Skip to main content
Glama
enesjakozh
deepsuthar496

Remote Command MCP Server

by deepsuthar496
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

원격 명령 MCP 서버

다양한 운영 체제에서 원격 명령 실행을 지원하는 모델 컨텍스트 프로토콜(MCP) 서버입니다. 이 서버는 셸 명령을 실행하기 위한 통합 인터페이스를 제공하여 Windows와 Unix 계열 시스템 간의 플랫폼별 차이점을 자동으로 처리합니다.

특징

  • 크로스 플랫폼 명령 실행

  • Windows와 Unix 간 자동 명령 정규화

  • 내장된 오류 처리 및 출력 스트리밍

  • 작업 디렉토리 사양 지원

  • 플랫폼별 셸 선택

Related MCP server: MCP Shell Server

설치

  1. 저장소를 복제합니다.

지엑스피1

  1. 종속성 설치:

npm install

  1. 서버를 빌드하세요:

npm run build

  1. 설정 파일에서 MCP 서버를 구성하세요.

VSCode Cline 확장 프로그램( cline_mcp_settings.json )의 경우:

{
  "mcpServers": {
    "remote-command": {
      "command": "node",
      "args": ["path/to/remote-command-server/build/index.js"],
      "disabled": false,
      "autoApprove": []
    }
  }
}

용법

서버는 호스트 머신에서 모든 유효한 셸 명령을 실행할 수 있는 execute_remote_command 라는 단일 도구를 제공합니다. 여기에는 다음이 포함됩니다.

  • 시스템 명령

  • 패키지 관리자 명령어(apt, yum, chocolatey 등)

  • 개발 도구(git, npm, python 등)

  • 파일 작업

  • 네트워크 명령

  • 서비스 관리

  • 그리고 시스템에서 사용 가능한 다른 CLI 명령

도구: execute_remote_command

매개변수:

  • command (필수): 호스트 OS에서 실행할 수 있는 유효한 셸 명령

  • cwd (선택 사항): 명령 실행을 위한 작업 디렉토리

예시

  1. 시스템 정보:

<use_mcp_tool>
<server_name>remote-command</server_name>
<tool_name>execute_remote_command</tool_name>
<arguments>
{
  "command": "systeminfo"  // Windows
  // or "uname -a"        // Linux
}
</arguments>
</use_mcp_tool>

  1. 패키지 관리:

<use_mcp_tool>
<server_name>remote-command</server_name>
<tool_name>execute_remote_command</tool_name>
<arguments>
{
  "command": "npm list -g --depth=0"  // List global NPM packages
}
</arguments>
</use_mcp_tool>

  1. 네트워크 운영:

<use_mcp_tool>
<server_name>remote-command</server_name>
<tool_name>execute_remote_command</tool_name>
<arguments>
{
  "command": "netstat -an"  // Show all network connections
}
</arguments>
</use_mcp_tool>

  1. Git 작업:

<use_mcp_tool>
<server_name>remote-command</server_name>
<tool_name>execute_remote_command</tool_name>
<arguments>
{
  "command": "git status",
  "cwd": "/path/to/repo"
}
</arguments>
</use_mcp_tool>

  1. 파일 작업:

<use_mcp_tool>
<server_name>remote-command</server_name>
<tool_name>execute_remote_command</tool_name>
<arguments>
{
  "command": "ls -la",  // List files with details
  "cwd": "/path/to/directory"
}
</arguments>
</use_mcp_tool>

  1. 프로세스 관리:

<use_mcp_tool>
<server_name>remote-command</server_name>
<tool_name>execute_remote_command</tool_name>
<arguments>
{
  "command": "ps aux"  // List all running processes (Unix)
  // or "tasklist"     // Windows equivalent
}
</arguments>
</use_mcp_tool>

  1. 서비스 제어:

<use_mcp_tool>
<server_name>remote-command</server_name>
<tool_name>execute_remote_command</tool_name>
<arguments>
{
  "command": "systemctl status nginx"  // Check service status (Linux)
  // or "sc query nginx"               // Windows equivalent
}
</arguments>
</use_mcp_tool>

보안 고려 사항

이 서버는 모든 시스템 명령을 실행할 수 있으므로 다음 보안 관행을 고려해 주시기 바랍니다.

  1. 액세스 제어 : MCP 서버에 대한 액세스를 신뢰할 수 있는 사용자에게만 제한합니다.

  2. 명령 검증 : 애플리케이션 로직에서 실행하기 전에 명령을 검증합니다.

  3. 작업 디렉토리 : cwd 매개변수를 사용하여 명령 실행을 특정 디렉토리로 제한합니다.

  4. 환경 : 시스템 설정이나 중요한 파일을 수정하는 명령에는 주의하세요.

  5. 권한 : 적절한 사용자 권한으로 MCP 서버를 실행합니다.

크로스 플랫폼 명령 처리

서버는 플랫폼별 차이점을 자동으로 처리합니다.

  1. 명령어 번역:

    • ls ⟷ dir (플랫폼에 따라 자동 변환)

    • 각 플랫폼에 적합한 파이프 연산자 형식

  2. 쉘 선택:

    • Windows: cmd.exe 사용

    • Unix/Linux: /bin/sh 사용

오류 처리

서버는 자세한 오류 메시지를 제공하고 응답에 stdout과 stderr를 모두 포함합니다. 명령이 실패하면 오류 원인에 대한 자세한 정보가 포함된 오류 메시지를 받게 됩니다.

오류 응답 예:

{
  "content": [
    {
      "type": "text",
      "text": "Command execution error: Command failed with exit code 1"
    }
  ],
  "isError": true
}

개발

프로젝트 구조

remote-command-server/
├── src/
│   └── index.ts    # Main server implementation
├── package.json
├── tsconfig.json
└── README.md

건물

npm run build

이렇게 하면 TypeScript 코드가 컴파일되고 build 디렉토리에 실행 파일이 생성됩니다.

기여하다

  1. 저장소를 포크하세요

  2. 기능 브랜치를 생성합니다( git checkout -b feature/amazing-feature )

  3. 변경 사항을 커밋하세요( git commit -m 'Add some amazing feature' )

  4. 브랜치에 푸시( git push origin feature/amazing-feature )

  5. 풀 리퀘스트 열기

특허

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

Available Tools

1 tool
execute_remote_commandC

Execute a command on the host machine

NameRequiredDescriptionDefault
commandYesCommand to execute
cwdNoWorking directory for command execution

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 for behavioral disclosure. It mentions execution but doesn't describe permissions required, whether commands run asynchronously, timeout behavior, error handling, or output format. For a potentially dangerous remote execution tool, this is a significant gap.

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 states the core functionality without unnecessary words. It's appropriately sized and front-loaded with the essential information.

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 tool that executes remote commands with no annotations and no output schema, the description is insufficient. It doesn't address critical aspects like security implications, execution environment, error conditions, or what the tool returns. The combination of high-risk functionality and minimal description creates 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 description coverage is 100%, so the schema already documents both parameters (command and cwd) adequately. The description doesn't add any additional meaning about parameter usage beyond what's in the schema, meeting the baseline for high schema coverage.

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 target ('command on the host machine'), providing a specific verb+resource combination. It doesn't need to differentiate from siblings since none exist, but it could be more specific about what types of commands or hosts are supported.

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?

No guidance is provided on when to use this tool versus alternatives or what prerequisites might be needed. The description states what it does but offers no context about appropriate use cases, security considerations, or limitations.

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 update
    • First observedexecute_remote_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

B3/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or confusion between tools. The tool's purpose is singular and clearly defined.

Naming Consistency5/5

Since there is only one tool, it inherently maintains consistency. The naming follows a clear verb_noun pattern (execute_remote_command).

Tool Count2/5

A single tool is too few for a server named 'Remote Command MCP Server', which suggests a broader scope for remote command execution. This minimal set limits functionality and may cause agent failures due to lack of supporting operations.

Completeness1/5

The tool surface is severely incomplete. It only provides command execution with no support for listing available commands, checking command status, handling outputs, or managing remote sessions, which are essential for the domain.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

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

  • SSH MCP Server

    mfangtao
    A
    license
    B
    quality
    C
    maintenance
    A server that enables remote command execution over SSH through the Model Context Protocol (MCP), supporting both password and private key authentication.
    1
    9 npm
    2
    MIT

  • SSH MCP Server

    vilasone455
    F
    license
    A
    quality
    D
    maintenance
    A local Model Context Protocol server that allows LLMs to securely execute shell commands on remote Linux and Windows systems via SSH connections.
    6
    4 npm
    2
    -

Appeared in Searches