querying, auditing, or tracking results from Xray test runs. If you just want to know which tests exist, use list_xray_tests. If you only care about the general status of a plan without needing step-by-step failures, checking list_test_plans might be enough.

However, if you need deep investigative work—like finding out why a test failed or tracking its history over time—you must use this server. Don't use it if your goal is simply bug logging; that’s for Jira issues. This tool handles the structured testing data itself.

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Xray (Test Management). All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

How we secure it →

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This server provides 9 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.

Available Capabilities

get_execution_details get_individual_test_runs get_test_details get_test_plan_details get_xray_settings list_test_executions list_test_plans list_test_sets list_xray_tests

Finding specific test results shouldn't take 20 minutes of dashboard clicking.

Right now, finding out what happened with a single failed test requires a tedious drill-down process. You start in the main Jira board view, filter by date, then you have to click into the specific execution record. Then, if that's not enough, you might need to navigate to the 'Steps' tab just to see which step threw the error and why.

With this MCP server, you just ask your agent: 'What were the results for test TST-42 on Monday?' The agent runs `get_execution_details` and returns a clean summary right away. You get the actionable data—the failure status and error message—in one simple response.

Xray Test Management MCP Server: Audit test run history with confidence.

Manually auditing a test case's reliability is brutal. You have to check multiple reports across different dates and cycles to see if the failure was temporary or persistent. This requires cross-referencing data from at least three separate views in Jira.

Now, you simply ask your agent to track the history for that one key. The agent uses `get_individual_test_runs` and compiles a complete timeline of successes and failures across all cycles. You instantly identify if it's just flaky or fundamentally broken.

Common Questions About Xray Test Management MCP

How do I see every available test case using list_xray_tests? +

Run list_xray_tests. This tool retrieves a complete roster of all test cases in your project, giving you their full names and unique keys. It's the fastest way to get an inventory.

What is the difference between list_test_executions and get_execution_details? +

list_test_executions gives you a summary of many runs (e.g., '10 tests ran, 2 failed'). get_execution_details, however, takes one specific run ID and provides the granular data for every single step taken during that test.

Can I see if all my required tests are in a plan using get_test_plan_details? +

Yes. Running get_test_plan_details shows you the full scope of the plan, including how many tests were expected and which ones have been executed or still need attention.

If a test fails, what tool should I use to find out why? +

You'll want get_execution_details. This tool is designed for deep dives into failures. It tells you exactly which step failed and provides the specific error message or status code.

If I need to verify environment settings or field mappings, which tool should I use? (get_xray_settings) +

You use get_xray_settings to pull the project's configuration. This confirms your agent knows exactly what status codes and environments your QA workflow uses. It prevents mapping errors when you analyze results.

I need to track a single test case across multiple cycles; is `get_individual_test_runs` the right tool? (get_individual_test_runs) +

Yes, use get_individual_test_runs. This pulls every instance of that specific test running over time. It gives you a focused history, which is better than scrolling through general execution logs.

How do I see how tests are grouped for regression or functional testing? (list_test_sets) +

list_test_sets shows all defined groups of tests. This helps you understand the structure of your test library before running a plan, letting you focus on specific functional areas.

What kind of detailed metadata does `get_test_details` provide for a single test case? (get_test_details) +

get_test_details provides the comprehensive data layer. Beyond just the title, you'll get key identifiers and prerequisites needed to fully understand that specific test step.

Can I check the specific steps of a test case through the agent? +

Yes. The get_test_details tool allows your AI agent to retrieve the full technical metadata for any test key, including the defined test steps, preconditions, and any linked requirement issues.

How do I find out which tests failed in a recent execution? +

You can use the get_execution_details tool. Provide the unique execution key, and your agent will return a granular breakdown of the results, highlighting tests that failed or were aborted.

Is it possible to see the progress of a test plan via chat? +

Absolutely. Using the get_test_plan_details tool, your agent can retrieve the scope and real-time progress metrics for any plan ID, helping you monitor overall QA coverage for a release.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript