@modelcontextprotocol/server Terminal MCP Server

@RichardTheuws

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

RichardTheuws

@modelcontextprotocol/server Terminal MCP Server について

Terminal server implementation for Model Context Protocol

@modelcontextprotocol/server Terminal 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": {
    "terminal": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-terminal"
      ]
    }
  }
}

@modelcontextprotocol/server Terminal 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 @modelcontextprotocol/server-terminal?

@modelcontextprotocol/server-terminal is an MCP server that provides secure, controlled access to terminal commands and npm operations over the Model Context Protocol. It lets AI agents execute shell commands, install packages, and run scripts in a sandboxed environment with configurable security constraints.

How to use @modelcontextprotocol/server-terminal?

Install the package via npm, then add the server to your MCP configuration file. In the config, you define an allowedCommands whitelist, a default timeout, a working directory, and optional environment variables. Once configured, you invoke operations like executeCommand, install, or runScript through the MCP client.

Key features of @modelcontextprotocol/server-terminal

Execute shell commands with full control
Built-in npm operations (install, run scripts)
Timeout handling for long-running commands
Security through an allowed commands list
Environment variables management and working directory control
TypeScript support

Use cases of @modelcontextprotocol/server-terminal

Automate build and test workflows by running npm scripts
Execute safe, predefined shell commands from an AI assistant
Install npm packages and manage dependencies programmatically
Run development servers (npm run dev) or builds (npm run build) via MCP

よくある質問

What commands can the server run?

Only commands listed in the `allowedCommands` configuration array (e.g., npm, node, git) may be executed. This provides a security boundary.

How are long-running commands handled?

The server enforces a configurable `defaultTimeout` (default: 30000 ms). Commands that exceed the timeout are terminated.

What runtime dependencies are required?

Node.js and npm are required. The server itself is installed via npm and runs as a Node.js process.

Where does the server execute commands?

Commands run in the directory specified by `defaultCwd` in the configuration. This can be overridden per invocation via the `cwd` option.

How are environment variables managed?

You can set a base set of environment variables in the configuration under `environmentVariables`. These are passed to every command.

「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

DocuWriter.ai

DocuWriter is an AI-powered platform for creating, updating and managing complete, structured documentation for entire codebases. Teams can connect repositories and generate documentation covering architecture, modules,

Routebase

Routebase keeps your API's design, docs, contract tests, mocks and monitoring in one living OpenAPI spec so they can't drift apart. Agents work on that same source of truth, under your team's permissions.

Moxie Docs

Jackalope-Dev

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

Modelglass

Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott