← 返回 Skills 市场
Xiaozhi Mcp Server
作者
elegant1998
· GitHub ↗
· v2.0.8
· MIT-0
248
总下载
0
收藏
1
当前安装
10
版本数
在 OpenClaw 中安装
/install xiaozhi-mcp-server
功能描述
让小智智能盒子连接OpenClaw,成为你的智能语音助手
安全使用建议
This skill appears to do what it says (bridge Xiaozhi to OpenClaw), but review a few things before installing: 1) inspect scripts/start.sh — it may auto-install Python packages globally using pip3 --break-system-packages; consider running inside a virtualenv or container instead. 2) ensure you trust and have the 'openclaw' CLI installed (server.py calls 'openclaw agent'); otherwise the service will fail. 3) start.sh contacts ifconfig.me to fetch a public IP at startup (no data exfiltration visible, but it's an external network call). 4) check the generated token file at ~/.config/openclaw-mcp/token and the target_session setting to avoid accidentally delivering replies to the wrong account. 5) the package.json metadata is slightly inconsistent (lists Python deps), which looks like sloppy packaging but not necessarily malicious. If you need higher assurance, ask the author for a packaged install or run the server in an isolated environment and audit runtime behavior (network endpoints, spawned processes).
功能分析
Type: OpenClaw Skill
Name: xiaozhi-mcp-server
Version: 2.0.8
The skill bundle is a legitimate integration between Xiaozhi smart speakers and the OpenClaw AI assistant. The core logic in `scripts/server.py` implements an MCP server that forwards voice commands to the OpenClaw CLI using safe `subprocess.run` calls (avoiding shell injection) and includes a `sanitize_message` function to filter input. The bundle includes standard setup scripts, configuration files, and ESP32 client code that align perfectly with the stated purpose of providing a voice-to-AI bridge.
能力评估
Purpose & Capability
The code implements an HTTP /mcp endpoint, a WebSocket /ws endpoint, token generation under ~/.config/openclaw-mcp/token, and a run_agent tool that calls the local 'openclaw agent' CLI — all consistent with a MCP server that forwards Xiaozhi voice input to OpenClaw. Minor incoherence: package.json lists Python packages under npm-style dependencies and the project expects a system 'openclaw' CLI which is not declared in metadata.
Instruction Scope
SKILL.md only instructs running scripts/start.sh and configuring the device; actual start.sh will create config.yaml if missing, interactively prompt for target_session, auto-generate a token file, and may install Python deps. The runtime server reads/writes files under the user's home (~/.config/openclaw-mcp) and runs the 'openclaw' CLI — these are within scope for this integration but are not fully documented in SKILL.md.
Install Mechanism
There is no formal install spec in registry metadata (instruction-only), but scripts/start.sh can auto-install Python packages using pip3 with --break-system-packages (global install). That modifies the host Python environment without isolating dependencies (no virtualenv). The script also queries an external service (ifconfig.me) to determine public IP and prints it; contacting that external endpoint on start is a modest privacy/operational concern.
Credentials
The skill does not declare required credentials or config paths beyond its own ~/.config/openclaw-mcp token and a local config.yaml. The code uses an optional environment variable XIAOZHI_MCP_PORT to override the port; this is proportional. No unrelated third-party credentials are requested.
Persistence & Privilege
always is false and the skill does not request elevated platform privileges. It writes state under the user's config directory (~/.config/openclaw-mcp) and creates PID/log files in /tmp — behavior consistent with a userland service. It does not modify other skills or system-wide agent settings.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install xiaozhi-mcp-server - 安装完成后,直接呼叫该 Skill 的名称或使用
/xiaozhi-mcp-server触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v2.0.8
- Bumped version to 2.0.8.
- Updated metadata in SKILL.md to reflect new version.
- Minor configuration and script adjustments.
v2.0.7
- Bump version to 2.0.7.
- Update metadata in SKILL.md and related files for new version.
- No functional or documentation changes detected beyond version updates.
v2.0.6
- Bumped version to 2.0.6.
- Added _meta.json file.
- Updated package.json and scripts/server.py.
- No user-facing feature changes documented.
v2.0.5
- Updated to version 2.0.5
- Documentation improvements in README.md and SKILL.md
- Removed obsolete file: docs/qq-group.png.md
- Updated package metadata in package.json
v2.0.3
xiaozhi-mcp-server 2.0.3
- 实现与OpenClaw的对接,让小智盒子成为智能语音助手
- 支持语音输入、查询天气、文档书写、信息搜索等多种任务
- 异步任务处理,支持长时间交互不中断
- 提供详细的安装、配置、使用说明
- 新增示例对话,提升用户上手体验
v2.0.2
- 更新描述和文档内容,将“小智音箱”改为“小智智能盒子”,并优化相关说明
- 增加详细的微信绑定和配置流程指导
- 丰富了对话示例,使功能展示更加清晰
- 作者信息调整为“无敌哥@瞄小智”
- 版本号升级至2.0.2
v2.0.1
- Bumped version to 2.0.1 for maintenance release.
- Updated dependencies listed in package.json.
- Minor updates or formatting changes to documentation in SKILL.md.
- No major feature changes or breaking changes introduced.
v2.0.0
xiaozhi-mcp-server 2.0.0
- Major update: Integrates xiaozhi smart speaker with the OpenClaw AI assistant for seamless smart voice interactions.
- Supports real-time voice input from xiaozhi, asynchronous AI processing, and spoken results.
- Handles a wide range of tasks including weather queries, document writing, and information searches.
- Provides installation and setup instructions for connecting the speaker to OpenClaw.
- Customizable via config.yaml (options for port and session target).
v1.0.1
Initial release of xiaozhi-mcp-server.
- Enables Xiaozhi smart box to connect with OpenClaw as a voice assistant.
让小智智能盒子连接欧克劳(OpenClaw),让欧克劳(OpenClaw)成为你的智能助手。
- Supports various tasks such as weather query, document writing, and information search via voice.
- Asynchronous processing for long tasks without timeout.
- Easy configuration and integration with Xiaozhi and OpenClaw platforms.
v1.0.0
xiaozhi-mcp-server 1.0.0 初始版本发布
- 实现小智语音通过OpenClaw处理与语音播报结果
- 支持查天气、写文档、查快递等多种任务
- 支持异步处理,长任务不会超时
- 简单配置后即可让小智与OpenClaw联通
- 提供详细安装和使用说明
元数据
常见问题
Xiaozhi Mcp Server 是什么?
让小智智能盒子连接OpenClaw,成为你的智能语音助手. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 248 次。
如何安装 Xiaozhi Mcp Server?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install xiaozhi-mcp-server」即可一键安装,无需额外配置。
Xiaozhi Mcp Server 是免费的吗?
是的,Xiaozhi Mcp Server 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Xiaozhi Mcp Server 支持哪些平台?
Xiaozhi Mcp Server 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Xiaozhi Mcp Server?
由 elegant1998(@elegant1998)开发并维护,当前版本 v2.0.8。
推荐 Skills