Skip to main content
Glama
enesjakozh
jakenuts

mcp-cli-exec MCP Server

by jakenuts
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

mcp-cli-exec Servidor MCP

Un potente servidor MCP de ejecución de comandos CLI que permite ejecutar comandos de shell con salida estructurada. Este paquete se centra específicamente en la funcionalidad de ejecución de comandos, lo que lo diferencia de otras herramientas MCP CLI.

Características

Herramientas

cli-exec-raw

Ejecutar un comando CLI sin formato y devolver una salida estructurada

  • Toma una cadena de comando y un tiempo de espera opcional (predeterminado: 5 minutos)

  • Devuelve resultados de ejecución detallados, incluidos stdout, stderr y código de salida.

  • Maneja los errores con elegancia con respuestas de error estructuradas

cli-exec

Ejecutar uno o más comandos CLI en un directorio de trabajo específico

  • Admite comandos individuales, comandos encadenados o una matriz de comandos

  • Todos los comandos se ejecutan en el directorio de trabajo especificado

  • Devuelve resultados detallados para cada comando:

    • Estado de éxito/fracaso

    • Código de salida

    • stdout y stderr (códigos ANSI eliminados)

    • Duración de la ejecución

    • Directorio de trabajo

  • Se detiene ante el primer fallo del comando

  • Tiempo de espera opcional por comando (predeterminado: 5 minutos)

Nota: Debido a las limitaciones del contexto de ejecución, cada comando se ejecuta de forma independiente. Los cambios de directorio (cd) dentro de los comandos no afectan a los comandos posteriores. Todos los comandos se ejecutan en el directorio de trabajo especificado inicialmente.

Formato de salida

Los comandos devuelven resultados estructurados que incluyen:

  • Estado de éxito/fracaso

  • Código de salida

  • stdout y stderr (con códigos ANSI eliminados)

  • Duración de la ejecución

  • Directorio de trabajo

  • Información detallada del error si corresponde

Ejemplo de uso

cli-exec-raw

Ejecución de comando simple:

{
  "command": "echo Hello World"
}

Con tiempo de espera:

{
  "command": "long-running-script.sh",
  "timeout": 300000
}

cli-exec

Comando único en un directorio específico:

{
  "workingDirectory": "/path/to/project",
  "commands": "npm install"
}

Múltiples comandos (todos se ejecutan en el mismo directorio de trabajo):

{
  "workingDirectory": "C:\\project",
  "commands": [
    "dir /b",
    "npm run build"
  ]
}

Related MCP server: MCP Server

Instalación

Opcionalmente instalar desde npm:

npm install -g mcp-cli-exec
# or with pnpm
pnpm add -g mcp-cli-exec

O simplemente usa npx en tu configuración

Para la extensión Cline VSCode

Agregar a %APPDATA%/Code - Insiders/User/globalStorage/rooveterinaryinc.roo-cline/settings/cline_mcp_settings.json :

{
  "mcpServers": {
    "mcp-cli-exec": {
      "command": "npx",
      "args": ["-y", "mcp-cli-exec"]
    }
  }
}

Para Claude Desktop

Agregue al archivo de configuración apropiado:

Windows: %APPDATA%/Claude/claude_desktop_config.json MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "mcp-cli-exec": {
      "command": "npx",
      "args": ["-y", "mcp-cli-exec"]
    }
  }
}

Configuración especial de Windows

Si encuentra el problema de surgimiento de ENOENT npx en Windows, use esta configuración alternativa que especifica las rutas completas:

{
  "mcpServers": {
    "mcp-cli-exec": {
      "command": "C:\\Users\\jim\\AppData\\Roaming\\nvm\\v22.1.0\\node.exe",
      "args": [
        "C:\\Users\\jim\\AppData\\Roaming\\npm\\node_modules\\npm\\bin\\npx-cli.js",
        "-y",
        "mcp-cli-exec"
      ]
    }
  }
}

Desarrollo

Instalar dependencias:

pnpm install

Construir el servidor:

pnpm run build

Para desarrollo con reconstrucción automática:

pnpm run watch

Depuración

Dado que los servidores MCP se comunican a través de stdio, la depuración puede ser un desafío. El Inspector MCP ofrece útiles herramientas de depuración:

pnpm run inspector

Esto le proporcionará una URL para acceder al inspector en su navegador, donde podrá:

  • Ver todos los mensajes de MCP

  • Inspeccionar las cargas útiles de solicitud/respuesta

  • Pruebe herramientas de forma interactiva

  • Supervisar el estado del servidor

Manejo de errores

El servidor incluye un manejo integral de errores:

  • Validación de entrada para todos los parámetros de la herramienta

  • Respuestas de error estructuradas

  • Manejo del tiempo de espera del comando

  • Validación del directorio de trabajo

  • Eliminación de código ANSI para una salida limpia

Detalles técnicos

  • Desarrollado con TypeScript y el SDK de MCP

  • Utiliza execa para una ejecución confiable de comandos

  • Tiempo de espera del comando predeterminado: 5 minutos

  • Admite sistemas Windows y similares a Unix (utilice los comandos adecuados para su sistema operativo, por ejemplo, 'dir' vs 'ls')

  • Ejecuta comandos secuencialmente, deteniéndose en el primer fallo

  • Cada comando se ejecuta independientemente en el directorio de trabajo especificado

Available Tools

2 tools
cli-execC

Execute one or more CLI commands in a specific working directory

ParametersJSON Schema
NameRequiredDescriptionDefault
commandsYesCommands to execute
timeoutNoOptional timeout in milliseconds per command (default: 5 minutes)
workingDirectoryYesWorking directory to execute commands in

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations provided, the description carries full burden but only states basic functionality. It doesn't disclose critical behavioral traits like execution safety (potential for destructive commands), authentication needs, error handling, output format, or rate limits. The mention of 'timeout' in the schema isn't reinforced in the description.

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

Conciseness5/5

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

The description is a single, efficient sentence that front-loads the core purpose without unnecessary words. Every element ('Execute', 'CLI commands', 'specific working directory') earns its place, making it optimally concise.

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 CLI execution tool with no annotations and no output schema, the description is insufficient. It lacks details on execution behavior (e.g., sequential vs. parallel), error propagation, security implications, or return values, leaving significant gaps for an agent to understand tool usage.

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%, so the schema fully documents all parameters. The description adds no additional parameter semantics beyond what's in the schema, maintaining the baseline score of 3 for adequate coverage through structured data alone.

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

Purpose4/5

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

The description clearly states the action ('Execute') and resource ('CLI commands') with additional context about working directory. It distinguishes from sibling 'cli-exec-raw' by specifying 'in a specific working directory', though the distinction isn't fully explicit about what makes the sibling different.

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 the sibling 'cli-exec-raw'. It mentions the working directory context but doesn't explain alternative scenarios, prerequisites, or exclusions for tool selection.

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

cli-exec-rawC

Execute a raw CLI command and return structured output

ParametersJSON Schema
NameRequiredDescriptionDefault
commandYesThe CLI command to execute
timeoutNoOptional timeout in milliseconds (default: 5 minutes)

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the tool executes commands and returns structured output, but fails to address critical behavioral aspects such as security implications, execution environment, error handling, or potential side effects. This is inadequate for a tool that executes arbitrary CLI commands.

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

Conciseness5/5

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

The description is extremely concise and front-loaded in a single sentence that captures the core functionality. Every word earns its place with no wasted text, making it easy for an agent to parse quickly.

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 of executing arbitrary CLI commands (which involves security, environment, and side-effect considerations), no annotations, and no output schema, the description is insufficiently complete. It doesn't explain what 'structured output' means, execution constraints, or safety warnings, leaving significant gaps for agent understanding.

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 clear parameter descriptions in the schema. The description adds no additional parameter semantics beyond what the schema provides, such as command syntax examples or timeout behavior details. Baseline 3 is appropriate when the schema does the heavy lifting.

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

Purpose4/5

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

The description clearly states the tool's purpose: 'Execute a raw CLI command and return structured output'. It specifies the verb ('execute'), resource ('raw CLI command'), and outcome ('return structured output'). However, it doesn't explicitly differentiate from its sibling 'cli-exec', which likely has similar functionality, preventing a perfect score.

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 its sibling 'cli-exec' or other alternatives. It lacks context about appropriate use cases, prerequisites, or exclusions, leaving the agent with minimal direction beyond the basic purpose.

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. 2 tool updatesv1.0.0
    • First observedcli-exec
    • First observedcli-exec-raw
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

C2.9/5.0

Scored across 2 tools

Disambiguation2/5

The two tools have significant overlap in purpose, both executing CLI commands. While cli-exec-raw specifies 'raw' and 'structured output', the distinction is subtle and could easily lead to confusion about which to use for basic command execution. The descriptions don't clearly delineate when to choose one over the other.

Naming Consistency4/5

Both tools follow a consistent cli-exec prefix pattern with hyphenated suffixes. The naming is predictable and readable, though the suffix conventions differ slightly (one has no suffix, the other uses '-raw'). This minor deviation keeps it from a perfect score.

Tool Count3/5

With only 2 tools, the server feels thin for a CLI execution domain. While it covers basic execution, more operations like command validation, history tracking, or batch processing might be expected. The count is borderline minimal but functional for core tasks.

Completeness2/5

For a CLI execution server, there are notable gaps. Missing tools for command chaining, environment variable management, output parsing beyond 'structured', or error handling make the surface incomplete. Agents will hit dead ends when needing advanced CLI interactions beyond simple execution.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • 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

  • MCP Server

    mokemoke0821
    A
    license
    Not graded
    quality
    D
    maintenance
    A cross-platform shell command execution server that supports Windows, macOS, and Linux environments with PowerShell, CMD, GitBash, and Bash shells, optimized for Japanese language environments.
    48 npm
    MIT

  • mcp2term

    FreddyE1982
    F
    license
    B
    quality
    D
    maintenance
    Enables safe execution of system shell commands with real-time streaming output and rich metadata capture. Provides configurable command execution with timeout controls, environment management, and extensible plugin architecture for monitoring command lifecycles.
    4
    -

  • MCP Terminal Tool Server

    gkgaurav31
    F
    license
    B
    quality
    D
    maintenance
    An MCP server that enables users to execute arbitrary shell commands on their local machine and receive the output. It provides a terminal tool for running system commands through MCP-compatible clients using the Python SDK.
    1
    -

Appeared in Searches