MCP Terminal Server

@RinardNick

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

RinardNick

MCP Terminal Server について

An MCP server that provides secure terminal access for Claude and other LLMs

#mcp-terminal#secure-terminal#mcp

MCP Terminal 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": {
    "mcp-terminal": {
      "command": "uv",
      "args": [
        "venv"
      ]
    }
  }
}

MCP Terminal 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 MCP Terminal Server?

MCP Terminal Server is a secure terminal execution server implementing the Model Context Protocol (MCP). It provides controlled command execution capabilities with security features and resource limits, designed for use with MCP-based applications like Claude Desktop.

How to use MCP Terminal Server?

Install the package using uv pip install mcp-terminal, then configure Claude Desktop with the command and args fields, specifying allowed commands, timeout, and maximum output size. The server can also be tested with the MCP Inspector tool.

Key features of MCP Terminal Server

Execute shell commands with output capture and error handling
Restrict allowed commands and prevent command injection
Command timeouts and maximum output size limits
Standard MCP message format with capability advertisement
Streaming output support for long-running commands

Use cases of MCP Terminal Server

Running development commands (git, pip, python, ls, cd) through Claude Desktop
Executing controlled shell commands from AI agents via MCP
Automating terminal tasks with enforced security boundaries and resource protection

よくある質問

What commands are allowed by default?

The server does not allow any commands by default; you must specify the allowed commands using the `--allowed-commands` argument.

What are the runtime dependencies?

MCP Terminal Server requires Python and the `uv` package manager. It is designed to work with MCP clients such as Claude Desktop.

How are commands protected from injection?

The server validates commands against a whitelist, blocks shell operators, and prevents command injection attempts.

What resource limits are enforced?

Each command has a configurable timeout (default 30 seconds) and a maximum output size (default 1 MB) to prevent hanging or memory exhaustion.

How does the server communicate?

It implements the Model Context Protocol version 1.0.0, using JSON messages over standard input/output (stdio) with the client.

「開発者ツール」の他のコンテンツ

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