小智AI-Xiaozhi Mcp Openclaw Official

按小智官方 MCP 接入方式,把小智 AI 设备通过 MCP 接到 OpenClaw / OpenAI-compatible 后端。适用于已经有小智 MCP 接入点(wss://api.xiaozhi.me/mcp/?token=...)的场景。提供一个 `openclaw_query(message)` MCP 工具,让小智在需要外部能力、复杂推理、联网查询或外部智能辅助时调用。 Official XiaoZhi MCP bridge for OpenClaw / OpenAI-compatible backends. Use when you already have a XiaoZhi MCP endpoint and want XiaoZhi to call an external assistant tool such as `openclaw_query(message)`.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "小智AI-Xiaozhi Mcp Openclaw Official" with this command: npx skills add joe12801/xiaozhi-mcp-openclaw-official

xiaozhi-mcp-openclaw-official

简体中文 | English


简体中文

作用

这是一个按小智官方文档方式接入的最小可用 MCP 原型。

数据流:

小智
→ MCP 接入点
→ mcp_pipe.py
→ openclaw_mcp.py
→ OpenAI/OpenAI-compatible 后端
→ 回复文本
→ 小智播报

提供的工具

  • openclaw_query(message)
    • 当用户提到“龙虾机器人”“龙虾”或需要外部能力时,调用这个工具
    • 返回适合语音播报的简短中文结果

启动步骤

  1. 安装依赖:
pip install -r requirements.txt
  1. 复制配置:
cp .env.example .env
  1. 修改 .env
  • MCP_ENDPOINT
  • OPENAI_BASE
  • OPENAI_KEY
  • MODEL
  1. 启动:
python3 mcp_pipe.py openclaw_mcp.py

关键配置项

  • MCP_ENDPOINT:小智 MCP 接入点
  • OPENAI_BASE:OpenAI/OpenAI-compatible 后端地址
  • OPENAI_KEY:后端 key
  • MODEL:模型名(如 gpt-5.4

注意事项

  • 不要把真实 .env 连同密钥一起分享
  • 这是一个原型桥接项目,后续可以继续增强成真正的 OpenClaw 多工具接入版

English

Purpose

This is a minimal working MCP prototype that follows XiaoZhi's official MCP integration style.

Flow:

XiaoZhi
→ MCP endpoint
→ mcp_pipe.py
→ openclaw_mcp.py
→ OpenAI/OpenAI-compatible backend
→ reply text
→ XiaoZhi speaks it

Provided tool

  • openclaw_query(message)
    • Use when the user mentions “龙虾机器人 / Lobster Robot” or when an external capability is needed
    • Returns a short Chinese reply suitable for voice playback

Startup

  1. Install dependencies:
pip install -r requirements.txt
  1. Copy config:
cp .env.example .env
  1. Update .env:
  • MCP_ENDPOINT
  • OPENAI_BASE
  • OPENAI_KEY
  • MODEL
  1. Start:
python3 mcp_pipe.py openclaw_mcp.py

Key config values

  • MCP_ENDPOINT: XiaoZhi MCP endpoint
  • OPENAI_BASE: OpenAI/OpenAI-compatible backend URL
  • OPENAI_KEY: backend API key
  • MODEL: model name (for example gpt-5.4)

Notes

  • Do not publish your real .env or secrets
  • This is a prototype bridge and can later be extended into a richer OpenClaw multi-tool integration

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

通义晓蜜 - 智能外呼

触发阿里云晓蜜外呼机器人任务,自动批量拨打电话。适用于批量外呼、客户回访、满意度调查、简历筛查约面试等场景。可从前置工具或节点获取外呼名单。

Registry SourceRecently Updated
General

Letterboxd Watchlist

Scrape a public Letterboxd user's watchlist into a CSV/JSONL list of titles and film URLs without logging in. Use when a user asks to export, scrape, or mirror a Letterboxd watchlist, or to build watch-next queues.

Registry SourceRecently Updated
General

Seedance Video Generation

Generate AI videos using ByteDance Seedance. Use when the user wants to: (1) generate videos from text prompts, (2) generate videos from images (first frame, first+last frame, reference images), or (3) query/manage video generation tasks. Supports Seedance 1.5 Pro (with audio), 1.0 Pro, 1.0 Pro Fast, and 1.0 Lite models.

Registry SourceRecently Updated
4.2K17jackycser
General

Universal Skills Manager

The master coordinator for AI skills. Discovers skills from multiple sources (SkillsMP.com, SkillHub, and ClawHub), manages installation, and synchronization...

Registry SourceRecently Updated