Back to Browse

Zebrunner MCP Server

Developer ToolsUse Caution4.6MCP RegistryLocal
Free

Server data from the Official MCP Registry

Zebrunner analytics, reporting and safe mutations: 79 adv_* tools, 15 resources, 22 prompts.

About

Zebrunner analytics, reporting and safe mutations: 79 adv_* tools, 15 resources, 22 prompts.

Security Report

4.6
Use Caution4.6High Risk

This is a Zebrunner test management MCP server with OAuth via Okta, per-user Zebrunner credential storage, and a broad set of read and mutation tools that match its stated purpose. The visible code shows JWT verification with JWKS, a PKCE-aware flow, and HTML sanitization, with no evidence of exfiltration, hardcoded secrets, or shell injection; the truncated portions and the sanitizeRqlString helper were not fully reviewed. Key points to verify are the skipLocalPkceValidation flag, the broad default scopes when the scp claim is absent, and the 'Auto-recovered' redirect URI fallback that accepts loopback and custom-scheme callbacks. Supply chain analysis found 14 known vulnerabilities in dependencies (0 critical, 9 high severity). Package verification found 1 issue.

6 files analyzed ยท 20 issues found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

HTTP Network Access

Connects to external APIs or services over the internet.

env_vars

Check that this permission is expected for this type of plugin.

File System Read

Reads files on your machine. Normal for tools that analyze or process local data.

database

Check that this permission is expected for this type of plugin.

What You'll Need

Set these up before or after installing:

Base URL for your Zebrunner instance (e.g., https://your-instance.zebrunner.com)Optional

Environment variable: ZEBRUNNER_URL

Your Zebrunner username/loginOptional

Environment variable: ZEBRUNNER_LOGIN

Your Zebrunner API authentication token (Personal API Token from Settings โ†’ API Tokens, or refreshToken from SSO session)Required

Environment variable: ZEBRUNNER_TOKEN

API request timeout in milliseconds (default: 30000)Optional

Environment variable: TIMEOUT

Number of retry attempts for failed API requests (default: 3)Optional

Environment variable: RETRY_ATTEMPTS

Delay between retry attempts in milliseconds (default: 1000)Optional

Environment variable: RETRY_DELAY

Maximum page size for paginated API requests (default: 100, max: 1000)Optional

Environment variable: MAX_PAGE_SIZE

Default page size for paginated API requests (default: 10)Optional

Environment variable: DEFAULT_PAGE_SIZE

Enable debug logging (default: false)Optional

Environment variable: DEBUG

Enable the rules engine for test case validation (default: auto-detected from mcp-zebrunner-rules.md file)Optional

Environment variable: ENABLE_RULES_ENGINE

Enable strict URL validation for security (default: true)Optional

Environment variable: STRICT_URL_VALIDATION

Skip URL validation if it fails (less secure, more permissive) (default: false)Optional

Environment variable: SKIP_URL_VALIDATION_ON_ERROR

Enable rate limiting for API calls (default: true)Optional

Environment variable: ENABLE_RATE_LIMITING

Maximum API requests per second (default: 5, max: 100)Optional

Environment variable: MAX_REQUESTS_PER_SECOND

Allow burst of API requests (default: 10, max: 200)Optional

Environment variable: RATE_LIMITING_BURST

HTTP server port (required for StreamableHTTP mode)Optional

Environment variable: PORT

Transport mode: stdio, http, or auto (default: auto)Optional

Environment variable: MCP_TRANSPORT

Authentication mode: headers, oauth, or both (default: headers)Optional

Environment variable: MCP_AUTH_MODE

Public URL of this MCP server (for OAuth metadata)Optional

Environment variable: MCP_SERVER_URL

How to Install

Add this to your MCP configuration file:

{
  "mcpServers": {
    "mcp-zebrunner": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-zebrunner@9.4.5"
      ],
      "env": {
        "PORT": "your-port-here",
        "DEBUG": "your-debug-here",
        "TIMEOUT": "your-timeout-here",
        "RETRY_DELAY": "your-retry-delay-here",
        "MAX_PAGE_SIZE": "your-max-page-size-here",
        "MCP_AUTH_MODE": "your-mcp-auth-mode-here",
        "MCP_TRANSPORT": "your-mcp-transport-here",
        "ZEBRUNNER_URL": "your-zebrunner-url-here",
        "MCP_SERVER_URL": "your-mcp-server-url-here",
        "RETRY_ATTEMPTS": "your-retry-attempts-here",
        "ZEBRUNNER_LOGIN": "your-zebrunner-login-here",
        "ZEBRUNNER_TOKEN": "your-zebrunner-token-here",
        "DEFAULT_PAGE_SIZE": "your-default-page-size-here",
        "ENABLE_RULES_ENGINE": "your-enable-rules-engine-here",
        "RATE_LIMITING_BURST": "your-rate-limiting-burst-here",
        "ENABLE_RATE_LIMITING": "your-enable-rate-limiting-here",
        "STRICT_URL_VALIDATION": "your-strict-url-validation-here",
        "MAX_REQUESTS_PER_SECOND": "your-max-requests-per-second-here",
        "SKIP_URL_VALIDATION_ON_ERROR": "your-skip-url-validation-on-error-here"
      }
    }
  }
}

Some servers take additional arguments. See the repository for details.

Documentation

View on GitHub

From the project's GitHub README.

Advanced Zebrunner MCP Server

version

A Model Context Protocol (MCP) server that brings advanced analytics, reporting, failure forensics, and safe TCM mutations to Zebrunner. Designed to coexist with the official Zebrunner MCP (beta) โ€” see the "Dual-MCP setup" section below.

Tool naming: every tool on this server is registered under the canonical adv_<name> form (e.g. adv_create_test_case, adv_list_test_runs) so it never collides with the official Zebrunner MCP. The legacy names are kept as deprecated aliases so prompts/scripts that called the old names continue to work for now; aliases will be removed in the next major release.

๐Ÿ†• v9.4.5 โ€” Artifacts you can actually read: new read-only tools adv_list_test_artifacts, adv_get_file_metadata, adv_download_artifact (page source XML, logs, links attached by automation). Failure analysis (adv_analyze_test_failure, adv_detailed_analyze_launch_failures, adv_analyze_test_execution_video) now lists artifacts and reads the failure page source (crash/permission dialog, keyboard, locator present or missing) to refine the classification. adv_download_test_screenshot no longer fails on XML. Plus API gap fixes and a new npm run self-check regression safety net. See change-logs.md.

v9.4.4 โ€” Test-run metadata agent UX: post-mutation steering hints (discover env/config before update; import does not set badges); dual-MCP routing resource for environments vs Build/Platform; richer tool-intel for adv_manage_test_run. Builds on v9.4.3 env contract โ€” see change-logs.md.

v9.4.3 โ€” adv_prepare_jira_automation_plan + /jira-automation-plan prompt: Zebrunner suite โ†’ structured Jira plan; adv_manage_test_run Public API environment as { name } / { id }. See change-logs.md, TEST_PROMPTS.md ยง20.

v9.3.1 โ€” TCM pagination fixes: correct get_all token walks, root_suite_id subtree scoping, honest bulk metadata. See PUBLIC_API_PAGINATION.md and change-logs.md.

v9.3.0 โ€” Multi-PR / period test impact: change_batches[], /test-impact-period, extended /test-impact. See TEST_IMPACT_WORKFLOW.md and TEST_IMPACT_PR_PERIOD_DESIGN.md.

๐Ÿ†• v9.2.7 โ€” New adv_scaffold_test_case wizard (hybrid form/conversational) to author test cases from best practices with an automatic warn-only similar-case check, plus optional projectAliases in zebrunner-config.json so tools accept short names as well as Zebrunner project keys. See release notes.

๐Ÿ†• v9.2.5 โ€” adv_get_test_authoring_trend (TAM template 7) completes 22/22 dashboard widget MCP coverage. Hub tools, pass-rate views, period modes. See TEST_PROMPTS.md ยง18 and change-logs.md.

v9.2.1 โ€” LLM-visible metrics (include_call_metrics, session breakdown), compact expansion (+19 tools), format/truncation bugfixes. See Token efficiency guide and change-logs.md.

v9.2.0 โ€” Opt-in token/cost optimizations: format:'compact', detail:'summary', adv_batch_get_test_cases, report inline:false. Defaults unchanged. See change-logs.md.

v9.1.0 โ€” Launch mutations: adv_rerun_launch_failures, adv_start_launch (Jenkins Build Now), plus /relaunch-regression-failures and /feature-scoped-launch prompts. See GitHub Release v9.1.0.

๐Ÿ“– Need help with installation? Check out our Step-by-Step Install Guide for detailed setup instructions.

๐Ÿš€ Installing via npm? See our MCP NPM Installation Guide for Claude Desktop, Cursor, IntelliJ IDEA, and ChatGPT Desktop configuration.

๐Ÿ“š Test vs Test Case vs Launch? See Terminology & Glossary โ€” definitions, counting rules, and how metrics are calculated.

๐Ÿ”ฅ Why This Server

This is the Advanced Zebrunner MCP Server โ€” built to go well beyond basic test case management and help QA teams work smarter and faster with AI. Compared to the official Zebrunner MCP (beta, ~70 tools spanning Public REST + Reporting/TAM/Launcher), this server provides 76 registered adv_* tools (70 inline-regression suite + 6 handler-module tools; see tools.json) and is safe to run side-by-side with the official server:

  • Reporting & Analytics โ€” dashboards, pass-rate trends, regression stability reports, runtime efficiency analysis, bug reviews, and weekly delta tracking
  • Test Coverage & Analysis โ€” coverage gaps, automation readiness scoring, and cross-suite analysis
  • Intelligent Rules System โ€” 3-tier quality rules with 100+ automated checkpoints for test case validation and improvement
  • Screenshot & Video Analysis โ€” OCR, image processing, and video analysis powered by sharp, ffmpeg, and tesseract
  • MCP Resources & Prompts โ€” @ context injection and / workflow commands for streamlined daily operations
  • Multi-Transport & Multi-Auth โ€” STDIO, Streamable HTTP, self-service OAuth, Okta SSO, and token exchange (Modes 1โ€“5)

๐Ÿ“‘ Table of Contents

  1. ๐Ÿ”ฅ Why This Server
  2. ๐ŸŽฏ What is this tool?
  3. ๐Ÿง  Intelligent Rules System
  1. ๐Ÿ“‹ Prerequisites
  2. ๐Ÿš€ Quick Start Guide
  3. ๐Ÿ”ง Usage Methods
  1. ๐Ÿ› ๏ธ Available Tools
  1. ๐Ÿ“Ž MCP Resources & Prompts (NEW)
  1. ๐ŸŽญ Role-Specific Prompts & Workflows
  1. ๐Ÿ“– Output Formats
  2. โš™๏ธ Configuration Options
  3. ๐Ÿงช Testing Your Setup
  4. ๐Ÿ” Troubleshooting
  5. ๐ŸŽฏ Example Workflows
  6. ๐Ÿ”ง Advanced Features
  7. ๐Ÿ“š Additional Documentation
  8. ๐Ÿค Contributing
  9. ๐Ÿ“„ License
  10. ๐ŸŽ‰ You're Ready!

๐ŸŽฏ What is this tool?

This tool allows you to:

  • Retrieve test cases and test suites from Zebrunner
  • Analyze test coverage and generate test code
  • Get test execution results and launch details
  • Validate test case quality with automated checks using intelligent rules
  • Generate reports and insights from your test data
  • Improve test cases with AI-powered suggestions and automated fixes

All through natural language commands in AI assistants!

โฌ†๏ธ Back to top

๐Ÿง  Intelligent Rules System

What Makes This Tool Special

Our MCP server includes a sophisticated 3-tier rules system that transforms how you work with test cases:

๐ŸŽฏ Test Case Review Rules (test_case_review_rules.md)
  • Purpose: Core quality standards and writing guidelines
  • What it does: Defines fundamental principles for writing high-quality test cases
  • Key areas: Independence, single responsibility, comprehensive preconditions, complete step coverage
  • Used by: adv_validate_test_case and adv_improve_test_case tools
โœ… Test Case Analysis Checkpoints (test_case_analysis_checkpoints.md)
  • Purpose: Detailed validation checklist with 100+ checkpoints
  • What it does: Provides granular validation criteria for thorough test case analysis
  • Key areas: Structure validation, automation readiness, platform considerations, quality assurance
  • Used by: adv_validate_test_case for comprehensive scoring and issue detection
โš™๏ธ MCP Zebrunner Rules (mcp-zebrunner-rules.md)
  • Purpose: Technical configuration for test generation and coverage analysis
  • What it does: Defines framework detection patterns, code templates, and coverage thresholds
  • Key areas: Framework detection, test generation templates, coverage thresholds, quality standards
  • Used by: adv_generate_draft_test_by_key and adv_get_enhanced_test_coverage_with_rules tools

How the Rules Work Together

graph TD
    A[Test Case] --> B[adv_validate_test_case]
    B --> C[test_case_review_rules.md]
    B --> D[test_case_analysis_checkpoints.md]
    B --> E[Validation Result + Issues]
    
    E --> F[adv_improve_test_case]
    F --> G[AI-Powered Improvements]
    
    A --> H[adv_generate_draft_test_by_key]
    H --> I[mcp-zebrunner-rules.md]
    H --> J[Generated Test Code]
    
    A --> K[adv_get_enhanced_test_coverage_with_rules]
    K --> I
    K --> L[Coverage Analysis + Rules Validation]

Why This Matters

  1. Consistency: All team members follow the same quality standards
  2. Automation: Reduce manual review time with automated validation
  3. Learning: New team members learn best practices through AI feedback
  4. Customization: Adapt rules to your project's specific needs
  5. Continuous Improvement: AI suggests improvements based on proven patterns

Customizing Rules for Your Project

You can customize any of the three rules files:

# Copy default rules to customize
cp test_case_review_rules.md my-project-review-rules.md
cp test_case_analysis_checkpoints.md my-project-checkpoints.md
cp mcp-zebrunner-rules.md my-project-technical-rules.md

# Use custom rules in validation
"Validate test case PROJ-123 using custom rules from my-project-review-rules.md"

Example customizations:

  • Mobile projects: Add mobile-specific validation rules
  • API projects: Focus on API testing patterns and data validation
  • Different frameworks: Customize code generation templates
  • Company standards: Align with your organization's testing guidelines

โฌ†๏ธ Back to top

๐Ÿ“‹ Prerequisites

What you need to know

  • Basic command line usage (opening terminal, running commands)
  • Your Zebrunner credentials (login and API token)
  • Basic understanding of test management (test cases, test suites)

Software requirements

  • Node.js 18 or newer - Download here
  • npm (comes with Node.js)
  • Access to a Zebrunner instance with API credentials

How to check if you have Node.js

Open your terminal/command prompt and run:

node --version
npm --version

If you see version numbers, you're ready to go!

โฌ†๏ธ Back to top

๐Ÿš€ Quick Start Guide

๐Ÿ’ก Want more detailed instructions? Check out our More Detailed Step-by-step Install Guide with troubleshooting tips and platform-specific instructions.

Step 1: Get the code

Choose one of these methods:

Option A: Clone from repository (recommended)
git clone https://github.com/maksimsarychau/mcp-zebrunner.git
cd mcp-zebrunner
Option B: Download and extract

Download the project files and extract them to a folder.

Step 2: Install dependencies

npm install

Step 3: Configure your Zebrunner connection

Create a .env file in the project folder with your Zebrunner details:

# Your Zebrunner instance URL (without trailing slash)
ZEBRUNNER_URL=https://your-company.zebrunner.com/api/public/v1

# Your Zebrunner login (usually your email)
ZEBRUNNER_LOGIN=your.email@company.com

# Your Zebrunner API token (get this from your Zebrunner profile)
ZEBRUNNER_TOKEN=your_api_token_here

# Optional: Enable debug logging (default: false)
DEBUG=false

# Optional: Enable intelligent rules system (auto-detected if rules file exists)
ENABLE_RULES_ENGINE=true
How to get your Zebrunner API token:
  1. Log into your Zebrunner instance
  2. Go to your profile settings
  3. Find the "API Access" section
  4. Generate a new API token
  5. Copy the token to your .env file

Step 4: Build the project

npm run build

Step 5: Test your connection

npm run test:health

If you see "โœ… Health check completed", you're ready to go!

๐Ÿ”„ Updating to New Version

Check current version

# Check your current version
npm run version
# or manually check package.json
cat package.json | grep '"version"'

Update steps

# 1. Pull latest changes from master branch
git pull origin master

# 2. Install any new dependencies
npm install

# 3. Rebuild the project
npm run build

# 4. Test your connection (requires valid .env file)
npm run test:health

Important Notes:

  • โœ… Your .env file must be properly configured for the health check to work
  • โœ… Restart Claude Desktop/Code after updating to reload the MCP server
  • โœ… Check release notes for any breaking changes before updating

If the health check fails, verify your .env configuration and Zebrunner credentials.

โฌ†๏ธ Back to top

๐Ÿ”ง Usage Methods

Method 1: Use with Claude Desktop/Code (Recommended)

Add this configuration to your Claude Desktop or Claude Code settings. Important: You must use the full absolute path to your project folder.

{
  "mcpServers": {
    "mcp-zebrunner": {
      "command": "node",
      "args": ["/full/absolute/path/to/mcp-zebrunner/dist/server.js"],
      "env": {
        "ZEBRUNNER_URL": "https://your-company.zebrunner.com/api/public/v1",
        "ZEBRUNNER_LOGIN": "your.email@company.com",
        "ZEBRUNNER_TOKEN": "your_api_token_here",
        "DEBUG": "false",
        "ENABLE_RULES_ENGINE": "true",
        "DEFAULT_PAGE_SIZE": "100",
        "MAX_PAGE_SIZE": "100"
      }
    }
  }
}

Example paths:

  • Windows: C:\\Users\\YourName\\Projects\\mcp-zebrunner\\dist\\server.js
  • macOS/Linux: /Users/YourName/Projects/mcp-zebrunner/dist/server.js

Alternative: Command Line Integration (Claude Code)

You can also add the server using the command line:

claude mcp add mcp-zebrunner \
  --env ZEBRUNNER_URL="https://your-company.zebrunner.com/api/public/v1" \
  --env ZEBRUNNER_LOGIN="your.email@company.com" \
  --env ZEBRUNNER_TOKEN="your_api_token_here" \
  --env DEBUG="false" \
  --env ENABLE_RULES_ENGINE="true" \
  -- node /full/absolute/path/to/mcp-zebrunner/dist/server.js

Important: Replace /full/absolute/path/to/mcp-zebrunner/ with the actual full path to your project folder.

Method 2: Run as standalone server

Development mode (with auto-reload)
npm run dev
Production mode
npm start

Method 3: Smart URL-Based Analysis ๐Ÿš€

NEW in v5.4.1+: Claude can automatically detect Zebrunner URLs and analyze them with optimal settings!

Just paste a Zebrunner URL in your conversation, and Claude will automatically:

  • Parse the URL to extract project, launch, and test IDs
  • Call the appropriate analysis tool
  • Use recommended settings (videos, screenshots, AI analysis enabled)
๐Ÿ“‹ Supported URL Patterns

1. Test Analysis URLs

https://your-workspace.zebrunner.com/projects/PROJECT/automation-launches/LAUNCH_ID/tests/TEST_ID

What happens:

  • Claude automatically calls adv_analyze_test_failure
  • Extracts: projectKey, testRunId (launch ID), testId
  • Enables: includeVideo: true, analyzeScreenshotsWithAI: true, all diagnostics

Example:

User: "Analyze https://your-workspace.zebrunner.com/projects/MCP/automation-launches/120911/tests/5455386"

Claude automatically calls:
{
  projectKey: "MCP",
  testRunId: 120911,
  testId: 5455386,
  includeVideo: true,
  analyzeScreenshotsWithAI: true,
  includeLogs: true,
  includeScreenshots: true,
  analyzeSimilarFailures: true,
  screenshotAnalysisType: "detailed",
  format: "detailed"
}

2. Launch Analysis URLs

https://your-workspace.zebrunner.com/projects/PROJECT/automation-launches/LAUNCH_ID

What happens:

  • Claude automatically calls adv_detailed_analyze_launch_failures
  • Extracts: projectKey, testRunId (launch ID)
  • Enables: includeScreenshotAnalysis: true, comprehensive analysis

Example:

User: "Analyze https://your-workspace.zebrunner.com/projects/MCP/automation-launches/120911"

Claude automatically calls:
{
  projectKey: "MCP",
  testRunId: 120911,
  filterType: "without_issues",
  includeScreenshotAnalysis: true,
  screenshotAnalysisType: "detailed",
  format: "summary",
  executionMode: "sequential"
}
โœจ Advanced Usage

Override Default Settings

Claude understands natural language overrides:

User: "Analyze https://...url... but without screenshots"
โ†’ Claude sets: analyzeScreenshotsWithAI: false

User: "Analyze https://...url... in jira format"
โ†’ Claude sets: format: "jira"

User: "Quick analysis of https://...url..."
โ†’ Claude sets: format: "summary", screenshotAnalysisType: "basic"

Multiple URLs

Analyze multiple tests/launches in one request:

User: "Compare these failures:
https://your-workspace.zebrunner.com/projects/MCP/automation-launches/120911/tests/5455386
https://your-workspace.zebrunner.com/projects/MCP/automation-launches/120911/tests/5455390"

โ†’ Claude analyzes both sequentially and compares results

Cross-Workspace Support

โš ๏ธ URLs from different workspaces will show a warning but still attempt analysis:

User: "Analyze https://other-workspace.zebrunner.com/..."
โ†’ Claude warns: "URL is from 'other-workspace.zebrunner.com' but configured workspace is 'your-workspace.zebrunner.com'"
โ†’ Proceeds with analysis using available credentials
๐Ÿ“– URL Pattern Reference
ComponentExampleExtracted AsUsed In Tool
Workspaceyour-workspace.zebrunner.comValidation onlyN/A
Project KeyMCPprojectKeyAll tools
Launch ID120911testRunIdAll tools
Test ID5455386testIdadv_analyze_test_failure only
๐ŸŽฏ Why Use URL-Based Analysis?

โœ… Faster: No need to manually specify IDs
โœ… Convenient: Copy-paste URLs directly from Zebrunner UI
โœ… Optimized: Automatic use of recommended settings
โœ… Smart: Claude detects intent and adjusts parameters
โœ… Flexible: Natural language overrides work seamlessly

๐Ÿ’ก Pro Tips
  1. Direct from Zebrunner: Copy URL directly from your browser while viewing a test/launch
  2. Batch Analysis: Paste multiple URLs separated by newlines
  3. Custom Settings: Add natural language instructions to override defaults
  4. Quick Checks: URLs work great for quick "what happened here?" questions
  5. Reports: Combine with format requests: "Generate JIRA ticket for https://...url..."

โฌ†๏ธ Back to top

๐Ÿค Dual-MCP setup (official zebrunner + Advanced)

Zebrunner now offers an official hosted MCP (beta) at https://{workspace}.zebrunner.com/api/mcp. It is safe to run both servers in the same Cursor / Claude session: every tool on this server is exposed under the adv_<name> prefix, so it never collides with the official tools.

Example .cursor/mcp.json:

{
  "mcpServers": {
    "zebrunner": {
      "url": "https://your-workspace.zebrunner.com/api/mcp",
      "headers": {
        "X-Zebrunner-Username": "your.name@company.com",
        "X-Zebrunner-Api-Token": "<your-zebrunner-api-token>"
      }
    },
    "mcp-zebrunner": {
      "command": "npx",
      "args": ["-y", "mcp-zebrunner"],
      "env": {
        "ZEBRUNNER_URL": "https://your-workspace.zebrunner.com/api/public/v1",
        "ZEBRUNNER_LOGIN": "your.name@company.com",
        "ZEBRUNNER_TOKEN": "<your-zebrunner-api-token>"
      }
    }
  }
}

Rule of thumb when both are connected:

Use zebrunner (official) forUse mcp-zebrunner (Advanced) for
list_projects, shared steps, test run replace/close, custom field createFailure forensics, runtime + flakiness analytics
Server-side filter DSL; file upload + screenshot content in triageReporting, dashboards, regression analyzers
Bulk launch/test comments, issue linking, launcher/preset CRUD, launch_testsPreview/confirm TCM mutations; Jenkins Build Now / rerun failures

Inside chat, ask adv_about_mcp_tools with mode: "routing" or open the zebrunner://mcp-routing resource for the full live-generated diff and routing table.

๐Ÿ› ๏ธ Available Tools

Once connected, you can use these tools through natural language in your AI assistant. This section highlights all 79 adv_* tools (see tools.json) organized by category. For the complete catalog with natural-language examples for every tool, see TOOLS_CATALOG.md.

Dashboard widgets: All 22 Zebrunner dashboard templates have MCP coverage (v9.2.5). See docs/TEST_PROMPTS.md ยง18 for example prompts and npm run test:api verification.

Token-efficient reads

Large TCM exports can consume significant context. Use these opt-in parameters (defaults stay backward-compatible). Full guide: docs/TOKEN_EFFICIENCY.md.

TechniqueExampleWhen to use
format: 'compact'adv_get_all_tcm_test_cases_by_project with format:'compact'Minified JSON (~22% smaller than pretty json)
detail: 'summary'adv_get_test_cases_by_suite_smart with detail:'summary'After filtering โ€” returns id, key, title, priority, automationState, webUrl only
adv_batch_get_test_cases{ case_keys: ["MCP-1","MCP-2"], detail:"summary", format:"compact" }Fetch a shortlist without N round-trips
adv_generate_report inline: falseWrites HTML/PNG to disk, returns pathsHuge dashboards in chat clients
count_only: trueAny bulk TCM/suite readMetrics without payload
Env flags (off)MCP_COMPACT_DEFAULTS=true, MCP_SUMMARY_DEFAULTS=trueServer-wide default flips after eval passes

Workflow: list/filter with detail:'summary' + format:'compact' โ†’ adv_get_test_case_by_key for full body (steps, preconditions) before create/update.

Example prompts for your assistant:

  • "List test cases in project MCP with summary detail and compact JSON."
  • "Fetch MCP-1 and MCP-2 in one batch call with summary and compact format."
  • "Generate a quality dashboard for MCP with inline false โ€” save to disk."

Tool naming: All tools are exposed as adv_<name> (e.g. adv_get_test_case_by_key). Use these names in prompts, scripts, and when both the official and Advanced MCP are connected. Legacy short names (get_test_case_by_key, etc.) are deprecated and only registered when ZEBRUNNER_REGISTER_LEGACY_ALIASES=true.

๐Ÿ“‹ Test Case Management

Core Test Case Tools
ToolDescriptionExample UsageBest For
adv_get_test_case_by_keyGet detailed test case information"Get test case MCP-123 details"All roles
adv_batch_get_test_casesFetch multiple cases by key (partial success)"Get MCP-1 and MCP-2 with summary detail"All roles
adv_get_test_cases_advancedAdvanced filtering with automation states, dates"Get test cases created after 2025-01-01 with automation state 'Manual'"QA, SDETs
adv_get_test_cases_by_automation_stateFilter by specific automation states"Show me all 'Not Automated' test cases in project MCP"SDETs, Managers
adv_get_test_case_by_titleSearch test cases by title (partial match)"Find test cases with title containing 'login functionality'"All roles
adv_get_test_case_by_filterAdvanced filtering by suite, dates, priority, automation state"Get test cases from suite 491 created after 2025-01-01 with high priority"QA, Managers
adv_get_automation_statesList available automation states"What automation states are available for project MCP?"All roles
adv_get_automation_prioritiesList available priorities with IDs"Show me all priority levels for project MCP"All roles
Batch Test Case Operations
ToolDescriptionExample UsageBest For
adv_get_all_tcm_test_cases_by_projectGet ALL test cases (handles pagination)"Get all test cases for project MCP"Managers, Leads
adv_get_all_tcm_test_cases_with_root_suite_idAll test cases with hierarchy info"Get all test cases with their root suite information"Analysts
adv_get_test_cases_by_suite_smartSmart suite test case retrieval with root/child auto-detection"Get test cases from suite 18824 in project MCP using smart mode"QA, Analysts
Test Case Change History

Most test case tools support optional change history enrichment โ€” fetching the audit log of modifications for each test case. This is useful for understanding when steps were changed, when automation state transitioned, or when a test case was deprecated.

ParameterTypeDefaultDescription
include_historybooleanfalseAttach a history array of parsed change entries to each test case
history_filtersteps_onlyevents_onlyall
history_limitnumber (1โ€“100)20Max history entries per test case

Supported on: adv_get_test_case_by_key, adv_get_test_cases_advanced, adv_get_test_cases_by_automation_state, adv_get_test_case_by_title, adv_get_test_case_by_filter, adv_get_all_tcm_test_cases_by_project, adv_get_test_cases_by_suite_smart

Example prompts:

  • "Get test case MCP-29 with change history" โ†’ sets include_history=true
  • "Show me MCP-29 history, events only" โ†’ sets include_history=true, history_filter='events_only'
  • "Get all automated test cases with their last 5 changes" โ†’ sets include_history=true, history_limit=5

Detected events: became_automated, became_manual, became_deprecated, became_undeprecated, steps_changed, preconditions_changed, postconditions_changed, and dynamically generated became_<state_name> for any project-specific automation state.

๐ŸŒณ Test Suite Hierarchy & Organization

Suite Management
ToolDescriptionExample UsageBest For
adv_list_test_suitesList suites with pagination"List test suites for project MCP"All roles
adv_get_suite_hierarchyHierarchical tree view"Show me the hierarchy of test suites with depth 3"Managers, QA
adv_get_root_suitesGet top-level suites"Show me all root suites for project MCP"Managers
adv_get_all_subsuitesGet all child suites"Get all subsuites from root suite 18697"QA, Analysts
Suite Analysis Tools
ToolDescriptionExample UsageBest For
adv_get_tcm_suite_by_idGet suite by ID (simple: fast direct API, full: hierarchy-enriched)"Show me suite 20421 in project MCP"All roles
adv_get_tcm_test_suites_by_projectComprehensive suite listing"Get all suites for project MCP with hierarchy"Managers
adv_get_all_tcm_test_case_suites_by_projectGet all TCM test case suites with pagination"Get all TCM test case suites for project MCP"Managers, Analysts
adv_get_root_id_by_suite_idFind root suite for any suite"What's the root suite for suite 12345?"Analysts

๐Ÿ”ง Mutation Tools

Safety Model: Every mutation tool follows a two-call confirmation gate. The first call returns a preview; only after user approval should confirm: true be passed to execute the mutation. All mutations are audit-logged to ~/.mcp-zebrunner-audit.jsonl. Use dry_run: true for raw payload inspection.

Next-step steering (v7.2.2): After every successful mutation, the server appends a Tip: block guiding the LLM to the most useful next action (e.g., "validate quality", "publish the draft", "populate the test run"). Hints are conditional -- they are suppressed when redundant. For example, the quality-check hint is omitted if review: true was already used. Created test cases are always forced to draft=true, and the hint always reminds the LLM to publish via adv_update_test_case. This approach is inspired by the Strands Agents steering pattern and delivers just-in-time guidance without bloating system prompts.

Suite Mutations
ToolDescriptionExample UsageBest For
adv_create_test_suiteCreate a new Test Suite"Create root suite 'Payments' in project MCP"QA, Managers
adv_update_test_suiteUpdate an existing Test Suite (full PUT)"Rename suite 18697 to 'Login & Registration'"QA, Managers
Test Case Mutations
ToolDescriptionExample UsageBest For
adv_create_test_caseCreate a new Test Case with runtime validation of priorities, automation states, and custom fields. Accepts {file_path} in attachments. Optional source_case_key to pre-populate from an existing test case."Create test case 'Verify login' in suite 17470 for project MCP"QA, SDETs
adv_update_test_casePartially update a Test Case by ID or key (PATCH). Accepts {file_path} in attachments for local file upload."Attach /Users/me/screenshot.png to test case MCP-42"QA, SDETs

๐Ÿ” Test Coverage & Analysis

Test Impact (PR / code changes) (v9.2.8)
ToolDescriptionExample UsageBest For
adv_analyze_test_impactRank Zebrunner cases affected by code changes from compact semantic context"Analyze test impact for diary edit + serving size changes on PROJ2"Developers, SDETs

Use the /test-impact MCP prompt (optional pr_url) for guided workflow. See TEST_IMPACT_WORKFLOW.md. Configure repositoryProjectMap via .env.example.

Coverage Analysis
ToolDescriptionExample UsageBest For
adv_get_test_coverage_by_test_case_steps_by_keyAnalyze implementation coverage"Analyze coverage for MCP-123 against this code: [paste code]"Developers, SDETs
adv_get_enhanced_test_coverage_with_rulesRules-based coverage analysis"Enhanced coverage analysis for MCP-123 with framework detection"SDETs, Leads
Duplicate Analysis

Documentation truncated โ€” see the full README on GitHub.

Reviews

No reviews yet

Be the first to review this server!