LineWhiz

LineWhiz

AI-powered MCP server for managing LINE Official Accounts. Send broadcasts, push messages, check analytics, manage rich menus — all through natural language via Claude, ChatGPT, or Cursor. 10 tools included: * Account info, friend count, message quota * Broadcast, push message, multicast * Delivery stats, user profiles, follower list * Rich menu management Supports 95M+ LINE users across Jap

Category
访问服务器

README

LineWhiz

Premium MCP server that lets AI agents manage LINE Official Accounts.

Users type natural language in Claude / ChatGPT / Cursor → LineWhiz calls the LINE Messaging API.

Python 3.11+ MCP License: MIT

Features

Tool Tier Description
get_account_info Free Get LINE OA info: name, plan, picture
get_friend_count Free Get follower count on a specific date
get_message_quota Free Get remaining message quota this month
send_broadcast Pro Send message to ALL friends
send_push_message Pro Send DM to a specific user
send_multicast Pro Send message to multiple users (max 500)
get_message_delivery_stats Pro Get delivery stats for a date
get_user_profile Pro Get user's display name, picture, etc.
list_rich_menus Pro List all rich menus for this LINE OA

Quick Start

Prerequisites

Setup

# Clone and install
cd linewhiz && uv sync

# Configure environment
cp .env.example .env
# Edit .env → fill in LINE_CHANNEL_ACCESS_TOKEN and LINE_CHANNEL_SECRET

# Run the server
uv run src/server.py

# Test with MCP Inspector
mcp dev src/server.py

# Run tests
uv run pytest

MCP Client Configuration

Add to your MCP client config (e.g., Claude Desktop claude_desktop_config.json):

{
  "mcpServers": {
    "linewhiz": {
      "command": "uv",
      "args": ["run", "src/server.py"],
      "cwd": "/path/to/linewhiz",
      "env": {
        "LINE_CHANNEL_ACCESS_TOKEN": "your_token_here",
        "LINE_CHANNEL_SECRET": "your_secret_here",
        "LINEWHIZ_TIER": "pro"
      }
    }
  }
}

Project Structure

linewhiz/
├── CLAUDE.md              # AI coding spec (single source of truth)
├── pyproject.toml
├── Dockerfile
├── docker-compose.yml
├── .env.example
├── src/
│   ├── server.py          # MCP entry point + tool registration
│   ├── config.py          # Env config via pydantic Settings
│   ├── auth/
│   │   ├── api_keys.py    # Key validation (SHA-256)
│   │   └── tiers.py       # Free/Pro/Business gating + rate limits
│   ├── tools/
│   │   ├── account.py     # get_account_info, get_friend_count, get_message_quota
│   │   ├── messaging.py   # send_broadcast, send_push, send_multicast
│   │   ├── richmenu.py    # list/create/set/link rich menus
│   │   ├── insights.py    # get_message_stats, get_user_profile
│   │   ├── automation.py  # [future] auto-reply
│   │   └── reporting.py   # [future] weekly report
│   ├── services/
│   │   ├── line_api.py    # Async LINE API wrapper
│   │   └── flex_builder.py
│   ├── models/
│   │   ├── user.py        # API key + tier models
│   │   └── usage.py       # Usage log model
│   └── db/
│       └── database.py    # SQLite async init + migrations
├── tests/
│   ├── conftest.py
│   ├── test_account.py
│   ├── test_messaging.py
│   ├── test_richmenu.py
│   └── test_auth.py
└── docs/

Tier System

Tier Price Daily Calls Tools
Free $0/mo 100 Account info, friend count, quota
Pro $15/mo 5,000 + Messaging, rich menus, insights
Business $45/mo Unlimited All tools

Docker

# Build and run
docker compose up --build

# Or build manually
docker build -t linewhiz .
docker run --env-file .env linewhiz

Development

# Install with dev dependencies
uv sync --all-extras

# Lint
uv run ruff check src/ tests/

# Type check
uv run mypy src/

# Test
uv run pytest -v

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选
LineWhiz