Skip to main content
Glama
enesjakoptzh
diegofornalha

MCP Shell Server

by diegofornalha
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Servidor Shell MCP

código decodificador emblema de herrería

Un servidor seguro para ejecutar comandos de shell que implementa el Protocolo de Contexto de Modelo (MCP). Este servidor permite la ejecución remota de comandos de shell autorizados con soporte para entrada a través de stdin.

Características

  • Ejecución segura de comandos : solo se pueden ejecutar comandos autorizados

  • Soporte de entrada estándar : pasa la entrada a los comandos a través de la entrada estándar

  • Salida completa : devuelve stdout, stderr, código de salida y tiempo de ejecución

  • Seguridad con operadores de shell : valida los comandos después de los operadores de shell (;, &&, ||, |)

  • Control de tiempo de espera : establece el tiempo máximo de ejecución de los comandos

Related MCP server: Shell MCP Server

Configurando el cliente MCP en tu Claude.app

Versión publicada

code ~/Library/Application\ Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "shell": {
      "command": "uvx",
      "args": [
        "mcp-shell-server"
      ],
      "env": {
        "ALLOW_COMMANDS": "ls,cat,pwd,grep,wc,touch,find"
      }
    },
  }
}

Versión local

Ajustes

code ~/Library/Application\ Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "shell": {
      "command": "uv",
      "args": [
        "--directory",
        ".",
        "run",
        "mcp-shell-server"
      ],
      "env": {
        "ALLOW_COMMANDS": "ls,cat,pwd,grep,wc,touch,find"
      }
    },
  }
}

Instalación

pip install mcp-shell-server

Usar

Iniciando el servidor

ALLOW_COMMANDS="ls,cat,echo" uvx mcp-shell-server
# Ou usando o alias
ALLOWED_COMMANDS="ls,cat,echo" uvx mcp-shell-server

La variable de entorno ALLOW_COMMANDS (o su alias ALLOWED_COMMANDS ) especifica qué comandos se pueden ejecutar. Los comandos se pueden separar mediante comas con espacios opcionales alrededor de ellos.

Formatos válidos para ALLOW_COMMANDS o ALLOWED_COMMANDS:

ALLOW_COMMANDS="ls,cat,echo"          # Formato básico
ALLOWED_COMMANDS="ls ,echo, cat"      # Com espaços (usando alias)
ALLOW_COMMANDS="ls,  cat  , echo"     # Múltiplos espaços

Formato de solicitud

# Execução básica de comando
{
    "command": ["ls", "-l", "/tmp"]
}

# Comando com entrada stdin
{
    "command": ["cat"],
    "stdin": "Hello, World!"
}

# Comando com timeout
{
    "command": ["long-running-process"],
    "timeout": 30  # Tempo máximo de execução em segundos
}

# Comando com diretório de trabalho e timeout
{
    "command": ["grep", "-r", "pattern"],
    "directory": "/path/to/search",
    "timeout": 60
}

Formato de respuesta

Respuesta exitosa:

{
    "stdout": "saída do comando",
    "stderr": "",
    "status": 0,
    "execution_time": 0.123
}

Respuesta de error:

{
    "error": "Comando não permitido: rm",
    "status": 1,
    "stdout": "",
    "stderr": "Comando não permitido: rm",
    "execution_time": 0
}

Seguridad

El servidor implementa varias medidas de seguridad:

  1. Lista blanca de comandos : solo se pueden ejecutar comandos explícitamente permitidos

  2. Validación del operador de shell : los comandos después de los operadores de shell (;, &&, ||, |) también se validan con la lista blanca

  3. Sin inyección de shell : los comandos se ejecutan directamente sin interpretación de shell

Desarrollo

Configuración del entorno de desarrollo

  1. Clonar el repositorio

git clone https://github.com/yourusername/mcp-shell-server.git
cd mcp-shell-server

  1. Instalar dependencias, incluidos los requisitos de prueba

pip install -e ".[test]"

Ejecución de pruebas

pytest

Referencia de API

Argumentos de solicitud

Campo

Tipo

Obligatorio

Descripción

dominio

cadena[]

Sí

Comando y sus argumentos como elementos de matriz

entrada estándar

cadena

No

Entrada que se pasará al comando

directorio

cadena

No

Directorio de trabajo para ejecutar el comando

se acabó el tiempo

entero

No

Tiempo máximo de ejecución en segundos

Campos de respuesta

Campo

Tipo

Descripción

salida estándar

cadena

Salida estándar del comando

error de error estándar

cadena

Salida de error de comando

estado

entero

Código de estado de salida

tiempo de ejecución

flotar

Tiempo de ejecución (en segundos)

error

cadena

Mensaje de error (presente sólo si falló)

Requisitos

  • Python 3.11 o superior

  • mcp>=1.1.0

Licencia

Licencia MIT: consulte el archivo LICENCIA para obtener más detalles

Available Tools

1 tool
shell_executeC

Execute um comando shell Comandos permitidos:

ParametersJSON Schema
NameRequiredDescriptionDefault
commandYesComando e seus argumentos como array
directoryYesDiretório de trabalho onde o comando será executado
stdinNoEntrada a ser passada para o comando via stdin
timeoutNoTempo máximo de execução em segundos

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 full burden for behavioral disclosure. It mentions 'Comandos permitidos: ' but doesn't specify which commands are allowed, security implications, or output behavior. This is a significant gap for a shell execution tool, as it lacks critical safety and operational details.

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

Conciseness2/5

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

The description is extremely brief but inefficiently structured, with 'Comandos permitidos: ' left incomplete. It fails to convey necessary information concisely, as the trailing text suggests missing content rather than purposeful brevity.

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?

For a shell execution tool with no annotations and no output schema, the description is insufficient. It doesn't explain return values, error handling, security restrictions, or allowed commands, leaving critical gaps in understanding how the tool behaves and what results to expect.

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

Parameters3/5

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

Schema description coverage is 100%, with all parameters well-documented in the input schema. The description adds no additional parameter semantics beyond what the schema provides, such as examples or constraints on allowed commands. This meets the baseline for high schema coverage.

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 'Execute um comando shell' which translates to 'Execute a shell command', providing a clear verb+resource combination. However, it's incomplete with 'Comandos permitidos: ' trailing off, making it vague about what commands are actually allowed. No sibling tools exist for differentiation, but the incomplete nature reduces clarity.

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?

The description provides no guidance on when to use this tool versus alternatives, prerequisites, or exclusions. It only states the basic purpose without context about appropriate scenarios or limitations, leaving the agent with no usage direction beyond the obvious.

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 observedshell_execute
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

C2.7/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility for confusion or overlap between tools. The tool 'shell_execute' has a single, clearly defined purpose of executing shell commands, so disambiguation is perfect.

Naming Consistency5/5

Since there is only one tool, naming consistency is inherently perfect. The tool name 'shell_execute' follows a clear verb_noun pattern, but with no other tools to compare, it sets no pattern to deviate from.

Tool Count2/5

A single tool is too few for a server named 'MCP Shell Server', which implies broader shell-related functionality. While the tool covers basic command execution, the scope feels thin, lacking tools for tasks like listing files, checking processes, or managing environment variables that are typical in shell operations.

Completeness2/5

The tool set is severely incomplete for a shell server. It only provides execution, missing essential operations like file manipulation (e.g., read, write, delete), directory navigation, process management, or system information retrieval. This will likely cause agent failures when trying to perform common shell tasks beyond simple command execution.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • mcp-shell-server

    tumf
    A
    license
    A
    quality
    A
    maintenance
    A secure shell command execution server implementing the Model Context Protocol (MCP). This server allows remote execution of whitelisted shell commands with support for stdin input.
    1
    198
    MIT

  • Shell MCP Server

    odysseus0
    A
    license
    Not graded
    quality
    D
    maintenance
    A Model Context Protocol server that allows LLMs to execute shell commands and receive their output in a controlled manner.
    7
    MIT

Appeared in Searches