MCP Allure Server

🚀 MCP-Allure

MCP-Allure is an MCP server that reads Allure reports and returns results in an LLM-friendly format.

🚀 Quick Start

In the era of rapid development of artificial intelligence and large language models (LLMs), there is an increasing need to bridge the gap between traditional test reports and AI analysis. The traditional Allure test report format, while suitable for human reading, is not optimized for LLM consumption and processing. MCP-Allure addresses this challenge by converting Allure test reports into an LLM-friendly format. This conversion enables AI models to better understand, analyze, and provide insights into test results, facilitating the following tasks:

• Generate meaningful test summaries and insights.
• Identify patterns in test failures.
• Suggest possible fixes for test failures.
• Enable more effective AI-assisted debugging.
• Promote the generation of automated test documentation.

By optimizing test reports for LLM consumption, MCP-Allure helps development teams fully leverage the potential of AI tools in the test workflow, leading to more efficient and intelligent test analysis and maintenance.

✨ Features

Problem Solving

• Efficiency: Traditional test report formats are not suitable for AI consumption, resulting in low efficiency in test analysis and maintenance.
• Accuracy: AI models may have difficulty interpreting and analyzing test reports that are not suitable for LLM consumption.
• Cost: Converting test reports into an LLM-friendly format can be time-consuming and resource-intensive.

Core Functions

• Conversion: Convert Allure test reports into an LLM-friendly format.
• Optimization: Optimize test reports for AI consumption.
• Efficiency: Efficiently convert test reports.
• Cost: Convert test reports at a low cost.
• Accuracy: Convert test reports with high precision.

📦 Installation

Install mcp-repo2llm using uv:

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

📚 Documentation

get_allure_report

• Read an Allure report and return JSON data.
• Input:
  • report_dir: Path to the Allure HTML report.
• Return:
  • A string of formatted JSON data, for example:

{
    "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": [

                            ]
                        }
                    ]
                }
            ]
        }
    ]
}