Skip to main content
Glama
enesjakozh
crisschan

MCP-Allure

by crisschan
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

MCP-Allure

MCP-Allure es un servidor MCP que lee los informes de Allure y los devuelve en formatos compatibles con LLM.

Motivación

A medida que la IA y los Grandes Modelos de Lenguaje (LLM) se integran cada vez más en el desarrollo de software, crece la necesidad de acortar la distancia entre los informes de pruebas tradicionales y el análisis asistido por IA. Los formatos tradicionales de informes de pruebas de Allure, si bien son legibles por humanos, no están optimizados para el uso y procesamiento de LLM.

MCP-Allure aborda este desafío transformando los informes de pruebas de Allure en formatos compatibles con LLM. Esta transformación permite que los modelos de IA comprendan, analicen y proporcionen información sobre los resultados de las pruebas, lo que facilita:

  • Genere resúmenes y perspectivas de pruebas significativas

  • Identificar patrones en fallas de pruebas

  • Sugerir posibles soluciones para las pruebas fallidas

  • Habilite una depuración asistida por IA más efectiva

  • Facilitar la generación automatizada de documentación de pruebas

Al optimizar los informes de pruebas para el consumo de LLM, MCP-Allure ayuda a los equipos de desarrollo a aprovechar todo el potencial de las herramientas de IA en su flujo de trabajo de pruebas, lo que genera un análisis y mantenimiento de pruebas más eficientes e inteligentes.

Problemas resueltos

  • Eficiencia : Los formatos de informes de pruebas tradicionales no están optimizados para el consumo de IA, lo que genera ineficiencias en el análisis y el mantenimiento de las pruebas.

  • Precisión : los modelos de IA pueden tener dificultades para interpretar y analizar informes de pruebas que no estén en un formato optimizado para el consumo de IA.

  • Costo : Convertir los informes de pruebas a formatos compatibles con LLM puede consumir mucho tiempo y ser costoso.

Características principales

  • Conversión : convierte los informes de pruebas de Allure en formatos compatibles con LLM.

  • Optimización : optimiza los informes de pruebas para el consumo de IA.

  • Eficiencia : Convierte informes de pruebas de manera eficiente.

  • Costo : Convierte informes de pruebas a bajo costo.

  • Precisión : Convierte informes de pruebas con alta precisión.

Instalación

Para instalar mcp-repo2llm usando uv:

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

Herramienta

obtener_informe_de_atractivo

  • Lee el informe de Allure y devuelve datos JSON

  • Aporte:

    • report_dir: Ruta del informe HTML de Allure

  • Devolver:

    • Cadena, datos JSON formateados, como esto:

{
    "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": [

                            ]
                        }
                    ]
                }
            ]
        }
    ]
}

Available Tools

1 tool
get_allure_reportC

read allure report and return json data

ParametersJSON Schema
NameRequiredDescriptionDefault
results_dirYes

TDQS

C2.4/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions reading and returning JSON data, but fails to disclose critical traits: whether this is a read-only operation (implied by 'read' but not explicit), potential side effects (e.g., file access permissions), error handling, or performance aspects (e.g., large report processing). The description adds minimal value beyond the basic action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very concise—a single sentence with no wasted words—and front-loaded with the core action. However, it is under-specified rather than efficiently concise; it could benefit from slightly more detail without losing brevity. It earns a high score for structure but loses a point due to under-specification.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (a tool to read and parse reports), lack of annotations, 0% schema coverage, and no output schema, the description is incomplete. It does not explain the return format beyond 'json data' (e.g., structure, keys), error conditions, or dependencies. For a tool with one parameter and no structured support, more context is needed to be adequately helpful.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, with 1 parameter ('results_dir') undocumented in the schema. The description does not compensate by explaining what 'results_dir' means (e.g., path to Allure results directory, expected format), its role in reading the report, or any constraints. This leaves the parameter's semantics unclear, failing to add meaning beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the tool 'read[s] allure report and return[s] json data', which provides a basic verb+resource combination ('read allure report') and outcome ('return json data'). However, it's vague about what constitutes an 'allure report' (e.g., test results, specific file format) and doesn't differentiate from siblings (though none exist). It avoids tautology by not merely restating the name, but lacks specificity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool—there are no alternatives mentioned (sibling tools are none), no context about prerequisites (e.g., requires an existing report directory), and no exclusions or comparisons. The description implies usage for reading reports but offers no further direction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev1.0.0
    • First observedget_allure_report
Deploy Server
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

TDQS

C2.7/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The tool 'get_allure_report' has a single, clearly defined purpose of reading Allure reports and returning JSON data.

Naming Consistency5/5

The single tool name 'get_allure_report' follows a clear verb_noun pattern (get + report). Since there is only one tool, consistency is inherently perfect with no deviations to assess.

Tool Count2/5

The server has only one tool, which feels thin for a reporting domain like Allure. A single tool for reading reports lacks essential operations such as generating, listing, or managing reports, making it under-scoped for typical use cases.

Completeness2/5

The tool surface is severely incomplete for an Allure reporting server. It only provides a 'get' operation for reports, missing critical functions like creating reports, listing available reports, updating report data, or deleting reports, which are essential for full lifecycle coverage.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • qasphere-mcp

    Hypersequent
    A
    license
    A
    quality
    F
    maintenance
    QA Sphere MCP server that enables Large Language Models to interact directly with test management system test cases, supporting AI-powered development workflows and test case discovery.
    15
    45 npm
    23
    MIT

  • MCP Code Reviewer

    whtan410
    F
    license
    Not graded
    quality
    D
    maintenance
    An AI-powered server for code analysis, requirements validation, and automated fix proposals with human-in-the-loop confirmation. It supports multiple LLM providers and ensures safe file modifications through automatic backups and path validation.
    -