Skip to main content
Glama
enesjakozh
tumf

mcp-shell-server

by tumf
OverviewSchemaRelated ServersScoreDiscussions
Python
Remote

MCP 셸 서버

코드코브 대장간 배지

모델 컨텍스트 프로토콜(MCP)을 구현하는 보안 셸 명령 실행 서버입니다. 이 서버는 stdin 입력을 지원하여 허용 목록에 있는 셸 명령을 원격으로 실행할 수 있도록 합니다.

특징

  • 보안 명령 실행 : 허용 목록에 있는 명령만 실행할 수 있습니다.

  • 표준 입력 지원 : stdin을 통해 명령에 입력 전달

  • 종합 출력 : stdout, stderr, 종료 상태 및 실행 시간을 반환합니다.

  • Shell Operator Safety : Shell 연산자(;, &&, ||, |) 다음에 나오는 명령을 검증합니다.

  • 시간 제한 제어 : 명령에 대한 최대 실행 시간 설정

Related MCP server: Shell MCP Server

Claude.app의 MCP 클라이언트 설정

출판된 버전

지엑스피1

{
  "mcpServers": {
    "shell": {
      "command": "uvx",
      "args": [
        "mcp-shell-server"
      ],
      "env": {
        "ALLOW_COMMANDS": "ls,cat,pwd,grep,wc,touch,find"
      }
    },
  }
}

로컬 버전

구성

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"
      }
    },
  }
}

설치

Smithery를 통해 설치

Smithery를 통해 Claude Desktop용 Shell Server를 자동으로 설치하려면:

npx -y @smithery/cli install mcp-shell-server --client claude

수동 설치

pip install mcp-shell-server

Smithery를 통해 설치

Smithery를 통해 Claude Desktop용 Shell Server를 자동으로 설치하려면:

npx -y @smithery/cli install mcp-shell-server --client claude

용법

서버 시작

ALLOW_COMMANDS="ls,cat,echo" uvx mcp-shell-server
# Or using the alias
ALLOWED_COMMANDS="ls,cat,echo" uvx mcp-shell-server

ALLOW_COMMANDS (또는 별칭 ALLOWED_COMMANDS ) 환경 변수는 실행 가능한 명령을 지정합니다. 명령은 쉼표로 구분할 수 있으며, 필요에 따라 공백을 사용할 수 있습니다.

ALLOW_COMMANDS 또는 ALLOWED_COMMANDS에 유효한 형식:

ALLOW_COMMANDS="ls,cat,echo"          # Basic format
ALLOWED_COMMANDS="ls ,echo, cat"      # With spaces (using alias)
ALLOW_COMMANDS="ls,  cat  , echo"     # Multiple spaces

요청 형식

# Basic command execution
{
    "command": ["ls", "-l", "/tmp"]
}

# Command with stdin input
{
    "command": ["cat"],
    "stdin": "Hello, World!"
}

# Command with timeout
{
    "command": ["long-running-process"],
    "timeout": 30  # Maximum execution time in seconds
}

# Command with working directory and timeout
{
    "command": ["grep", "-r", "pattern"],
    "directory": "/path/to/search",
    "timeout": 60
}

응답 형식

성공적인 응답:

{
    "stdout": "command output",
    "stderr": "",
    "status": 0,
    "execution_time": 0.123
}

오류 응답:

{
    "error": "Command not allowed: rm",
    "status": 1,
    "stdout": "",
    "stderr": "Command not allowed: rm",
    "execution_time": 0
}

보안

서버는 여러 가지 보안 조치를 구현합니다.

  1. 명령 허용 목록 : 명시적으로 허용된 명령만 실행할 수 있습니다.

  2. Shell 연산자 검증 : Shell 연산자(;, &&, ||, |) 뒤에 오는 명령도 허용 목록에 대해 검증됩니다.

  3. 셸 주입 없음 : 셸 해석 없이 명령이 직접 실행됩니다.

개발

개발 환경 설정

  1. 저장소를 복제합니다

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

  1. 테스트 요구 사항을 포함한 종속성 설치

pip install -e ".[test]"

테스트 실행

pytest

API 참조

요청 인수

필드

유형

필수의

설명

명령

끈[]

예

명령과 해당 인수를 배열 요소로 사용

표준입력

끈

아니요

명령에 전달될 입력

예배 규칙서

끈

아니요

명령 실행을 위한 작업 디렉토리

타임아웃

정수

아니요

최대 실행 시간(초)

응답 필드

필드

유형

설명

표준 출력

끈

명령의 표준 출력

표준 에러

끈

명령의 표준 오류 출력

상태

정수

종료 상태 코드

실행 시간

뜨다

실행에 걸리는 시간(초)

오류

끈

오류 메시지(실패한 경우에만 표시됨)

요구 사항

  • Python 3.11 이상

  • mcp>=1.1.0

특허

MIT 라이선스 - 자세한 내용은 라이선스 파일을 참조하세요.

Available Tools

1 tool
shell_executeA

Execute a shell command Allowed commands: pwd, grep, cat, ls, wc Allowed patterns: Default timeout: 30s; maximum timeout: 300s; output cap: 1048576 bytes

ParametersJSON Schema
NameRequiredDescriptionDefault
stdinNoInput to be passed to the command via stdin
commandYesCommand and its arguments as array
timeoutNoMaximum execution time in seconds; clamped to server maximum
directoryNoOptional working directory. Omit to use the MCP server process current working directory; relative paths are resolved from that same server process CWD.

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the transparency burden. It discloses the allowed commands, default/maximum timeout, and output cap, providing useful behavioral context. However, it omits details about stderr handling, output truncation behavior, or the fact that all allowed commands are read-only, preventing a perfect score.

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 brief and front-loaded with the primary action, followed by key constraints. However, the 'Allowed patterns: ' line is empty and incomplete, which introduces a minor structural flaw and reduces clarity.

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

Completeness3/5

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

The description captures the essential constraints (allowed commands, timeout, output cap) and parameter semantics are handled by the schema. Yet it does not describe the return format, stderr handling, or exit code behavior, and the incomplete 'Allowed patterns' field leaves a gap in coverage for a shell execution tool.

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?

The input schema already provides complete descriptions for all four parameters (100% coverage), so the baseline is 3. The description adds marginal value by mentioning the default timeout (30s) and maximum timeout (300s), which aligns with the 'timeout' parameter but does not elaborate on other parameters beyond what the schema already states.

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

Purpose5/5

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

The description explicitly states 'Execute a shell command' and lists the allowed commands (pwd, grep, cat, ls, wc), making the tool's purpose specific and unambiguous. Even without siblings, the allowed-command list defines scope clearly.

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

Usage Guidelines3/5

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

The description communicates constraints via 'Allowed commands' and 'Allowed patterns', indicating when the tool is appropriate. However, it does not explicitly state when to use this tool versus alternatives (there are none listed) or provide a 'when not to use' guideline, leaving usage context somewhat implicit.

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. Dates show when Glama detected each change.

  1. 1 tool updatev1.1.0
    • Changedshell_execute4 fields changed
      • changedInput schema / properties / directory / description
        Previous value: -"Absolute path to a working directory where the command will be executed"New value: +"Optional working directory. Omit to use the MCP server process current working directory; relative paths are resolved from that same server process CWD."
      • changedInput schema / properties / timeout / description
        Previous value: -"Maximum execution time in seconds"New value: +"Maximum execution time in seconds; clamped to server maximum"
      • changedInput schema / properties / timeout / minimum
        Previous value: -0New value: +1
      • changedInput schema / required
        Previous value: -[
-  "command",
-  "directory"
-]New value: +[
+  "command"
+]
  2. 1 tool update
    • First observedshell_execute
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.9/5.0
Disambiguation5/5

Only one tool exists, so there is no possibility of confusion or overlap. Every action goes through the single shell_execute tool.

Naming Consistency5/5

The tool name shell_execute follows a clear verb_noun pattern, consistent with common MCP naming conventions. Even with a single tool, the name is predictable and descriptive.

Tool Count3/5

With only one tool, the set feels thin, but for a restricted shell executor it could be acceptable. The scope is narrow, making the tool count borderline rather than clearly excessive or insufficient.

Completeness3/5

The tool covers the allowed commands (pwd, grep, cat, ls, wc), but the restricted set excludes many typical shell operations like file writing or process control. This suggests notable gaps for a server named 'shell', though the explicit allowlist mitigates some issues.

Maintenance

ActivityMaintained
ResponsivenessWithin a week

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • Shell-MCP

    kevinwatt
    A
    license
    B
    quality
    D
    maintenance
    A secure MCP server for executing whitelisted shell commands with resource and timeout controls, designed for integration with Claude and other MCP-compatible LLMs.
    20
    389
    7
    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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/tumf/mcp-shell-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server