Container Use MCP — インストール & ライブデモ

なぜ使うのか

主な機能

One isolated container per agent task — no host pollution
Multiple agents work in parallel on the same repo via git worktrees inside containers
Replay, diff, and discard any environment after the fact
Pre-baked language images (node, python, go) or BYO Dockerfile
Works with Claude Code, Cursor, Goose, Aider through the same MCP layer

ライブデモ

実際の動作

container-use-mcp.replay ▶ 準備完了

0/0

インストール

クライアントを選択

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "container-use-mcp": {
      "command": "cu",
      "args": [
        "mcp"
      ]
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config を開く。保存後、アプリを再起動。

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "container-use-mcp": {
      "command": "cu",
      "args": [
        "mcp"
      ]
    }
  }
}

Cursor は Claude Desktop と同じ mcpServers スキーマを使用。プロジェクト設定はグローバルより優先。

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "container-use-mcp": {
      "command": "cu",
      "args": [
        "mcp"
      ]
    }
  }
}

Cline サイドバーの MCP Servers アイコンをクリックし、"Edit Configuration" を選択。

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "container-use-mcp": {
      "command": "cu",
      "args": [
        "mcp"
      ]
    }
  }
}

Claude Desktop と同じ形式。Windsurf を再起動して反映。

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "container-use-mcp",
      "command": "cu",
      "args": [
        "mcp"
      ]
    }
  ]
}

Continue はマップではなくサーバーオブジェクトの配列を使用。

~/.config/zed/settings.json

{
  "context_servers": {
    "container-use-mcp": {
      "command": {
        "path": "cu",
        "args": [
          "mcp"
        ]
      }
    }
  }
}

context_servers に追加。保存時に Zed がホットリロード。

claude mcp add container-use-mcp -- cu mcp

ワンライナー。claude mcp list で確認、claude mcp remove で削除。

ユースケース

実用的な使い方： Container Use

Try three refactoring approaches in parallel, keep the best

👤 Engineers exploring design space ⏱ ~15 min intermediate

使うタイミング： You have 3 different ideas for a refactor and want to see all of them run/pass tests before picking one.

前提条件

Server/skill installed and authenticated — See repo README

フロー

Spin up three isolated envs

Create three container-use environments named refactor-a/b/c, all on this repo at HEAD.✓ コピーしました

→ Three env_ids printed
Apply each approach in its own env

In refactor-a do the strategy-pattern version; in -b inline everything; in -c extract a service object. Run the full test suite in each. Report pass/fail and diff size.✓ コピーしました

→ Per-env test summary and diff stats
Pick the winner and merge

Apply the diff from refactor-b to my working copy. Discard the other two environments.✓ コピーしました

→ Patch applied locally

結果： Three real experiments evaluated side-by-side without ever breaking your host repo.

注意点

Forgetting to discard old envs leaks disk — Forgetting to discard old envs leaks disk — cu environment list then cu environment discard <id> periodically.

組み合わせ： github · filesystem

組み合わせ

他のMCPと組み合わせて10倍の力を

container-use-mcp + github

Pair with github for complementary capabilities

Use this server together with github to complete a multi-step task.✓ コピーしました

container-use-mcp + filesystem

Pair with filesystem for complementary capabilities

Use this server together with filesystem to complete a multi-step task.✓ コピーしました

ツール

このMCPが提供する機能

ツール	入力	呼び出すタイミング	コスト
environment_create	name: str, image: str	Start a fresh sandbox for the next task	Local CPU/disk
environment_run_cmd	env_id, cmd	Execute build/test commands inside the sandbox	free
environment_file_write	env_id, path, contents	Apply edits without touching the host	free
environment_diff	env_id	Review the agent's work before merging back	free

コストと制限

運用コスト

APIクォータ: See provider docs for rate limits
呼び出しあたりのトークン: Varies by tool
金額: See repo README for pricing details
ヒント: Cache tool results and avoid repeated identical calls.

セキュリティ

権限、シークレット、影響範囲

認証情報の保管： Use environment variables; never commit secrets

データ送信先： Tool calls go to the provider's API as documented

トラブルシューティング

よくあるエラーと対処法

docker daemon not running

Container Use requires a local Docker or compatible runtime. Start Docker Desktop or colima.

確認： Run `docker ps` successfully

out of disk

Old environments aren't auto-pruned. Run cu environment list then cu environment discard <id> for anything older than a day.

確認： Check `docker system df`

代替案

Container Use 他との比較

代替案	代わりに使う場面	トレードオフ
Dagger Cloud	You want hosted, multi-tenant agent envs	Paid; container-use is local-first

その他

リソース

📖 GitHub の公式 README を読む

🐙 オープンな issue を見る

🔍 400以上のMCPサーバーとSkillsを見る