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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.