Skip to main content
Glama

Zebrunner MCP Server

analyze_test_cases_duplicates_semantic

Identify duplicate test cases using semantic analysis and step clustering to optimize test suites and reduce redundancy in quality assurance workflows.

Instructions

๐Ÿง  Advanced semantic duplicate analysis using LLM-powered step clustering and two-phase analysis

Input Schema

NameRequiredDescriptionDefault
analysis_modeNoAnalysis mode: basic (fast), semantic (LLM-powered), hybrid (both)hybrid
formatNoOutput formatmarkdown
include_clickable_linksNoInclude clickable links to Zebrunner web UI (markdown format only)
include_semantic_insightsNoGenerate semantic insights about workflows and patterns
include_similarity_matrixNoInclude detailed similarity matrix in output
project_keyYesProject key (e.g., 'ANDROID', 'IOS')
similarity_thresholdNoTest case similarity threshold percentage (50-100, default: 80)
step_clustering_thresholdNoStep clustering threshold percentage (50-100, default: 85)
suite_idNoOptional: Analyze specific test suite ID
test_case_keysNoOptional: Analyze specific test case keys instead of suite
use_medoid_selectionNoUse medoid-based representative selection instead of heuristic
use_step_clusteringNoEnable two-phase clustering (step clusters first, then test case clusters)

Input Schema (JSON Schema)

{ "properties": { "analysis_mode": { "default": "hybrid", "description": "Analysis mode: basic (fast), semantic (LLM-powered), hybrid (both)", "enum": [ "basic", "semantic", "hybrid" ], "type": "string" }, "format": { "default": "markdown", "description": "Output format", "enum": [ "dto", "json", "string", "markdown" ], "type": "string" }, "include_clickable_links": { "default": false, "description": "Include clickable links to Zebrunner web UI (markdown format only)", "type": "boolean" }, "include_semantic_insights": { "default": true, "description": "Generate semantic insights about workflows and patterns", "type": "boolean" }, "include_similarity_matrix": { "default": false, "description": "Include detailed similarity matrix in output", "type": "boolean" }, "project_key": { "description": "Project key (e.g., 'ANDROID', 'IOS')", "minLength": 1, "type": "string" }, "similarity_threshold": { "default": 80, "description": "Test case similarity threshold percentage (50-100, default: 80)", "maximum": 100, "minimum": 50, "type": "number" }, "step_clustering_threshold": { "default": 85, "description": "Step clustering threshold percentage (50-100, default: 85)", "maximum": 100, "minimum": 50, "type": "number" }, "suite_id": { "description": "Optional: Analyze specific test suite ID", "type": "number" }, "test_case_keys": { "description": "Optional: Analyze specific test case keys instead of suite", "items": { "type": "string" }, "type": "array" }, "use_medoid_selection": { "default": true, "description": "Use medoid-based representative selection instead of heuristic", "type": "boolean" }, "use_step_clustering": { "default": true, "description": "Enable two-phase clustering (step clusters first, then test case clusters)", "type": "boolean" } }, "required": [ "project_key" ], "type": "object" }

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/maksimsarychau/mcp-zebrunner'

If you have feedback or need assistance with the MCP directory API, please join our Discord server