Skip to main content
Glama
enesjakozh
Sunwood-ai-labs

Command Executor MCP Server

by Sunwood-ai-labs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript

명령 실행자 MCP 서버

사전 승인된 명령을 안전하게 실행하기 위한 모델 컨텍스트 프로토콜 서버입니다.

🎥 데모

https://github.com/user-attachments/assets/ed763a12-b685-4e0b-b9a5-bc948a590f51

Related MCP server: MCP Shell Server

✨ 특징

  • 사전 승인된 명령 목록을 통한 안전한 명령 실행

  • 환경 변수를 통해 구성 가능한 허용 명령

  • TypeScript 및 MCP SDK로 구축됨

  • 원활한 통합을 위한 stdio를 통한 통신

  • 오류 처리 및 보안 검증

  • 실시간 명령 출력 스트리밍

🚀 설치

종속성 설치:

지엑스피1

서버를 빌드하세요:

npm run build

자동 재빌드를 사용한 개발의 경우:

npm run watch

⚙️ 구성

🔒 허용된 명령어

기본적으로 다음 명령이 허용됩니다.

  • git

  • 엘에스

  • mkdir

  • CD

  • 엔피엠

  • 엔피엑스

  • 파이썬

ALLOWED_COMMANDS 환경 변수를 설정하여 허용되는 명령을 사용자 정의할 수 있습니다.

export ALLOWED_COMMANDS=git,ls,mkdir,python

🔌 Claude 데스크톱 통합

Claude Desktop과 함께 사용하려면 서버 구성을 추가하세요.

MacOS의 경우:

~/Library/Application Support/Claude/claude_desktop_config.json

Windows의 경우:

%APPDATA%/Claude/claude_desktop_config.json

구성 예:

{
  "mcpServers": {
    "command-executor": {
      "command": "/path/to/command-executor/build/index.js"
    }
  }
}

🛡️ 보안 고려 사항

명령 실행 서버는 여러 가지 보안 조치를 구현합니다.

  1. 사전 승인된 명령 목록

    • 명시적으로 허용된 명령만 실행할 수 있습니다.

    • 기본 목록은 제한적이고 보안에 중점을 둡니다.

    • 명령은 주입을 방지하기 위해 접두사로 검증됩니다.

  2. 명령 검증

    • 명령어 접두사 검증으로 명령어 주입이 방지됩니다.

    • 보안 강화를 위해 셸 실행 없음

    • 환경 변수가 적절하게 정리되었습니다.

  3. 오류 처리

    • 허가되지 않은 명령에 대한 포괄적인 오류 처리

    • 디버깅을 위한 오류 메시지 지우기

    • 실패한 명령으로 인해 서버가 충돌하지 않습니다.

  4. 환경 격리

    • 서버는 자체 환경에서 실행됩니다.

    • 환경 변수를 제어할 수 있습니다

    • 제한된 시스템 접근

💻 개발

📁 프로젝트 구조

command-executor/
├─ src/
│  └─ index.ts      # Main server implementation
├─ build/
│  └─ index.js      # Compiled JavaScript
├─ assets/
│  └─ header.svg    # Project header image
└─ package.json     # Project configuration

🐛 디버깅

MCP 서버는 stdio를 통해 통신하므로 디버깅이 어려울 수 있습니다. MCP Inspector 사용을 권장합니다.

npm run inspector

검사기는 브라우저에서 디버깅 도구에 액세스할 수 있는 URL을 제공합니다.

🛠️ 도구 API

서버는 단일 도구를 제공합니다.

실행 명령

미리 승인된 명령을 실행합니다.

매개변수:

  • command (문자열, 필수): 실행할 명령

요청 예시:

{
  "name": "execute_command",
  "arguments": {
    "command": "git status"
  }
}

응답 예시:

{
  "content": [
    {
      "type": "text",
      "text": "On branch main\nNothing to commit, working tree clean"
    }
  ]
}

오류 응답:

{
  "content": [
    {
      "type": "text",
      "text": "Command execution failed: Command not allowed"
    }
  ],
  "isError": true
}

❌ 오류 처리

서버는 다양한 시나리오에 대한 자세한 오류 메시지를 제공합니다.

  1. 허가되지 않은 명령

    {
  "code": "InvalidParams",
  "message": "Command not allowed: [command]. Allowed commands: git, ls, mkdir, cd, npm, npx, python"
}

  2. 실행 실패

    {
  "content": [
    {
      "type": "text",
      "text": "Command execution failed: [error message]"
    }
  ],
  "isError": true
}

🤝 기여하기

  1. 저장소를 포크하세요

  2. 기능 브랜치를 생성하세요

  3. 변경 사항을 커밋하세요

  4. 지점으로 밀어 넣기

  5. 새로운 풀 리퀘스트 만들기

📄 라이센스

이 프로젝트는 MIT 라이선스에 따라 라이선스가 부여되었습니다. 자세한 내용은 라이선스 파일을 참조하세요.

Available Tools

1 tool
execute_commandC

事前に許可されたコマンドを実行します

ParametersJSON Schema
NameRequiredDescriptionDefault
commandYes実行するコマンド

TDQS

C2.9/5.0
Behavior2/5

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

Without annotations, the description carries the full burden. It mentions 'pre-authorized commands' implying an authorization check, but does not disclose what happens if unauthorized, potential side effects, or return values. This is insufficient for a command execution tool.

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 sentence that is front-loaded and efficient. Every word earns its place with no redundancy or fluff.

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 simplicity (1 parameter, no output schema), the description is minimal. It fails to cover important behavioral aspects like success/failure modes, authorization details, or examples. For a potentially powerful tool, it leaves significant gaps.

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 coverage is 100% with a single parameter 'command' described as '実行するコマンド' (command to execute). The tool description adds the constraint that commands must be pre-authorized, which adds meaning beyond the schema. Baseline of 3 is appropriate as the description adds some value but not extensive detail.

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 verb 'execute' and the resource 'pre-authorized commands', distinguishing it well. It is specific about the pre-authorization constraint, which adds clarity, though no siblings exist to differentiate from.

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, nor any when-not or prerequisites. It merely states what it does without context for appropriate usage.

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
    • Addedexecute_command
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

B3.2/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of confusion between tools. The agent can only select 'execute_command', so disambiguation is perfect.

Naming Consistency5/5

The single tool is named 'execute_command', following a clear verb_noun pattern, which is consistent and intuitive.

Tool Count3/5

One tool is minimal for a command executor. While it covers the core functionality of executing pre-approved commands, it lacks supporting tools for listing or managing commands, making the set feel thin.

Completeness2/5

The tool surface is severely incomplete. It only provides execution but lacks tools to list available commands, check execution status, or retrieve results, which are essential for effective agent interaction.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources

Related MCP Connectors

Related MCP Servers

  • MCP Terminal

    sichang824
    A
    license
    C
    quality
    C
    maintenance
    A server that enables AI assistants to execute terminal commands and retrieve outputs via the Model Context Protocol (MCP).
    3
    26
    MIT

  • MCP Toolkit

    zxfgds
    A
    license
    Not graded
    quality
    D
    maintenance
    A comprehensive Model Context Protocol server implementation that enables AI assistants to interact with file systems, databases, GitHub repositories, web resources, and system tools while maintaining security and control.
    42 npm
    2
    MIT

  • Code Sandbox MCP Server

    philschmid
    A
    license
    B
    quality
    D
    maintenance
    A secure Model Context Protocol server that allows AI assistants and LLM applications to safely execute Python and JavaScript code snippets in containerized environments.
    2
    204
    MIT

Appeared in Searches