Container Use MCP — Installieren & Live-Demo

Warum nutzen

Hauptfunktionen

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

Live-Demo

In der Praxis

container-use-mcp.replay ▶ bereit

0/0

Installieren

Wählen Sie Ihren Client

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

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

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.

VS Code → Cline → MCP Servers → Edit

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

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.continue/config.json

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

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json

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

In context_servers hinzufügen. Zed lädt beim Speichern neu.

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

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: Container Use

Try three refactoring approaches in parallel, keep the best

👤 Engineers exploring design space ⏱ ~15 min intermediate

Wann einsetzen: You have 3 different ideas for a refactor and want to see all of them run/pass tests before picking one.

Voraussetzungen

Server/skill installed and authenticated — See repo README

Ablauf

Spin up three isolated envs

Create three container-use environments named refactor-a/b/c, all on this repo at HEAD.✓ Kopiert

→ 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.✓ Kopiert

→ 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.✓ Kopiert

→ Patch applied locally

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

Fallstricke

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

Kombinieren mit: github · filesystem

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

container-use-mcp + github

Pair with github for complementary capabilities

Use this server together with github to complete a multi-step task.✓ Kopiert

container-use-mcp + filesystem

Pair with filesystem for complementary capabilities

Use this server together with filesystem to complete a multi-step task.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen	Kosten
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

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: See provider docs for rate limits
Tokens pro Aufruf: Varies by tool
Kosten in €: See repo README for pricing details
Tipp: Cache tool results and avoid repeated identical calls.

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: Use environment variables; never commit secrets

Datenabfluss: Tool calls go to the provider's API as documented

Fehlerbehebung

Häufige Fehler und Lösungen

docker daemon not running

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

Prüfen: 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.

Prüfen: Check `docker system df`

Alternativen

Container Use vs. andere

Alternative	Wann stattdessen	Kompromiss
Dagger Cloud	You want hosted, multi-tenant agent envs	Paid; container-use is local-first

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen