AI导哈

Extent测试报告分析MCP服务器

这是一个通过MCP协议让AI助手读取、分析和理解Extent测试报告的服务器，支持解析JSON与Spark HTML格式报告、提取测试汇总统计、获取失败详情及堆栈信息，并可比较两次报告以识别回归，适用于软件开发中的自动化测试结果分析和质量保障场景。

  • by QATonic
  • Python
  • 本地部署
  • 更新于
在 GitHub 查看 QATonic/mcp-extent

使用说明

Extent Report MCP Server

This is a Model Context Protocol (MCP) server that enables AI assistants (like Claude, Cursor, and QAFlow) to read, analyze, and understand Extent Reports.

Features

  • Parse Extent Reports (JSON and Spark HTML formats)
  • Extract test summaries (Pass/Fail/Skip rates)
  • Retrieve detailed failure analysis including stack traces
  • Compare reports to identify regressions

Installation

# Install with uv (recommended)
uv tool install mcp-extent

# Or install with pip
pip install mcp-extent

Usage (Local Development)

Since you are running this from source, add the total path to your configuration:

{
  "mcpServers": {
    "mcp-extent": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "D:/mcp-extent", 
        "mcp-extent"
      ]
    }
  }
}

Note: Adjust the path D:/mcp-extent if you move the project.

Tools

  • get_extent_report: Parse full report
  • get_test_summary: Get high-level stats
  • get_failed_tests: Get detailed failure info
  • analyze_failures: Pattern matching for failures
  • compare_reports: Compare two report runs

相关 MCP