Allure Test Reports MCP server

MCP-Allure serves as a Model Context Protocol (MCP) server that converts Allure test reports into formats optimized for Large Language Models (LLMs). This tool bridges the gap between traditional test reporting and AI-assisted analysis, enabling more effective use of AI in test result interpretation.

Installation Options

Installing via Smithery

The easiest way to install MCP-Allure is through Smithery:

npx -y @smithery/cli install @crisschan/mcp-allure --client claude

Manual Installation

To install MCP-Allure manually, you'll need to set up an MCP configuration:

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

This configuration needs to be saved in your MCP client's configuration location. The path to the server script should be adjusted to match where you've placed the MCP-Allure files on your system.

Using MCP-Allure

Getting Allure Reports

The main functionality is provided through the get_allure_report tool:

1. First, ensure you have generated an Allure HTML report from your test results
2. Use the get_allure_report function with the path to your report directory

Input Parameters

• report_dir: Path to the Allure HTML report directory

Output Format

The tool returns a JSON string containing structured test report data, including:

• Test suites with names, titles, descriptions, and status
• Test cases with details like severity, status, and execution timestamps
• Steps with their status and timing information
• Any attachments and nested steps

Example JSON Output Structure

{
    "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": []
                        }
                    ]
                }
            ]
        }
    ]
}

This structured format makes it easy for LLMs to analyze test results, identify patterns in failures, and generate insights about test performance.

Common Use Cases

• Generate test result summaries for team review
• Identify recurring patterns in test failures
• Get AI-assisted suggestions for fixing failing tests
• Create automated test documentation
• Enable more effective debugging with AI assistance

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.