rf-log-mcp
rf-log-mcp
Un servidor MCP para inspeccionar archivos de resultados de Robot Framework, que proporciona a los LLM vistas de evidencia concisas.
Resumen de funciones
Entradas admitidas:
output.xml: Robot / Rebot 6.0.x / 6.1+ / 7.xoutput.json: Robot / Rebot 7.2+
Capacidades MCP expuestas:
Herramientas
parse_resultget_viewsearch_messages
Recursos
rf://runs/{run_id}/summaryrf://runs/{run_id}/tests/{test_id}
Vistas admitidas:
summaryfailure_pathstep_window
Related MCP server: RobotMCP
Notas clave
Este proyecto es un servidor MCP stdio
La forma correcta es: el host MCP inicia el proceso
rf-log-mcpy luego invoca herramientas y recursos a través de stdio
Inicio rápido
1. Instalar dependencias
uv sync2. Ejemplo de configuración de MCP recomendado
{
"mcpServers": {
"rf-log-mcp": {
"command": "uv",
"args": [
"run",
"python",
"-m",
"rf_log_mcp"
]
}
}
}Empaquetado e instalación
Construcción
uv buildTras la construcción se generan:
dist/rf_log_mcp-0.1.0-py3-none-any.whldist/rf_log_mcp-0.1.0.tar.gz
Instalar wheel
uv pip install dist/rf_log_mcp-0.1.0-py3-none-any.whlTras la instalación se puede iniciar directamente:
rf-log-mcpEjemplo de configuración de MCP para paquetes instalados
{
"mcpServers": {
"rf-log-mcp": {
"command": "rf-log-mcp",
"args": []
}
}
}Ejemplo de ruta explícita en Windows
{
"mcpServers": {
"rf-log-mcp": {
"command": "D:\\project\\rf_log_mcp\\.venv\\Scripts\\rf-log-mcp.exe",
"args": []
}
}
}Flujo de llamada típico
Paso 1: Analizar el archivo de resultados
parse_result(path="tests/fixtures/single_failure_611.xml")Retorno típico:
{
"ok": true,
"run_id": 1,
"source_format": "xml"
}Paso 2: Obtener resumen
get_view(run_id=1, view="summary")Paso 3: Obtener ruta de fallo o buscar mensajes
get_view(run_id=1, view="failure_path")
search_messages(run_id=1, query="timeout")Variables de entorno
RF_LOG_MCP_DB
Se utiliza para sobrescribir la ruta predeterminada de la base de datos SQLite.
Ejemplo en PowerShell:
$env:RF_LOG_MCP_DB="D:\data\rf-log-mcp\store.sqlite3"
rf-log-mcpEjemplo de configuración de MCP:
{
"mcpServers": {
"rf-log-mcp": {
"command": "rf-log-mcp",
"args": [],
"env": {
"RF_LOG_MCP_DB": "D:\\data\\rf-log-mcp\\store.sqlite3"
}
}
}
}Preguntas frecuentes
1. ¿Por qué usar uv?
Las versiones de dependencias del entorno local pueden entrar en conflicto con las de MCP, por lo que se necesita un venv para aislar los conflictos de dependencias (conda es demasiado lento, uv es rápido)
2. ¿Pueden get_view / search_messages recibir rutas de archivo?
Sí.
Si el archivo ya ha sido analizado, el servicio convertirá primero la ruta al run_id correspondiente antes de realizar la consulta.
Sin embargo, se recomienda seguir utilizando preferentemente el run_id entero devuelto por parse_result().
5. ¿En qué casos no se puede utilizar este proyecto directamente?
Si tu plataforma LLM:
No admite MCP
O no admite el inicio de procesos locales
Entonces no se puede conectar directamente y se requiere una capa de integración adicional.
Verificación de desarrollo
uv run ruff check .
uv run pytestAvailable Tools
3 toolsget_viewC
Get one supported view using a numeric run id or an already-parsed file path.
Inputs: run_id (required), view (required), selector, cursor, +1 more. Returns: object
parse_resultB
Parse a Robot Framework output.xml or RF 7.2+ output.json file and index it.
Inputs: path (required), force_rebuild. Returns: object
search_messagesC
Search indexed messages using a numeric run id or an already-parsed file path.
Inputs: run_id (required), query (required), level, limit, +1 more. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: get_view retrieves a specific view, parse_result processes and indexes files, and search_messages queries indexed messages. There is no overlap in functionality, and the descriptions clearly differentiate their roles, making misselection unlikely.
All tool names follow a consistent verb_noun pattern (get_view, parse_result, search_messages) with clear, descriptive verbs and nouns. The naming is uniform throughout, using snake_case consistently without any deviations or mixed conventions.
With only 3 tools, the set feels thin for a Robot Framework log management server, as it might lack operations like updating or deleting parsed data. However, the tools cover core parsing and querying functions, making it borderline appropriate but potentially limited in scope.
The tools provide basic parsing and search capabilities, but there are notable gaps: no update or delete operations for indexed data, and no tools for managing multiple runs or views beyond retrieval. This could lead to dead ends in workflows requiring data modification or broader management.
Maintenance
Related MCP Connectors
MCP server exposing the Backtest360 engine API as tools for AI agents.
MCP server for Pentest-Tools.com: run scans, manage findings and reports via your preffered LLM.
MCP server for building and testing AI agents with multi-model experimentation and insights.
Related MCP Servers
- AlicenseAqualityDmaintenanceMCP server for log file analysis. Gives LLMs the ability to efficiently analyze large log files without loading them into context.7101MIT
- AlicenseBqualityBmaintenanceRobotMCP is a comprehensive Model Context Protocol (MCP) server that bridges the gap between human language and Robot Framework automation. It enables AI agents to understand test intentions, execute steps interactively, and generate complete test suites from successful executions.194,288 PyPI118Apache 2.0
- AlicenseNot gradedqualityDmaintenanceMCP server that helps resolve Robocop static code analysis errors and warnings via LLM, providing tools to get reports and run format.11MIT
- AlicenseNot gradedqualityCmaintenanceA local MCP server that parses Robot Framework output.xml files, scores and groups failures, and exposes structured triage data to Claude Desktop and Claude Code.MIT