QA-MCP: Test Standardization & Orchestration Server

Instructions

Implementation Reference

• src/qa_mcp/tools/lint.py:100-181 (handler)

  The core handler function for 'testcase.lint_batch' that processes a list of test cases, lints each using lint_testcase, computes aggregate statistics, identifies common issues, and provides recommendations.
  def lint_batch( testcases: list[dict], include_improvement_plan: bool = False, strict_mode: bool = False, ) -> dict: """ Lint multiple test cases and provide aggregate analysis. Args: testcases: List of test case dictionaries include_improvement_plan: Whether to include improvement plans strict_mode: If True, applies stricter validation rules Returns: Dictionary containing: - results: Individual lint results for each test case - aggregate: Aggregate statistics - recommendations: Overall recommendations """ results = [] total_score = 0 total_passed = 0 all_issues = [] for idx, tc in enumerate(testcases): result = lint_testcase(tc, include_improvement_plan, strict_mode) result["index"] = idx result["testcase_id"] = tc.get("id", f"TC-{idx + 1}") results.append(result) total_score += result["score"] if result["passed"]: total_passed += 1 all_issues.extend(result["issues"]) # Calculate aggregate statistics count = len(testcases) avg_score = total_score / count if count > 0 else 0 pass_rate = (total_passed / count * 100) if count > 0 else 0 # Find common issues issue_counts = {} for issue in all_issues: key = issue["rule"] issue_counts[key] = issue_counts.get(key, 0) + 1 common_issues = sorted( [{"rule": k, "count": v} for k, v in issue_counts.items()], key=lambda x: x["count"], reverse=True, )[:5] # Top 5 common issues # Generate recommendations recommendations = [] if avg_score < 60: recommendations.append("Genel test case kalitesi düşük. Standart eğitimi önerilir.") if any(i["rule"] == "preconditions.required" for i in common_issues): recommendations.append("Birçok test case'de ön koşullar eksik. Bu alanı zorunlu kılın.") if any(i["rule"] == "test_data.recommended" for i in common_issues): recommendations.append( "Test data tanımlaması yetersiz. Data-driven testing pratiklerini uygulayın." ) if pass_rate < 70: recommendations.append( f"Geçme oranı düşük (%{pass_rate:.1f}). Kalite kapısı standartlarını gözden geçirin." ) return { "results": results, "aggregate": { "total_testcases": count, "average_score": round(avg_score, 1), "pass_rate": round(pass_rate, 1), "passed_count": total_passed, "failed_count": count - total_passed, "total_issues": len(all_issues), "common_issues": common_issues, }, "recommendations": recommendations, "grade_distribution": _calculate_grade_distribution(results), }
• src/qa_mcp/server.py:146-164 (registration)

  Tool registration in list_tools(), including name, description, and input schema definition.
  Tool( name="testcase.lint_batch", description="Birden fazla test case'i toplu analiz eder", inputSchema={ "type": "object", "properties": { "testcases": { "type": "array", "items": {"type": "object"}, "description": "Analiz edilecek test case listesi", }, "strict_mode": { "type": "boolean", "description": "Daha katı kurallar uygula", }, }, "required": ["testcases"], }, ),
• src/qa_mcp/server.py:331-341 (registration)

  Dispatch logic in call_tool() that invokes the lint_batch function with parsed arguments and handles audit logging.
  elif name == "testcase.lint_batch": result = lint_batch( testcases=arguments["testcases"], include_improvement_plan=False, strict_mode=arguments.get("strict_mode", False), ) audit_log( name, arguments, f"Batch lint: {result.get('aggregate', {}).get('average_score', 0)} avg", )
• src/qa_mcp/tools/lint.py:12-98 (helper)

  Supporting function lint_testcase used by lint_batch to analyze individual test cases using LintEngine.
  def lint_testcase( testcase: dict, include_improvement_plan: bool = True, strict_mode: bool = False, ) -> dict: """ Lint a test case and return quality analysis. Args: testcase: Test case dictionary to analyze include_improvement_plan: Whether to include prioritized improvement plan strict_mode: If True, applies stricter validation rules Returns: Dictionary containing: - score: Quality score (0-100) - grade: Letter grade (A-F) - passed: Whether it meets minimum threshold - issues: List of found issues - suggestions: General improvement suggestions - improvement_plan: Prioritized actions (if requested) """ # Initialize engine standard = TestCaseStandard.get_default() if strict_mode: standard.minimum_score = 75 # Higher threshold in strict mode engine = LintEngine(standard) # Parse test case try: tc = TestCase(**testcase) except Exception as e: return { "score": 0, "grade": "F", "passed": False, "issues": [ { "severity": "error", "field": "structure", "rule": "valid_structure", "message": f"Test case yapısı geçersiz: {str(e)}", "suggestion": "Test case'in gerekli alanları içerdiğinden emin olun", } ], "suggestions": ["Test case yapısını QA-MCP standardına göre düzeltin"], "improvement_plan": [], "error": str(e), } # Run lint result: LintResult = engine.lint(tc) # Build response response = { "score": result.score, "grade": result.grade, "passed": result.passed, "issues": [ { "severity": issue.severity.value, "field": issue.field, "rule": issue.rule, "message": issue.message, "suggestion": issue.suggestion, } for issue in result.issues ], "suggestions": result.suggestions, } # Add improvement plan if requested if include_improvement_plan: response["improvement_plan"] = engine.get_improvement_plan(result) # Add summary statistics response["summary"] = { "total_issues": len(result.issues), "errors": sum(1 for i in result.issues if i.severity.value == "error"), "warnings": sum(1 for i in result.issues if i.severity.value == "warning"), "info": sum(1 for i in result.issues if i.severity.value == "info"), "minimum_score": standard.minimum_score, } return response