Savvy Scratch MCP Server
An MCP server that enables AI assistants to analyze scratch-off lottery games across 19 U.S. states, with tools for account management, game browsing, and subscription.
README
Savvy Scratch MCP Server
Install
Claude Desktop
Open your claude_desktop_config.json:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Add the Savvy Scratch server:
{
"mcpServers": {
"savvyscratch": {
"command": "npx",
"args": ["-y", "@savvyscratch/mcp-server"]
}
}
}
Restart Claude Desktop. You're done.
Claude Code
Add to your project's .mcp.json (or run claude mcp add):
{
"mcpServers": {
"savvyscratch": {
"command": "npx",
"args": ["-y", "@savvyscratch/mcp-server"]
}
}
}
Other MCP-compatible clients
Any client that supports stdio MCP servers can run:
npx -y @savvyscratch/mcp-server
What is this?
An MCP (Model Context Protocol) server that gives AI assistants access to Savvy Scratch — pro-gambler-grade analysis of scratch-off lottery games across 19 U.S. states.
Register, sign in, browse live game data, and subscribe — all through natural conversation with your AI. Zero configuration required.
First-time setup (through your AI)
Once installed, just talk to your AI:
- "Register a Savvy Scratch account for me" → AI uses the
registertool - "What scratch-off games should I play in Florida?" → AI uses
login+get_games - "Subscribe me to Savvy Scratch" → AI uses
get_subscribe_link
No API keys. No env vars. Your account lives in your AI session.
Tools
Auth & Account
| Tool | Description |
|---|---|
register |
Create a new Savvy Scratch account |
login |
Sign in with email and password |
logout |
Sign out |
check_subscription |
View subscription status and plan details |
get_subscribe_link |
Get a link to subscribe |
Game Analysis
| Tool | Description | Free | Subscriber |
|---|---|---|---|
list_states |
List all 19 covered states | Full | Full |
get_games |
Get scratch-off games for a state | Top 3 | All games |
game_details |
Detailed prize breakdown for a game | Locked | Full |
best_games |
Best games for a budget and state | Top 3 | All matches |
Pricing
Free accounts see top-3 previews in every state. A Savvy Scratch subscription ($5/mo or $50/yr) unlocks:
- All games in all 19 states
- Detailed prize-tier breakdowns with live remaining prizes
- Budget-optimized recommendations ranked by weighted score
- Pro gambler methodology applied to every game
Example Conversation
You: What scratch-off games should I play in Florida?
AI: [calls login, then get_games with state=fl]
Shows top 3 games with scores and odds...
"Subscribe to see all 100 games. Use get_subscribe_link to get started."
You: I have $10 to spend in Georgia, what's best?
AI: [calls best_games with state=ga, budget=10]
Shows top-rated games at $10 or under ranked by weighted score
You: Show me the prize breakdown for Atlanta Falcons
AI: [calls game_details with state=ga, game_name="Atlanta Falcons"]
Full prize tier breakdown with remaining prizes and adjusted odds
Build from source
git clone https://github.com/myque08/savvymcp.git
cd savvymcp
npm install
npm run build
node dist/index.js
Links
- npm package: https://www.npmjs.com/package/@savvyscratch/mcp-server
- Website: https://www.savvyscratch.com
- GitHub: https://github.com/myque08/savvymcp
- Report issues: https://github.com/myque08/savvymcp/issues
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。