data-ai MCP Server
🚀 One sentence → your one-person company of AI experts → complete deliverable in minutes. 276 CN + 184 EN + 5 more languages (ko/ru/pt-BR/id/ar) · zero-code YAML · auto-verified acceptance · Web Studio / Desktop / Docker · 15 LLM providers (11 key-free). 一句话组建你的「一人公司」AI 专家团队,几分钟交付完整方案;验收自动核验,网页 / 桌面 / Docker 全渠道。
Discovered via github-seeds:mcp-hot and last synced 1d ago.
1. Install the package
npx agency-orchestrator serve
2. Add to claude_desktop_config.json
{
"mcpServers": {
"agency-orchestrator": {
"command": "npx",
"args": [
"agency-orchestrator",
"serve"
]
}
}
}Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows)
否
string
string
array
**自定义 API(智谱、月之暗面、硅基流动等 OpenAI 兼容 API):** ```bash ao init --provider openai --model 模型名 \ --base-url https://你的API地址/v1 \ --api-key 你的key ``` 或手动编辑 `.env`: ```env AO_PROVIDER=openai AO_MODEL=模型名 OPENAI_BASE_URL=https://你的API地址/v1 OPENAI_API_KEY=你的key ``` 常见示例:
string
string
model
array
number
string
否
string[]
string
object
`provider: "deepseek"`
string
string
string
> ⚠️ 注意:这些平台请使用 `provider: "openai"`,不要用 `provider: "ollama"`。Ollama 仅用于本地模型,不发送 API Key。 > 💡 **网页 Studio 里更简单**:「供应商」面板支持直接**添加自定义供应商**(任意 OpenAI 兼容 endpoint,带 SiliconFlow / OpenRouter / 火山方舟 / 智谱 / Kimi 等常见预设,点一下自动填 base_url),加完即可在顶部下拉切换使用。Claude Code / Gemini CLI / Codex 卡片还支持配置**第三方中转**(填中转商的 base_url + token,跳过官方账号登录)。 ## CLI 命令 ```bash ao demo # 零配置体验多智能体协作 ao init # (可选)复制 276 个中文角色到本地以便编辑 ao init --lang en # (可选)复制 191 个英文角色到本地以便编辑 ao init --workflow # 交互式创建工作流 ao compose "一句话描述" # AI 智能编排工作流 ao compose "一句话描述" --run # 编排并立即执行 ao team save <workflow.yaml> # 把角色阵容存成可复用团队 (Loadout) ao team list / show / rm # 管理已保存的团队 ao run --team <名字> "新任务" # 用已保存的团队跑新任务(锁定阵容) ao prompt optimize "提示词" # AI 优化提示词(--save 存为可复用资产) ao prompt test / list / garden # 测试 / 管理 / 起手模板(提示词沉淀) ao skills [名字] # 列出/查看可挂到步骤的方法论 skill ao run <workflow.yaml> [选项] # 执行工作流 ao validate <workflow.yaml> # 校验(不执行) ao plan <workflow.yaml> # 查看执行计划(DAG) ao explain <workflow.yaml> # 用自然语言解释执行计划 ao roles # 列出所有角色 ao serve # 启动 MCP Server(供 Claude Code / Cursor 调用) ```
string
> **需要代理才能访问的官方 API(OpenAI / Gemini / xAI / Claude 等)**:AO 会读 `HTTPS_PROXY` / `HTTP_PROXY` / `ALL_PROXY` 自动走代理—— > Node 的 `fetch` 默认**不读**这些变量,这正是"curl 能通、AO 连不上"的头号原因,AO 替你接上了。 > 本机地址(`localhost` / `127.0.0.1` 等)**永远直连**,不会被绕进代理,所以 Ollama、Studio 自身不受影响; > 你自己写的 `NO_PROXY` 会被保留。想彻底关掉这层接管:`AO_NO_PROXY=1`。 > 这几家都**不预设默认模型**(各家模型编码互不通用,写死一个就是给你埋一个"跑起来才发现模型不存在"): > 在 YAML 里写 `model:`,或在 Studio 供应商页配好 key 后点「获取模型列表」拉真实全量。 > Gemini 的 key 变量名**特意不叫 `GEMINI_API_KEY`**——那个名字被 gemini-cli 占着,共用会把你本机的 CLI 一起改道。 **自定义 API(智谱、月之暗面、硅基流动等 OpenAI 兼容 API):** ```bash ao init --provider openai --model 模型名 \ --base-url https://你的API地址/v1 \ --api-key 你的key ``` 或手动编辑 `.env`: ```env AO_PROVIDER=openai AO_MODEL=模型名 OPENAI_BASE_URL=https://你的API地址/v1 OPENAI_API_KEY=你的key ``` 常见示例:
Reduce container attack surface by building application images on Google distroless base images that contain only the application runtime with no shell, package manager, or unnecessary OS utilities.
Investigate compromised Docker containers by analyzing images, layers, volumes, logs, and runtime artifacts to identify malicious activity and evidence.
Harden the Docker daemon by configuring daemon.json with user namespace remapping, TLS authentication, rootless mode, and CIS benchmark controls.
Container escape is a critical attack technique where an adversary breaks out of container isolation to access the host system or other containers. Detection involves monitoring for escape indicators
AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
ToolJet is the open-source foundation of ToolJet AI - the enterprise app generation platform for building internal tools, dashboard, business applications, workflows and AI agents 🚀
Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation.
Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation.
Learn how to use the Redis Manager Claude skill. Complete guide with installation instructions and examples.
Learn how to use the Privacy Search Claude skill. Complete guide with installation instructions and examples.
Learn how to use the Clawboard Claude skill. Complete guide with installation instructions and examples.