Container Use MCP — Install & Live Demo

Why use it

Key features

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

What it looks like in practice

container-use-mcp.replay ▶ ready

0/0

Install

Pick your client

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

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

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

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

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

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

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

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

Add to context_servers. Zed hot-reloads on save.

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

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use Container Use

Try three refactoring approaches in parallel, keep the best

👤 Engineers exploring design space ⏱ ~15 min intermediate

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

Prerequisites

Server/skill installed and authenticated — See repo README

Flow

Spin up three isolated envs

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

→ 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.✓ Copied

→ 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.✓ Copied

→ Patch applied locally

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

Pitfalls

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

Combine with: github · filesystem

Combinations

Pair with other MCPs for X10 leverage

container-use-mcp + github

Pair with github for complementary capabilities

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

container-use-mcp + filesystem

Pair with filesystem for complementary capabilities

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

Tools

What this MCP exposes

Tool	Inputs	When to call	Cost
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

Cost & Limits

What this costs to run

API quota: See provider docs for rate limits
Tokens per call: Varies by tool
Monetary: See repo README for pricing details
Tip: Cache tool results and avoid repeated identical calls.

Security

Permissions, secrets, blast radius

Credential storage: Use environment variables; never commit secrets

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

Troubleshooting

Common errors and fixes

docker daemon not running

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

Verify: 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.

Verify: Check `docker system df`

Alternatives

Container Use vs others

Alternative	When to use it instead	Tradeoff
Dagger Cloud	You want hosted, multi-tenant agent envs	Paid; container-use is local-first

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills