# Xiaozhi Deploy Guide

> Bilingual guide for deploying XiaoZhi (xiaozhi-esp32) locally: server, firmware, LLM/TTS and MCP | 小智本地部署中英双语教程：服务器、固件、大模型语音与 MCP

- **Type:** MCP server
- **Install:** `agentstack add mcp-linlop911-xiaozhi-deploy-guide`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [linlop911](https://agentstack.voostack.com/s/linlop911)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [linlop911](https://github.com/linlop911)
- **Source:** https://github.com/linlop911/xiaozhi-deploy-guide

## Install

```sh
agentstack add mcp-linlop911-xiaozhi-deploy-guide
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# XiaoZhi Local Deployment Guide

[English](README.md) | [简体中文](README_zh.md)

A practical, step-by-step bilingual guide for deploying **XiaoZhi (小智)** — the open-source AI voice assistant — on your own hardware and server. It covers the whole local deployment workflow: server deployment, LLM / ASR / TTS configuration, firmware build & flash, MCP extension, digital human module, and troubleshooting.

## What is XiaoZhi?

XiaoZhi is an open-source AI voice assistant ecosystem:

- **ESP32 device (firmware)** — captures audio, detects the wake word offline, plays replies, and shows status on a display
- **xiaozhi-server** — handles speech recognition (ASR), LLM conversation, text-to-speech (TTS), OTA, and MCP tool management
- **LLM API** — Qwen, DeepSeek, or any OpenAI-compatible model
- **MCP endpoint (optional)** — connects external tools (calculator, weather, smart home, ...) to your assistant
- **Digital human module (optional)** — browser-based avatar page with local wake-word runtime for testing/display

## System Architecture

```text
ESP32 device (firmware)  ⇄ WebSocket ⇄ xiaozhi-server (ASR + LLM + TTS)  → LLM API
                                        ⇄ MCP ⇄ mcp-endpoint-server → custom tools
                                        ⇄ digital-human (browser test page)
```

## Table of Contents

| # | Chapter | 章节 |
| --- | --- | --- |
| 1 | [Deployment Overview](docs/01-部署方式总览.md) | [部署方式总览](docs/01-部署方式总览.md) |
| 2 | [Server Deployment](docs/02-服务器端部署.md) | [服务器端部署](docs/02-服务器端部署.md) |
| 3 | [MCP Endpoint Deployment](docs/03-MCP接入点部署.md) | [MCP 接入点部署](docs/03-MCP接入点部署.md) |
| 4 | [Adding MCP Features](docs/04-给小智接入MCP功能.md) | [给小智接入 MCP 功能](docs/04-给小智接入MCP功能.md) |
| 5 | [Firmware Build & Flash](docs/05-固件编译烧录.md) | [固件编译与烧录](docs/05-固件编译烧录.md) |
| 6 | [LLM & Voice Configuration](docs/06-大模型与语音配置.md) | [大模型与语音配置](docs/06-大模型与语音配置.md) |
| 7 | [FAQ](docs/07-常见问题FAQ.md) | [常见问题 FAQ](docs/07-常见问题FAQ.md) |
| 8 | [Digital Human Module](docs/08-数字人模块.md) | [数字人模块](docs/08-数字人模块.md) |
| 9 | [Common Errors & Screenshots](docs/09-常见报错与截图.md) | [常见报错与截图](docs/09-常见报错与截图.md) |

## Recommended Path

1. Deploy the server (Chapter 2)
2. Configure the LLM (Chapter 6)
3. Build and flash the firmware (Chapter 5)
4. Provision Wi-Fi and start talking
5. Extend with MCP tools (Chapters 3 & 4) or the digital human module (Chapter 8)

## Upstream Projects

- [78/xiaozhi-esp32](https://github.com/78/xiaozhi-esp32) — ESP32 firmware
- [xinnan-tech/xiaozhi-esp32-server](https://github.com/xinnan-tech/xiaozhi-esp32-server) — voice server
- [xinnan-tech/mcp-endpoint-server](https://github.com/xinnan-tech/mcp-endpoint-server) — MCP endpoint server
- [78/mcp-calculator](https://github.com/78/mcp-calculator) — MCP calculator example

## License

MIT — see [LICENSE](LICENSE).

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [linlop911](https://github.com/linlop911)
- **Source:** [linlop911/xiaozhi-deploy-guide](https://github.com/linlop911/xiaozhi-deploy-guide)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** yes
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-linlop911-xiaozhi-deploy-guide
- Seller: https://agentstack.voostack.com/s/linlop911
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.