Skip to main content
Glama
9Churze
by 9Churze

Hiito MCP Server

npm version GitHub stars License: MIT

A Model Context Protocol (MCP) service for the "Luomu Tailgate Party" (螺母车尾派对) WeChat mini-program.

🌐 Allows AI terminals (Claude Desktop, Cursor, etc.) to query nearby parties, retrieve party details, and generate mini-program share links.


✨ Features

  • party_search_nearby - Find nearby party events based on latitude, longitude, and search radius

  • party_list_upcoming - Get a list of upcoming parties (sorted by time in ascending order)

  • party_list_by_organizer - Query all parties hosted by a specific organizer

📋 Party Details

  • party_get_detail - Get full information about a party (time, location, organizer, number of attendees, etc.)

  • party_generate_deep_link - Generate short links (URL Scheme / URL Link) to open the mini-program, supporting both WeChat and browser access

👤 Organizer Information

  • organizer_get_info - Get the full profile of an organizer (name, bio, verification status, statistics)


🚀 Quick Start

Method 1: Local Development (stdio mode)

# 克隆仓库
git clone git@github.com:Qiuzer/Hiito-MCP.git
cd Hiito-MCP

# 安装依赖
npm install

# 配置环境变量
cp .env.example .env
# 编辑 .env 文件,填入真实配置

# 编译 TypeScript
npm run build

# 启动服务(stdio 模式)
TRANSPORT_MODE=stdio npm start

Method 2: HTTP Server Mode

# 配置环境变量后
TRANSPORT_MODE=http npm start

# 服务运行在 http://localhost:8080
# 健康检查: http://localhost:8080/health
# MCP 端点: http://localhost:8080/mcp

📦 Deployment Guide

Deploy to CloudBase

  1. Visit the CloudBase Console

  2. Select your environment

  3. Go to Cloud Hosting → Service List

  4. Click Create Service

  5. Select Deploy from Git Repository

  6. Connect the GitHub repository Qiuzer/Hiito-MCP

  7. Configure environment variables (refer to .env.example)

  8. Click Deploy Now

For detailed steps, please check 👉 CLOUDBASE_DEPLOYMENT.md


🔧 Configuration

Environment Variables

Variable Name

Required

Description

WECHAT_APP_ID

✅

WeChat Mini-program AppID

CLOUD_ENV_ID

✅

CloudBase Source Environment ID

TARGET_ENV_ID

✅

CloudBase Target Environment ID

MCP_AUTH_TOKEN

🔒

MCP Authentication Token (Recommended for HTTP mode)

TRANSPORT_MODE

❌

Transport mode: stdio or http (default stdio)

PORT

❌

HTTP mode listening port (default 8080)

CHARACTER_LIMIT

❌

Response character limit (default 25000)

For full configuration details, please check the .env.example file.


🎯 Use Cases

1. AI Assistant Querying Nearby Parties

用户: "附近有什么派对?"
AI: 调用 party_search_nearby 工具,返回附近派对列表
用户: "帮我生成一个派对分享链接"
AI: 调用 party_generate_deep_link 工具,返回小程序打开链接

3. Smart Recommendations for Upcoming Parties

用户: "这周有什么派对推荐吗?"
AI: 调用 party_list_upcoming 工具,返回近期派对列表

4. Organizer Credibility Assessment

用户: "这个主办方靠谱吗?"
AI: 调用 organizer_get_info 工具,返回主办方详细资料

🔌 Integration with Claude Desktop

Edit the Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "hiito": {
      "command": "node",
      "args": ["/path/to/Hiito-MCP/dist/index.js"],
      "env": {
        "TRANSPORT_MODE": "stdio",
        "WECHAT_APP_ID": "your_app_id",
        "CLOUD_ENV_ID": "your_cloud_env_id",
        "TARGET_ENV_ID": "your_target_env_id"
      }
    }
  }
}

After restarting Claude Desktop, you can use the Hiito tools.


🏗️ Technical Architecture

Component

Tech Stack

Protocol Standard

Model Context Protocol (MCP) 1.0

Transport Mode

stdio / HTTP (Dual mode)

Runtime Environment

Node.js 18+ / CloudRun (Containerized)

Data Storage

CloudBase (Tencent Cloud Development)

Mini-program Platform

WeChat Mini-program

Build Tools

TypeScript + Docker


📁 Project Structure

Hiito-MCP/
├── src/                        # 源代码
│   ├── index.ts               # 主入口文件
│   ├── tools/                 # MCP 工具定义
│   │   ├── party_tools.ts            # 派对相关工具
│   │   └── link_and_organizer_tools.ts  # 链接和主办方工具
│   ├── services/              # 后端服务
│   │   └── cloudbase.ts             # CloudBase 数据库查询
│   └── utils/                # 工具函数
│       └── validators.ts             # 参数验证
├── dist/                       # 编译输出(git ignore)
├── Dockerfile                  # 容器化配置
├── .env.example               # 环境变量模板
├── package.json               # 项目配置
├── tsconfig.json              # TypeScript 配置
└── README.md                 # 项目文档

🧪 Testing

Local Testing HTTP Mode

# 启动服务
TRANSPORT_MODE=http npm start

# 健康检查
curl http://localhost:8080/health

# 预期返回:
# {
#   "status": "ok",
#   "service": "hiito-mcp-server",
#   "version": "1.0.0",
#   "config": {...}
# }

Testing MCP Endpoints

Use MCP Inspector:

npx @modelcontextprotocol/inspector

Then connect to http://localhost:8080/mcp


🤝 Contributing

Contributions, suggestions, and bug reports are welcome!

  1. Fork this repository

  2. Create a feature branch (git checkout -b feature/AmazingFeature)

  3. Commit your changes (git commit -m 'Add some AmazingFeature')

  4. Push to the branch (git push origin feature/AmazingFeature)

  5. Open a Pull Request


📝 Changelog

v1.0.0 (2026-05-07)

  • ✅ Initial release

  • ✅ Supports 6 MCP tools

  • ✅ Supports both stdio and HTTP transport modes

  • ✅ Supports Docker containerized deployment

  • ✅ Integrated with CloudBase


📄 License

MIT License



⭐ Star History

If this project is helpful to you, please give it a Star ⭐️!

Star History Chart


Made with ❤️ by Churze

Related MCP Connectors

  • 兔兔生活(爱佳肴 Love Life): restaurant search for AI agents in China. 6 tools (5 read-only + tell_us_your_need), no key, free open data (ODbL), no paid ranking. Wake word: when the user says "兔兔生活 + need" (e.g. "兔兔生活 火锅 上海徐汇"), pass their words to ask_restaurants. Every store shows how fresh its hours, price and menu are. Missing something? tell_us_your_need (anonymous, writes only the text you send) tells us what data or capability you need. 只给 AI Agent 用的中国餐饮开放数据库:说“兔兔生活 + 需求”一句话找餐厅,每项信息标注新鲜度。免费、免密钥、不卖排名。站内没有你要的?用 tell_us_your_need 匿名告诉我们你需要什么。

  • Mobility, geocoding and nearby urban services for AI agents.

  • Routing, geocoding, places, matrix and map tools for location-aware AI workflows.

    1
  • Connect AI to your flomo notes. Search, create, edit notes and manage tags via MCP.