Smart Pet with MCP

by shijianzhong

61 stars
236 downloads
Not rated
GitHub

About

一个桌宠形式的mcp client,可以对接任意mcp server,配合测试的mcp server 开源地址:https://github.com/shijianzhong/mcp-server-for-pc

Details

Author
shijianzhong
GitHub stars
61
Downloads
236
Categories
Other

- Intelligent interaction via speech recognition and NLP
- Modern UI built with Vue3 and Electron
- Real-time response based on MCP protocol
- Cross-platform support for Windows, macOS, and Linux
- Voice recognition via the FunASR engine
- MCP server configuration management

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Smart Pet with MCP
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Clone the repository, install dependencies with pnpm install, and start the development environment with pnpm start. A Docker container is required for the FunASR speech recognition engine. Build for production using pnpm build:win, pnpm build:mac, or pnpm build:linux.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "smart pet with mcp": {
            "smart-pet-with-mcp": {
                "command": "docker",
                "args": [
                    "pull",
                    "registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.12"
                ]
            }
        }
    }
}

McpServers

{
    "smart-pet-with-mcp": {
        "command": "docker",
        "args": [
            "pull",
            "registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.12"
        ]
    }
}

Smart Pet with MCP

一个基于 MCP(Model Context Protocol)协议的智能宠物伴侣应用,通过语音识别和自然语言处理技术,为宠物主人提供实时互动和服务。该应用是一个 MCP-Client 应用,可以自主无限搭配 MCP-Server 实现需求。

配合测试的mcp server 开源地址:https://github.com/shijianzhong/mcp-server-for-pc
该mcp server 主要是用来操作个人PC的,比如打开浏览器,打开应用,打开文件,播放音乐,发送邮件等。

项目特点

- 🎯 智能交互:通过语音识别和自然语言处理实现智能对话
- 🎨 精美界面:采用 Vue3 + Electron 构建的现代化界面
- 🔄 实时响应:基于 MCP 协议实现快速响应
- 🐱 宠物陪伴:提供虚拟宠物互动体验
- 🌐 多平台支持:支持 Windows、macOS 和 Linux 系统

技术栈

- 前端框架:Vue 3 + Electron
- 语音识别:FunASR
- 协议支持:MCP (Model Context Protocol)
- UI 渲染:Pixi.js
- 数据库:Better-SQLite3
- AI 模型:支持 Anthropic、OpenAI 等大模型

功能特性

核心功能

- 🎤 语音识别:通过麦克风捕获用户语音,并转换为文本 - 🤖 自然语言处理:将语音识别的文本转换为 MCP 协议格式的指令 - 💬 智能对话:支持与虚拟宠物进行自然语言对话 - 🎮 交互控制:支持语音和点击等多种交互方式

特色功能

- 🎭 虚拟形象:支持 Live2D 虚拟形象展示 - 🌡️ 环境感知:支持天气和环境信息展示 - 🔄 实时更新:支持应用自动更新 - ⚙️ 配置管理:支持 MCP 服务器配置管理

系统架构

┌─────────────────┐     ┌─────────────────┐     ┌─────────────────┐
│                 │     │                 │     │                 │
│  Smart Pet App  │────▶│    MCP Client   │────▶│    MCP Server   │
│  (Electron)     │     │                 │     │                 │
│                 │     │                 │     │                 │
└─────────────────┘     └─────────────────┘     └─────────────────┘
        │                       │                       │
        │                       │                       │
        ▼                       ▼                       ▼
┌─────────────────┐     ┌─────────────────┐     ┌─────────────────┐
│                 │     │                 │     │                 │
│  FunASR Engine  │     │  AI Models      │     │  File System    │
│                 │     │                 │     │                 │
└─────────────────┘     └─────────────────┘     └─────────────────┘

快速开始

环境要求

- Node.js >= 16 - pnpm >= 7 - Docker (用于运行 FunASR)

安装步骤

1. 克隆项目

git clone https://github.com/yourusername/smart-pet-with-mcp.git
cd smart-pet-with-mcp

2. 安装依赖

pnpm install

3. 启动开发环境

pnpm start

构建应用

```bash

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.