Allure Test Report Transformer for LLMs

Overview

MCP-Allure is a specialized MCP server designed to read Allure test reports and transform them into formats optimized for Large Language Models (LLMs). This tool bridges the gap between traditional test reporting and AI-assisted analysis, enabling more efficient and intelligent test analysis and maintenance.

Motivation

As AI and LLMs become increasingly integral to software development, there is a growing need to make traditional test reports more accessible to these models. Allure reports, while human-readable, are not optimized for LLM consumption. MCP-Allure addresses this by converting these reports into LLM-friendly formats, enabling:

• Generation of meaningful test summaries and insights
• Identification of patterns in test failures
• Suggestions for potential fixes for failing tests
• More effective AI-assisted debugging
• Automated test documentation generation

Problems Solved

• Efficiency: Traditional test reporting formats are not optimized for AI consumption, leading to inefficiencies in test analysis and maintenance.
• Accuracy: AI models may struggle with interpreting and analyzing test reports that are not in a format optimized for AI consumption.
• Cost: Converting test reports to LLM-friendly formats can be time-consuming and expensive.

Key Features

• Conversion: Converts Allure test reports into LLM-friendly formats.
• Optimization: Optimizes test reports for AI consumption.
• Efficiency: Converts test reports efficiently.
• Cost: Converts test reports at a low cost.
• Accuracy: Converts test reports with high accuracy.

Installation

To install MCP-Allure using uv, add the following configuration to your setup:

{
  "mcpServers": {
    "mcp-allure-server": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "mcp[cli]",
        "mcp",
        "run",
        "/Users/crisschan/workspace/pyspace/mcp-allure/mcp-allure-server.py"
      ]
    }
  }
}

Tool

get_allure_report

• Functionality: Reads an Allure report and returns JSON data.
• Input:
• report_dir: Path to the Allure HTML report.
• Return: Formatted JSON data, structured as follows:

{
    "test-suites": [
        {
            "name": "test suite name",
            "title": "suite title",
            "description": "suite description",
            "status": "passed",
            "start": "timestamp",
            "stop": "timestamp",
            "test-cases": [
                {
                    "name": "test case name",
                    "title": "case title",
                    "description": "case description",
                    "severity": "normal",
                    "status": "passed",
                    "start": "timestamp",
                    "stop": "timestamp",
                    "labels": [],
                    "parameters": [],
                    "steps": [
                        {
                            "name": "step name",
                            "title": "step title",
                            "status": "passed",
                            "start": "timestamp",
                            "stop": "timestamp",
                            "attachments": [],
                            "steps": []
                        }
                    ]
                }
            ]
        }
    ]
}

About

MCP-Allure is a tool designed to read and transform Allure test reports, making them more accessible for AI and LLM analysis.

Resources

• Readme

License

Apache-2.0 license

Activity

• Stars: 1 star
• Watchers: 1 watching
• Forks: 0 forks

Languages

• Python: 100.0%