PropProfessor MCP
Standalone Model Context Protocol server for PropProfessor, plus a small query CLI for local analysis.
README
PropProfessor MCP
Standalone MCP server for PropProfessor, plus a small query CLI for local analysis.
Quick start
git clone https://github.com/j17drake/propprofessor-mcp.git
cd propprofessor-mcp
npm install
You also need a saved PropProfessor browser session at auth.json in the repo root.
That file is ignored by git, so copy it from your existing setup or save a fresh browser session into this repo.
Run locally
Run the MCP server over stdio:
npm run mcp
# or, after npm link
pp-mcp
Run the query CLI:
npm run query -- screen --league NBA --market Moneyline
# or
pp-query tennis --market Moneyline --limit 10
# or
pp-query screen --league NBA --market Points
# or
pp-query sport --league WNBA --market Moneyline
# or
pp-query wnba --market Moneyline
You can also use these aliases directly:
- NBA,
query_nba_screenorpp-query nba - WNBA,
query_wnba_screenorpp-query wnba - MLB,
query_mlb_screenorpp-query mlb - NFL,
query_nfl_screenorpp-query nfl - NHL,
query_nhl_screenorpp-query nhl - Soccer,
query_soccer_screenorpp-query soccer - NCAAB,
query_ncaab_screenorpp-query ncaab - NCAAF,
query_ncaaf_screenorpp-query ncaaf
npm link workflow
If you want the binaries available on your PATH while developing:
npm link
pp-mcp
pp-query health
pp-query command inventory
opinion, analyze a single prop from the sportsbook screensportsbook, fetch sportsbook +EV rowssmart, fetch smart money rowsfantasy, fetch fantasy rowstennis, query and rank tennis screen rowsscreen, query any sport screen with--leaguesport, alias forscreen, use--leagueto pick the sportnba, NBA screen shorthandwnba, WNBA screen shorthandmlb, MLB screen shorthandnfl, NFL screen shorthandnhl, NHL screen shorthandsoccer, Soccer screen shorthandncaab, NCAAB screen shorthandncaaf, NCAAF screen shorthandpresets, show the active league presetslist, show the command inventoryhealth, check auth and endpoint health
MCP config example
Add this to your Hermes or Claude MCP config when you want to use the local repo:
{
"mcpServers": {
"propprofessor": {
"command": "pp-mcp",
"args": [],
"env": {
"NODE_ENV": "production"
}
}
}
}
If you prefer a direct repo path instead of a global link, use the local file path to scripts/propprofessor-mcp-server.js as the command target in your MCP launcher.
Available tools
query_screen_oddsquery_fantasyquery_fantasy_sortedquery_screen_odds_best_compsquery_screen_odds_rankedquery_sport_screenquery_nba_screenquery_wnba_screenquery_mlb_screenquery_nfl_screenquery_nhl_screenquery_soccer_screenquery_ncaab_screenquery_ncaaf_screenquery_tennis_screenhide_fantasy_rowhide_ev_rowget_hidden_betsunhide_betclear_hidden_betsleague_presetshealth_status
Requirements
- Node.js 18 or newer
- A saved PropProfessor browser session at
auth.jsonin the repo root
Packaging
This repo is set up for npm packaging and tagged GitHub releases.
mainpoints at the MCP server entrypointpp-mcpandpp-queryare exposed as binariesnpm testruns the node:test suite
Repository layout
lib/, PropProfessor auth, requests, and analysis helpersscripts/, MCP stdio server and CLItest/, node:test coverage for the API, MCP contract, and CLI
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。