CLI MCP Server

@MladenSU

リポジトリ

基本情報

カテゴリ

開発者ツール

ライセンス

MIT

トランスポート

stdio

作者

MladenSU

CLI MCP Server について

Command line interface for MCP clients with secure execution and customizable security policies

CLI MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "cli-mcp-server": {
      "command": "npx",
      "args": [
        "@smithery/cli",
        "install",
        "cli-mcp-server",
        "--client",
        "claude"
      ]
    }
  }
}

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。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is CLI MCP Server?

A secure Model Context Protocol (MCP) server that enables controlled command-line execution with robust security measures including command whitelisting, path validation, and execution controls. It is designed to provide safe CLI access for LLM applications while maintaining security.

How to use CLI MCP Server?

Install via Smithery (npx @smithery/cli install cli-mcp-server --client claude) or manually with uv/uvx. Configure required environment variable ALLOWED_DIR; optional variables set allowed commands/flags, timeouts, and shell operator behaviour. Add the server to Claude Desktop’s claude_desktop_config.json. The server exposes two tools: run_command and show_security_rules.

Key features of CLI MCP Server

Secure command execution with strict validation
Configurable command and flag whitelisting with 'all' option
Path traversal prevention and validation
Shell operator injection protection (opt‑in)
Execution timeouts and command length limits
Async operation support
Working directory restriction and validation

Use cases of CLI MCP Server

Provide controlled CLI access from AI assistant applications
Execute whitelisted system commands safely within a confined directory
Allow LLMs to run commands like ls, cat, pwd, echo without full shell access

よくある質問

What tools does CLI MCP Server provide?

Two tools: `run_command` to execute whitelisted commands, and `show_security_rules` to display current security configuration and restrictions.

What configuration is required?

`ALLOWED_DIR` is required. Default values: `ALLOWED_COMMANDS=ls,cat,pwd`, `ALLOWED_FLAGS=-l,-a,--help`, `MAX_COMMAND_LENGTH=1024`, `COMMAND_TIMEOUT=30`, `ALLOW_SHELL_OPERATORS=false`.

How does command whitelisting work?

Set `ALLOWED_COMMANDS` and `ALLOWED_FLAGS` to a comma‑separated list of allowed commands/flags, or to `'all'` to allow any command/flags.

What security measures are implemented?

Command whitelist enforcement, flag validation, path traversal prevention, shell operator blocking (can be enabled), command length limits, execution timeouts, working directory restrictions, and symlink resolution/validation.

How can I install CLI MCP Server for Claude Desktop?

Via Smithery: `npx @smithery/cli install cli-mcp-server --client claude`. Alternatively, manually add the server configuration with `uv` or `uvx` in `claude_desktop_config.json`.

「開発者ツール」の他のコンテンツ

Eddyter AI Rich Text Editor MCP

EddyterAI

Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R

discoverGPT

Joe Monastiero

discoverGPT is visualAI's MCP gateway for AI commerce: one connection gives Claude 40 tools spanning product search, data-quality review, AI-discovery feeds, and virtual try-on, all backed by a single canonical product c

OrangePro

Aamir Siddiqui

OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

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

Foremerge

naw103

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.