---
title: "Docker Agent deploy: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/skills/docker-agent-deploy/
description: "Pins Docker's agent serve, share, and eval skill, which refuses a non-loopback listener that has no auth token."
---

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

> Pins Docker's agent serve, share, and eval skill, which refuses a non-loopback listener that has no auth token.

[← Explore all skills](/skills/)

AGENT DEPLOYMENT / Docker

# Docker Agent deploy

Pins Docker's agent serve, share, and eval skill, which refuses a non-loopback listener that has no auth token.

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

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 exposing a Docker Agent as a server (MCP, HTTP API, A2A, ACP, or OpenAI-compatible chat), distributing an agent via an OCI registry with `docker agent share`, or measuring agent quality with `docker agent eval`. Even if the user just says they want to "turn my agent into an MCP server", "let Claude Desktop use my agent", "publish my agent to Docker Hub", "push my agent like an image", or "test my agent in CI", this skill applies. Covers `serve mcp/api/a2a/acp/chat` listen addresses and auth flags, `share push/pull`, eval session JSON format, scoring metrics, and the `--baseline` regression gate.”

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

01 / THE REASONING

## Why this made the selection.

 - The catalogue has docker-agent-run and docker-agent-config from this repository and not the serve, share, and eval skill.
- The file draws a hard line around loopback, auth, and --safety autonomous, and it says GitHub tokens are not forwarded into evals automatically.

### A good fit for

 - Exposing an existing Docker Agent on loopback with an auth token, or gating an eval on a baseline rather than an absolute score

### Weigh up before choosing

 - This review did not execute the resource.
- npx skills add docker/skills prompts for skills and agents; it is not a docker-agent-deploy-only command. The README's one-skill example names docker-compose-patterns.
- The skill says it was verified against Docker CLI 29.7.2 and that Docker's docs default --safety to restricted. Neither was checked.
- references/eval-format.md, references/sources.md, and checks/verification.md were not opened.

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-deploy/SKILL.md
- README.md
- LICENSE

### Our findings

 - The skill says each serve mode defaults to a loopback address and that a non-loopback bind without an auth token or key is refused.
- It says --insecure-no-auth is an exception, never a default, and that --safety must not be raised to autonomous on a network-reachable listener.
- It says GITHUB_TOKEN and GH_TOKEN are not forwarded into eval containers automatically, and that a baseline or run with zero evaluations is rejected rather than treated as passing.

### Not established by this review

 - The resource was not executed and its tools were not called.
- docker agent serve, share, and eval were not run.
- No listener was bound and no registry push was made.
- The eval-format reference was not opened.
- 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 quick start is the command above, and it says the command prompts for which skills and which agents to install.
- The README lists docker-agent-deploy in the Docker Agent product row.
- The same README shows /plugin install docker-skills@docker for Claude Code, which installs the plugin rather than this one file.

### Before you start

 - A skills-compatible agent or the skills CLI
- The docker-agent CLI if the skill's commands are followed, which this review did not install

### Compatibility

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

### Implementation

shell

### Local skill text plus optional Docker Agent and registry credentials

 - Read the skill
- Serve an agent only if the operator runs docker agent serve
- Push or pull an agent only with the operator's registry login

### Cost model

Apache-2.0; no docker agent command was run

04 / FOLLOW THE EVIDENCE

## The source trail.

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

 - [docker-agent-deploy SKILL.md ↗](https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-agent-deploy/SKILL.md) Checked 2026-10-14 https://github.com/docker/skills/blob/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-agent-deploy/SKILL.md Supports: loopback auth refusal, safety limit, and eval token boundary
- [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: npx skills add docker/skills and the docker-agent-deploy catalog row
- [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-W21 source re-review at the existing pin ↗](https://raw.githubusercontent.com/docker/skills/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-agent-deploy/SKILL.md) Checked 2026-10-15 https://raw.githubusercontent.com/docker/skills/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-agent-deploy/SKILL.md Supports: upstreamDescription, review.notTested, review.reviewedAt
- [2026-10-15 C2-W21 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 Platform Eval Flywheel ↗ Evaluates and iterates on Google Cloud Agent Platform models and agents, with a confirmation card before every billed evaluation run.](/skills/google-agent-platform-eval-flywheel/)[### Anthropic Skill Creator ↗ Develops skills from realistic task fixtures and baseline comparisons, with separate trigger-description experiments and human output review.](/skills/anthropics-skill-creator/)[### Arize Evaluator ↗ Creates and runs Arize LLM-as-judge and code evaluators through the ax CLI, with a rule against fabricating scores.](/skills/arize-ai-arize-evaluator/)

 [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/)
