MCP CLI

@gelisam

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

gelisam

MCP CLI について

a simple MCP server allowing VS Code to run a specific shell command without asking

#mcp-cli#shell-command#ai-assistant

MCP CLI 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

MCP CLI 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 MCP CLI?

MCP CLI is a Model Context Protocol (MCP) server that exposes shell commands as tools for AI assistants such as GitHub Copilot. It lets users maintain a list of allowed shell commands, so each tool only needs to be authorized once for improved security.

How to use MCP CLI?

Install via cabal install, then create a JSON configuration file listing the allowed commands with optional names, descriptions, arguments, and working directories. In VS Code Agent mode, add it as a stdio MCP server using the command mcp-cli <path-to-config>.

Key features of MCP CLI

Exposes shell commands as MCP tools for AI assistants.
Restricts allowed commands to a preconfigured list.
Supports named tools with custom descriptions.
Allows passing arguments as environment variables.
Configurable working directory per tool.
Top-level and tool-specific environment variables.

Use cases of MCP CLI

Running build commands or test suites via an AI assistant.
Executing database connection scripts with specific parameters.
Automating git operations with custom arguments.
Running approved diagnostic commands like date, pwd, ls.
Controlling which shell commands an AI assistant may execute.

よくある質問

How does MCP CLI differ from allowing GitHub Copilot to run arbitrary shell commands?

MCP CLI lets you predefine a list of allowed commands, so you only authorize each tool once instead of being asked per execution, improving security and convenience.

What runtime is required to install MCP CLI?

The README shows installation via `cabal install`, indicating a Haskell build environment. No other runtime dependencies are mentioned.

How is the configuration file structured?

The JSON file lists commands as strings or objects. Objects can specify a name, description, command with argument placeholders, an arguments array, working directory, and environment variables.

What transport does MCP CLI use?

It uses the MCP stdio transport, as configured in `.vscode/mcp.json` with `"type": "stdio"`.

Where does the MCP CLI configuration file live?

The configuration file path is provided as an argument when starting the server, typically stored in the workspace folder (e.g., `${workspaceFolder}/mcp-cli.json`).

「開発者ツール」の他のコンテンツ

Capgo MCP

Cap-go

Console, Backend and CLI to manage Capgo Instant update and Native build for Capacitor apps Build and upload to app store your mobile app

LastPing

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci

Yocoolab

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

Vibgrate MCP

Vibgrate

Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up

Nebelus

Nebelus is an enterprise agentic-AI platform for regulated industries. This MCP server exposes the Nebelus Construction API: ~48 tools that give an MCP client full agent build parity — create/update/probe agents, edit ag