Advanced Zebrunner MCP Server

Read from the package source without running it. The installed server may list more.

• about_mcp_tools

  📚 Discover Advanced Zebrunner MCP Server capabilities: tools summary/detail, prompts catalog (/commands), resources catalog (@data), or dual-MCP routing guidance. Use mode='summary' for a full overview, or mode='routing' for the table that explains when to prefer the official `zebrunner` MCP vs this server when both are connected.

• aggregate_test_cases_by_feature

  🔍 Find ALL test cases related to a specific feature across the project.

• analyze_regression_runtime

  📊 Analyze Regression Runtime Efficiency: collects per-launch elapsed time, attempt/re-run breakdown, per-test duration classification (Short / Medium / Long with configurable thresholds), Average Runtime per Test, and Weighted Runtime Index. Supports baseline comparison with a previous milestone or build to track deviation (%). Targets one project per call; aggregate across teams by calling multi

• analyze_screenshot

  🔍 Analyze test screenshot with OCR and visual analysis - returns image to Claude Vision for detailed analysis

• analyze_test_cases_duplicates

  🔍 Analyze test cases for duplicates and group similar ones by step similarity (80-90%)

• analyze_test_cases_duplicates_semantic

  🧠 Advanced semantic duplicate analysis using LLM-powered step clustering and two-phase analysis

• analyze_test_execution_video

  🎬 Download and analyze test execution video with Claude Vision - extracts frames, compares with test case, and predicts if failure is bug or test issue. NEW: Analysis depth modes (quick/standard/detailed), parallel frame extraction, similar failures search, and historical trends analysis!

• analyze_test_failure

  🔍 Deep forensic analysis of failed test including logs, screenshots, error classification, and similar failures. 💡 NEW: Compare with last passed execution to see what changed! 💡 TIP: Can be auto-invoked from Zebrunner test URLs like: https://workspace.zebrunner.com/projects/PROJECT/automation-launches/LAUNCH_ID/tests/TEST_ID

• batch_get_test_cases

  📦 Fetch multiple test cases by key in one call (partial success).

• create_test_casewrite action
• create_test_suitewrite action

  🔧 (Beta) Create a new Test Suite in a Zebrunner project. Requires Engineer role or higher in the target project. Suites can be nested at any depth by providing parent_suite_id. Omit parent_suite_id to create a root-level suite. TWO-STEP FLOW: 1) Call with all fields (without confirm) to get a preview + confirmation_token. 2) After user approval, call with ONLY confirm: true and the confirmation_t

• detailed_analyze_launch_failures

  🚀 Analyze failed tests WITHOUT linked issues in a launch with grouping, statistics, and recommendations. Automatically analyzes all tests if ≤10, otherwise first 10 (use offset/limit for more). Use filterType: 'all' to include tests with issues. Supports pagination and screenshot analysis. **NEW:** Jira format with smart grouping - creates combined tickets for similar errors! 💡 TIP: Can be auto-

• download_test_screenshot

  📸 Download test screenshot with authentication from Zebrunner

• find_flaky_tests

  🔍 Find flaky tests across launches using a 3-phase approach: (1) cross-launch flip-flop analysis of automated tests, (2) manual-only test case scan via TCM execution history, (3) dual-perspective enrichment of top automated flaky tests with TCM data. Detects tests that oscillate between PASSED/FAILED across multiple launches within a time window.

• generate_draft_test_by_key

  🧪 Generate draft test code from Zebrunner test case with intelligent framework detection

• generate_report

  📊 (Beta) Universal report generator. Supports 6 report types: quality_dashboard (HTML+Markdown with 6 panels), coverage (per-suite test coverage table), pass_rate (per-platform with targets), runtime_efficiency (with delta vs previous milestone), executive_dashboard (standup-ready combined report), release_readiness (Go/No-Go assessment). Can generate single or multiple reports per call.

• generate_weekly_regression_stability_report

  📌 Generate weekly regression stability report with pass rates, WoW deltas, and Jira-ready output

• get_all_launches_for_project

  📋 List individual launch executions for a project with pagination. Returns launch names, statuses, and timestamps. Use this to browse or list launches, NOT for aggregated results/pass rates (use adv_get_platform_results_by_period for that).

• get_all_launches_with_filter

  🔍 Search and filter individual launch executions by milestone, build number, or launch name. Returns matching launches with statuses. Use this to find specific launches, NOT for aggregated results/pass rates (use adv_get_platform_results_by_period for that).

• get_all_subsuites

  📋 Get all subsuites from a root suite as flat list with pagination

• get_all_tcm_test_case_suites_by_project

  📋 Get ALL TCM test case suites by project using comprehensive pagination

• get_all_tcm_test_cases_by_project

  📋 Get ALL TCM test cases by project using comprehensive pagination

• get_all_tcm_test_cases_with_root_suite_id

  🌳 Get ALL TCM test cases enriched with root suite ID information

• get_automation_priorities

  🎯 Get available priorities for a project (names and IDs)

• get_automation_states

  🔧 Get available automation states for a project (names and IDs)

• get_available_projects

  🏗️ Discover available projects with their keys and IDs for dynamic project selection

• get_bug_failure_info

  🔬 Get comprehensive failure information including failure summary and detailed test runs (SQL widgets, templateId: 6 & 10)

• get_bug_review

  🔍 Get detailed bug review with failures, defects, reproduction dates, and optional automatic failure detail fetching (SQL widget, templateId: 9)

• get_enhanced_test_coverage_with_rules

  🔍 Enhanced test coverage analysis with configurable rules validation and quality scoring

• get_launch_details

  🚀 Get comprehensive launch details including test sessions (uses new reporting API with enhanced authentication)

• get_launch_summary

  📋 Get quick launch summary without detailed test sessions (uses new reporting API)

• get_launch_test_summary

  📊 Get lightweight launch test summary with statistics (auto-paginated, token-optimized)

• get_platform_results_by_period

  📊 Get aggregated test results, pass rate, and statistics for a project over a time period (last 7 days, last 30 days, etc.). Returns total passed/failed/skipped/aborted counts and pass rate percentage. Use this when asked for 'results', 'pass rate', 'test statistics', 'how many passed/failed', or 'results for last N days'. Accepts any Zebrunner project key (e.g. 'DEF', 'MCP') or aliases (web/andr

• get_project_milestones

  🎯 Get available milestones for a project with pagination and filtering

• get_root_id_by_suite_id

  🔍 Get root suite ID for a specific suite ID

• get_root_suites

  🌳 Get root suites (suites with no parent) from project

• get_suite_hierarchy

  🌳 Get hierarchical test suite tree with configurable depth

• get_tcm_suite_by_id

  🔍 Get test suite by its numeric ID. This is the primary tool for any "show me suite", "get suite by ID", or "find suite" request. Supports two modes: - simple (default): Fast direct API call. Returns suite fields (id, title, description, parentSuiteId, relativePosition). Best for quick lookups. - full: Fetches all project suites and enriches with hierarchy (rootSuiteId, parent chain, clickable li

• get_tcm_test_suites_by_project

  📋 Get TCM test suites by project with pagination (Java methodology)

• get_test_case_by_filter

  🔍 Get test cases using advanced filtering options with exact matching

• get_test_case_by_key

  🔍 Get detailed test case by key or numeric ID. Accepts: • Test case key: 'MCP-29', 'MCP-2' • Numeric ID: '86280' (requires project_key) • From Zebrunner URL: extract project_key and caseId from URLs like https://example.zebrunner.com/projects/MCP/test-cases?caseId=86280 → project_key='MCP', case_key='86280' Default format is 'json' which exposes all raw field values. Use 'json' when using this to

• get_test_case_by_title

  🔍 Get test cases by title using partial match search with pagination support

• get_test_cases_advanced

  📊 Advanced test case retrieval with filtering and pagination (✨ Enhanced with automation state and date filtering)

• get_test_cases_by_automation_state

  🤖 Get test cases filtered by automation state with token-based pagination (💡 Use adv_get_automation_states to see available states). Call repeatedly with page_token to paginate through all results.

• get_test_cases_by_suite_smart

  🧠 Smart test case retrieval by suite ID - automatically detects if suite is root suite and uses appropriate filtering with enhanced pagination

• get_test_coverage_by_test_case_steps_by_key

  🔍 Analyze test case coverage against actual implementation with recommendations

• get_test_execution_history

  📊 Get execution history for a test across multiple launches - shows pass/fail history, last passed execution, and pass rate

• get_test_run_by_idwrite action

  🔍 Get detailed Test Run information by ID from Public API

• get_test_run_configuration_groupswrite action

  Get list of Configuration Groups and their Options for a project. These are used to configure Test Runs.

• get_test_run_result_statuseswrite action

  Get list of Result Statuses configured for a project. These statuses are used when assigning results to Test Cases.

• get_top_bugs

  🐞 Top N most frequent defects with optional issue links (SQL widget, templateId: 4)

• import_launch_results_to_test_runwrite action
• improve_test_case

  🔧 Analyze and improve a test case with detailed suggestions and optional automatic fixes

• list_test_run_test_caseswrite action

  📝 List all Test Cases in a Test Run from Public API

• list_test_runs

  🏃 List Test Runs from Public API with advanced filtering

• list_test_suites

  📋 List test suites for a project (✅ Verified Working)

• manage_test_runwrite action
• regression_results_analyzer

  📊 Analyze regression test results for a milestone or build: test run overview, new/top bugs, bugs per suite, and slowest tests. Accepts milestone name and/or build number to find all TCM test runs.

• rerun_launch_failures
• start_launch

  🚀 (Beta) Start a new automation launch via Zebrunner "Build now" (Reporting API job/parameters + job:build). IMPORTANT: … … Resolves a template launch by launch_id, launch name query, and/or suite_path, fetches live job parameters, merges your overrides (build, locale, test_run_rules, or parameters map), and triggers CI. Use build: ".*" for latest build. Discover parameters first via adv_get_laun

• test_reporting_connection

  🔌 Test connection to Zebrunner Reporting API with new authentication

• update_test_casewrite action
• update_test_suitewrite action

  🔧 (Beta) Update an existing Test Suite by its numeric ID. Requires Engineer role or higher in the target project. ⚠️ IMPORTANT: This uses PUT (full replacement). You must always provide 'title' even if you only want to change another field. Setting parent_suite_id to null or omitting it will promote the suite to root level. TWO-STEP FLOW: 1) Call with all fields (without confirm) to get a preview

• validate_test_case

  🔍 Validate a test case against quality standards and best practices (Dynamic Rules Support + Improvement)

• Code scan96 source files scanned; 96 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitystatic API keys via environment variables6/15
• Maintenancelast push 10 days ago15/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Safety score

83/100

higher than 65% of 48,255 servers

Tools

64

the typical server has 7

Tools that change things

16%

typical: 0%. Fewer write tools means less an agent can break

GitHub stars

5

more than 83% of 28,688 servers

Downloads a week

536

more than 89% of 12,191 servers with a package

Advanced Zebrunner MCP Server: common questions

Is Advanced Zebrunner MCP Server safe?

Mostly: it is graded B (83/100). Read the Advanced Zebrunner MCP Server safety report

How do I install Advanced Zebrunner MCP Server?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does Advanced Zebrunner MCP Server need an API key?

Yes. The registry entry asks for ZEBRUNNER_TOKEN.

Is Advanced Zebrunner MCP Server maintained?

The last commit was 49 days ago (2026-09-16). The latest release is v9.2.1.

How does Advanced Zebrunner MCP Server compare with other MCP servers?

safety score 83/100 (higher than 65% of 48,255 servers); tools 64 (the typical server has 7); tools that change things 16% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.