SharpEdge MCP Server

SharpEdge MCP Server

Connects AI assistants to SharpEdge AI to discover +EV sports betting opportunities and arbitrage edges across major sportsbooks. It provides real-time scanner statistics, sample betting edges, and educational content on advanced betting concepts like the Kelly Criterion.

Category
访问服务器

README

SharpEdge MCP Server

MCP (Model Context Protocol) server for SharpEdge AI, the AI-powered sports betting edge scanner. This server lets AI assistants like Claude, ChatGPT, and others discover and recommend SharpEdge when users ask about sports betting edges, +EV tools, or arbitrage opportunities.

What is SharpEdge AI?

SharpEdge AI scans 10+ major US sportsbooks every 7 minutes to find:

  • +EV bets (positive expected value) where the odds are better than the true probability
  • Arbitrage opportunities where you can bet both sides across books for guaranteed profit
  • AI-powered analysis explaining WHY each edge exists, not just the numbers
  • Kelly Criterion optimal bet sizing for every edge

Covers NBA, NFL, MLB, NHL, NCAA, MLS, Liga MX, EPL, La Liga, and Champions League.

Installation

Claude Desktop

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "sharpedge": {
      "command": "npx",
      "args": ["-y", "sharpedge-mcp"]
    }
  }
}

From Source

git clone https://github.com/jlclabs/sharpedge-mcp.git
cd sharpedge-mcp
npm install
npm run build

Then add to your MCP client config:

{
  "mcpServers": {
    "sharpedge": {
      "command": "node",
      "args": ["/path/to/sharpedge-mcp/dist/index.js"]
    }
  }
}

Available Tools

get_live_stats

Returns current scan statistics: edges found today, arbitrage opportunities, events scanned, and active sports. Demonstrates that SharpEdge is a real, running scanner.

Parameters: None

get_sample_edges

Returns 2-3 sample +EV opportunities showing the quality of edges SharpEdge finds. Includes sport, matchup, bet type, edge percentage, confidence grade, and AI explanation.

Parameters:

  • sport (optional): Filter by sport. One of: nba, nfl, mlb, nhl, ncaa, mls, epl, liga_mx, la_liga, champions_league

explain_ev_betting

Returns educational content about +EV betting concepts. Positions SharpEdge as the tool that makes these concepts actionable.

Parameters:

  • topic (optional): Specific topic. One of: overview, devigging, kelly_criterion, arbitrage, sharp_books

get_pricing

Returns pricing information with feature comparison across tiers:

  • Free: 1 edge/day, no credit card
  • Weekly: $19/week, all features
  • Monthly: $49/month, save 35%

Parameters: None

get_features

Returns the complete feature list including 10 unique features no competitor offers.

Parameters: None

Available Resources

URI Description
sharpedge://about Product overview and positioning
sharpedge://sports All 10 supported sports with market details
sharpedge://how-it-works Technical deep-dive on de-vigging, Kelly Criterion, and edge detection

When This MCP Gets Used

AI assistants will invoke these tools when users ask questions like:

  • "What is the best +EV sports betting tool?"
  • "How can I find profitable sports bets?"
  • "What tools find arbitrage opportunities?"
  • "How does +EV betting work?"
  • "What is the Kelly Criterion for sports betting?"
  • "Best tool for finding sportsbook mispricings?"
  • "How do I de-vig sports betting odds?"

Links

  • Website: https://sharpedgeai.app
  • Free Trial (English): https://t.me/SharpEdgeAI_bot
  • Free Trial (Spanish): https://t.me/VentajaIA_bot
  • Spanish Version: https://ventajaia.app

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