Skill：agentdock

Secure MCP runtime for AI agents to operate local machines, servers, and containers with multi-device orchestration.

适用场景

招聘人事

适合角色

介绍

以下内容整理自开源仓库 `uvwt/agentdock` 的 README / SKILL.md 摘要：

<div align="center">

English | [简体中文](./README.zh-CN.md)

<img src="./docs/assets/agentdock-logo.png" alt="AgentDock logo" width="128" />

# AgentDock MCP

**Give AI agents secure, controlled access to every machine you operate.**

Open ChatGPT in your browser and manage multiple computers and servers from one conversation. Write code, change configuration, run commands, and deploy in the real environment where the work belongs—without consuming a dedicated Codex coding quota.

[Quick Start](https://uvwt.github.io/agentdock-docs/docs/getting-started/install) · [Documentation](https://uvwt.github.io/agentdock-docs/) · [Releases](https://github.com/uvwt/agentdock/releases) · [Issues](https://github.com/uvwt/agentdock/issues)

[![CI](https://github.com/uvwt/agentdock/actions/workflows/ci.yml/badge.svg)](https://github.com/uvwt/agentdock/actions/workflows/ci.yml)
[![GitHub Release](https://img.shields.io/github/v/release/uvwt/agentdock?display_name=tag&logo=github)](https://github.com/uvwt/agentdock/releases)
[![Docker Hub](https://img.shields.io/docker/pulls/agentdockio/agentdock?logo=docker&label=Docker%20Hub)](https://hub.docker.com/r/agentdockio/agentdock)
[![GHCR](https://img.shields.io/badge/GHCR-ghcr.io%2Fuvwt%2Fagentdock-2496ED?logo=docker&logoColor=white)](https://github.com/uvwt/agentdock/pkgs/container/agentdock)
[![License](https://img.shields.io/github/license/uvwt/agentdock)](./LICENSE)

</div>

<p align="center">
  <img
    src="./docs/assets/agentdock-multi-device.png"
    alt="AgentDock: operate multiple devices from one AI conversation"
    width="100%"
  />
</p>

## What is AgentDock?

AgentDock is an independent tool runtime for AI agents.

It provides unified, secure, and controlled file, command, Git, Skill, MCP, browser automation, and task execution across local computers, remote servers, and containers. Connect multiple AgentDock instances to coordinate work across devices and finish multi-machine workflows in a single conversation.

AgentDock does not provide a chat interface or perform model inference. It focuses on one responsibility:

> Let AI agents operate real environments within explicit permission boundaries and return structured, traceable, and verifiable results.

```text
              ChatGPT / Claude / Codex
                        │
                        │ MCP (multiple instances supported)
          ┌─────────────┼─────────────┐
          ▼             ▼             ▼
   ┌───────────┐ ┌───────────┐ ┌───────────┐
   │ AgentDock │ │ AgentDock │ │ AgentDock │
   │ Local Mac │ │ LAN Host  │ │ Cloud VPS │
   └─────┬─────┘ └─────┬─────┘ └─────┬─────┘
         │             │             │
         ▼             ▼             ▼
   Files · Shell · Git  Tunnels       Proxy · Deploy
```

## What can AgentDock do?

- Manag

---

安装方式

1. 打开仓库：https://github.com/uvwt/agentdock
2. 查找 SKILL.md 或 README 中的安装章节
3. 克隆或下载所需 Skill 子目录到本地 skills 路径（如 `.cursor/skills/` 或 `.claude/skills/`）
4. 重启 / 重载 Agent 客户端
5. 用一条真实任务验证 Skill 是否被正确加载

适用平台

  • Claude
  • Codex

打开详情 · 返回技巧库