---
title: "Docker Agent run: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/skills/docker-agent-run/
description: "Pins Docker's skill for docker agent run, including the safety modes and the exception that a local stdio MCP server stays outside the sandbox VM."
---

# Docker Agent run: review, setup & limitations · Undominated.ai

> Pins Docker's skill for docker agent run, including the safety modes and the exception that a local stdio MCP server stays outside the sandbox VM.

[← Explore all skills](/skills/)

AGENT DEVELOPMENT / Docker

# Docker Agent run

Pins Docker's skill for docker agent run, including the safety modes and the exception that a local stdio MCP server stays outside the sandbox VM.

 [See setup guidance ↓](#setup)[Original source ↗](https://github.com/docker/skills/tree/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-agent-run)

SOURCE REVIEW

 Reviewed 2026-10-15
 Evidence 5 linked sources
 Publisher Docker
 Licence [Apache-2.0 ↗](https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/LICENSE)
 Revision f79172733725
 [Read what was—and wasn’t—checked ↓](#review)

“Use this skill when running a Docker Agent with `docker agent run`, choosing a safety/approval mode, using the `--sandbox` isolation flag, setting up aliases, or troubleshooting a run (missing credentials, worktrees). Even if the user just says they want to "run my agent", "make my agent auto-approve tool calls", "run this agent safely", or "why can't my agent see my API key", this skill applies. Covers `--safety` (strict/balanced/restricted/autonomous), `--yolo`, `--sandbox` and its network allowlist, `--worktree`, `docker agent alias`, and `docker agent doctor`.”

 [Docker · upstream description ↗](https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-agent-run/SKILL.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - The catalogue has Docker's agent-config and sandbox-credential skills and not this run skill.
- The file says unattended runs should use restricted rather than autonomous, and it states that sandboxes are reused across runs.

### A good fit for

 - Choosing a docker agent run safety mode, or checking whether a local MCP server is inside the sandbox

### Weigh up before choosing

 - This review did not execute the resource.
- The README's non-interactive example installs docker-compose-patterns, not docker-agent-run. The general add command prompts for which skills.
- The skill's references and assets directories were not opened. Compatibility with Docker Desktop 4.63+ and Docker CLI 29.7.2 is the file's statement and was not checked against an installed CLI.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - skills/docker-agent-run/SKILL.md
- README.md
- LICENSE

### Our findings

 - The skill defines strict, balanced, restricted, and autonomous safety modes, and it says autonomous is equivalent to --yolo.
- It says not to default an unattended run to autonomous or --yolo, and to use restricted so an unexpected tool call fails closed.
- It says --sandbox keeps built-in toolsets in a microVM, with the exception that a local stdio MCP server still runs as a host process, and that sandboxes are reused rather than torn down at the end of a session.

### Not established by this review

 - The resource was not executed and its tools were not called.
- docker agent run was not invoked.
- No sandbox was started.
- Not executed: it was not installed or run.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Add a skill to your workflow.

[Upstream setup instructions ↗](https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/README.md)

DOCUMENTED COMMAND

 npx skills add docker/skills Copy command ↗

Run in your terminal to choose your AI tools, project or global scope, and installation method. This short command follows the current upstream version; the review covers the revision shown above.

 - The README's quick start is the command above and says it prompts for which skills and agents.
- A non-interactive example on the next lines names docker-compose-patterns, not docker-agent-run.
- The product table describes docker-agent-run as the skill for safety modes, sandbox isolation, aliases, worktrees, and troubleshooting.

### Before you start

 - A skills-compatible agent
- The docker-agent CLI plugin if the commands are run, which the skill says needs Docker Desktop 4.63+ or a standalone install
- The sbx CLI if --sandbox is used

### Compatibility

Claude Code · OpenAI Codex · Cursor · GitHub Copilot · Gemini CLI · OpenCode · Windsurf · Cline · Kiro

### Implementation

shell

### Local run guidance; sandbox does not cover a declared stdio MCP server

 - Read the skill
- Run docker agent only if the operator invokes it
- Treat a local stdio MCP server as a host process, as the skill states

### Cost model

Apache-2.0; Docker Agent was not started

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [docker-agent-run SKILL.md ↗](https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-agent-run/SKILL.md) Checked 2026-10-14 https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-agent-run/SKILL.md Supports: safety modes and sandbox MCP exception
- [Repository README ↗](https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/README.md) Checked 2026-10-14 https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/README.md Supports: install line and docker-agent-run table text
- [Repository LICENSE ↗](https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/LICENSE) Checked 2026-10-14 https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/LICENSE Supports: Apache License Version 2.0
- [2026-10-15 C2-W22 source re-review at the existing pin ↗](https://raw.githubusercontent.com/docker/skills/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-agent-run/SKILL.md) Checked 2026-10-15 https://raw.githubusercontent.com/docker/skills/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-agent-run/SKILL.md Supports: upstreamDescription, review.notTested, review.reviewedAt
- [2026-10-15 C2-W22 source re-review at the existing pin ↗](https://raw.githubusercontent.com/docker/skills/f79172733725e2fd236343ee7b963c446ed85d09/README.md) Checked 2026-10-15 https://raw.githubusercontent.com/docker/skills/f79172733725e2fd236343ee7b963c446ed85d09/README.md Supports: install.command

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### Agent Development for Claude Code Plugins ↗ Explains how to write a Claude Code plugin agent file (frontmatter, trigger description, system prompt) and ships a Bash script that checks one agent file.](/skills/anthropic-agent-development/)[### Cloudflare Agents SDK ↗ Guides stateful Cloudflare agent applications through current SDK documentation, persistence, scheduling and approval-aware tool flows.](/skills/cloudflare-agents-sdk/)[### Context engineering ↗ Orders agent context as a hierarchy instead of dumping the repository into the prompt.](/skills/addyosmani-context-engineering/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Choose a toolkit](/tools/)
- [Inspect execution hosts](/agents/)
- [Check tool access](/mcp-servers/)
- [Check project dependencies](/check-repo/)
