Parse JUnit reports, detect flaky tests, and evaluate quality gates.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "mcp-qa-toolbox" yet — see the docs or source repo.
Please parse this JUnit XML test report and summarize total tests, failures, errors, skipped tests, and failed test names.
Returns a test summary with key failure details or a list of failed cases.
Please compare test results from the last 10 runs, identify flaky tests, and show how often they occur.
Outputs suspected flaky tests and their pass/fail variability across runs.
Determine whether this build passes based on the test report and quality gate rules, and explain the decision.
Returns a pass/fail decision and explains which tests or metrics triggered failure.
Developers or DevOps teams can use it in CI to parse JUnit XML reports and return pass/fail decisions based on quality gates. This reduces manual effort when reviewing test outcomes.
When test outcomes vary across repeated runs, teams can use it to identify flaky tests. This helps prioritize fixes for tests that undermine pipeline stability.
Development teams can quickly parse JUnit XML regression reports to extract failures, errors, and skipped tests. It is useful for getting a fast view of test quality before release.
It provides three QA-focused capabilities: parsing JUnit XML reports, detecting flaky tests across multiple runs, and producing pass/fail decisions based on quality gates.
The provided information explicitly mentions support for JUnit XML reports. For other formats, see the source repository.
The available material only states that it is an MCP server and does not include installation steps, runtime dependencies, or key requirements. See the source repository for details.
Analyze test reports across runs to find regressions, fixes, and persistent failures.
MCP tool for QA workflows, testing, defect tracking, and reporting.
Run local QA checks for APIs, test cases, errors, and SLA evaluation.
Analyze repositories, plan tests, and generate Playwright end-to-end test cases.
Automate QA with generated scenarios, Playwright tests, execution, and GitHub bug reports.
Analyze and fix test failures with plain-language guidance in IDE and Slack.