CLI MCP Server

@anjumanraut

リポジトリ

基本情報

カテゴリ

開発者ツール

トランスポート

stdio

作者

anjumanraut

CLI MCP Server について

A simplified MCP server for terminal command execution

CLI MCP Server の設定

標準の設定はありません

このサーバーの README には解析可能な MCP 設定ブロックが含まれていません。インストール手順はリポジトリをご確認ください。

リポジトリ

CLI MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is CLI MCP Server?

CLI MCP Server is a Model Context Protocol (MCP) server implementation that allows MCP-compatible AI assistants to execute terminal commands in specified directories. It is for developers who want to let AI assistants run shell commands within controlled, user-defined paths.

How to use CLI MCP Server?

Install Node.js v16+ and npm v7+, then clone the repo and run npm install. Start the server by passing allowed directory paths as arguments to start-server.sh (macOS/Linux) or start-server.bat (Windows). Configure Claude by adding the server to its claude_desktop_config.json with the server path and allowed directories.

Key features of CLI MCP Server

Executes terminal commands via MCP-compatible AI assistants
Only allows commands in user-specified directories
Includes path validation to prevent unauthorized access
Cross-platform support (macOS, Linux, Windows)
Configurable with Claude Desktop via JSON configuration

Use cases of CLI MCP Server

Let Claude run file operations or scripts in a project directory
Automate development tasks like builds or tests through AI conversation
Execute system commands in a sandboxed, path-restricted environment

よくある質問

What directories can the server access?

Only directories provided as command-line arguments when starting the server. The server validates paths to block access outside those directories.

What runtime does CLI MCP Server require?

Node.js v16 or higher and npm v7 or higher.

How do I configure Claude to use this server?

Add an entry under `mcpServers` in Claude’s configuration file (e.g., `claude_desktop_config.json`) pointing to the server start script and listing allowed directory paths.

Are there security restrictions?

Yes. The server only executes commands in explicitly allowed directories and performs path validation. The README advises using a dedicated low‑permission user and reviewing all executed commands.

What transport or authentication does the server use?

The README does not mention transport or authentication details.

「開発者ツール」の他のコンテンツ

Casefile

azimov777

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

offprompt

MCP server that lets Claude Code, Cursor or Codex ask you for API keys on a local page and write them to .env. The agent only ever sees key names.

Launchdog

Devin Starks

Launch your product from your AI agent. Connect Claude Code, Codex, Cursor or ChatGPT to Launchdog over MCP and your agent drafts the listing, picks a launch week and books it. 50 launches a week, ranked only by human vo

FARPY

mangomunchr

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

Cronwatch

cronwatchdev

CronWatch records every run of your scheduled jobs in your own database, and speaks up when one is missed, fails, gets stuck, runs slow or costs too much. CronWatch is free and open-source.