Python REPL MCP Server
Servidor MCP de Python REPL
Este servidor MCP proporciona un REPL (bucle de lectura-evaluación-impresión) de Python como herramienta. Permite la ejecución de código Python mediante el protocolo MCP con una sesión persistente.
Configuración
¡No requiere configuración! El proyecto utiliza uv para la gestión de dependencias.
Related MCP server: Python REPL MCP Server
Ejecución del servidor
Simplemente ejecute:
uv run src/python_repl/server.pyUso con Claude Desktop
Agregue esta configuración a su archivo de configuración de Claude Desktop:
{
"mcpServers": {
"python-repl": {
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/python-repl-server",
"run",
"mcp_python"
]
}
}
}El servidor proporciona tres herramientas:
execute_python: ejecuta código Python con variables persistentescode: El código Python a ejecutarreset: booleano opcional para restablecer la sesión
list_variables: Mostrar todas las variables en la sesión actualinstall_package: Instalar un paquete desde pypi
Ejemplos
Establecer una variable:
a = 42Utilice la variable:
print(f"The value is {a}")Enumere todas las variables:
# Use the list_variables toolRestablecer la sesión:
# Use execute_python with reset=trueContribuyendo
¡Agradecemos sus contribuciones! No dude en enviar una solicitud de incorporación de cambios. Aquí tiene algunas maneras de contribuir:
Informar errores
Sugerir nuevas funciones
Mejorar la documentación
Agregar casos de prueba
Enviar mejoras de código
Antes de enviar una solicitud de relaciones públicas, asegúrese de:
Su código sigue el estilo existente
Ha actualizado la documentación según sea necesario
¿Tal vez escribir algunas pruebas?
Para realizar cambios importantes, primero abra un problema para discutir lo que le gustaría cambiar.
Available Tools
3 toolsexecute_pythonB
Execute Python code and return the output. Variables persist between executions.
Inputs: code (required), reset.
install_packageB
Install a Python package using uv
Inputs: package (required).
list_variablesB
List all variables in the current session
Inputs: no named parameters.
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 with no overlap: execute_python runs code, install_package manages dependencies, and list_variables inspects the session state. An agent can easily tell them apart as they target different aspects of the Python REPL workflow.
All tools follow a consistent verb_noun pattern (execute_python, install_package, list_variables) with clear, descriptive names. The naming convention is uniform throughout the set, making it predictable and easy to understand.
With only 3 tools, the set feels thin for a Python REPL server, as it lacks operations like uninstalling packages, clearing variables, or handling errors. While the core functions are covered, the count is borderline low for the domain's typical scope.
The tools cover basic execution, package installation, and variable listing, but there are notable gaps: no way to update or remove packages, delete variables, or manage session state beyond listing. This could cause agent failures in more complex workflows.
Related MCP Connectors
A simple MCP server built with FastMCP and python
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
MCP server that lets your AI assistant build and deploy apps, hosting each one at a live URL.
Related MCP Servers
- FlicenseBqualityDmaintenanceA Python-based MCP server implementation that can be easily installed via pip or directly from GitHub, providing a simple way to deploy and run MCP server functionality.1-
- AlicenseNot gradedqualityDmaintenanceProvides a persistent Python REPL session as a tool for executing code, managing files, installing packages, and initializing projects via the MCP protocol.1MIT
- AlicenseAqualityDmaintenanceA production-grade MCP server providing a persistent Python REPL with multi-session support, sandboxing, and timeout protection, enabling LLM agents to execute Python code across multiple turns with variables that persist between calls.1221 PyPI1MIT
- AlicenseNot gradedqualityDmaintenanceAsync Python REPL + Shell execution for MCP. Provides persistent state, background jobs, interactive input() bridging, and crash isolation in a single server.1Apache 2.0