StatsPlus MCP Server
Exposes the StatsPlus API as tools for MCP-compatible clients, enabling users to query player/team statistics, contracts, ratings, and game history via natural language.
README
StatsPlus MCP Server
An MCP server that exposes the StatsPlus API as tools for use with Claude and other MCP-compatible clients.
Prerequisites
- Node.js 18+
- A StatsPlus league account linked to a team
Installation
git clone https://github.com/joshuarichard/StatsPlus-MCP.git
cd StatsPlus-MCP
npm install
npm run build
Configuration
Getting your session cookie
The StatsPlus API requires an active browser session. To get your cookie:
- Log into
https://statsplus.net/<your-league-url>in your browser - Open DevTools (
Cmd+Option+Ion Mac,F12on Windows/Linux) - Go to Application → Cookies →
https://statsplus.net - Copy the
sessionidandcsrftokenvalues and combine them:sessionid=<value>;csrftoken=<value>
Adding to your MCP client
Add the following to your MCP client config (e.g. ~/.claude/mcp.json for Claude Code):
{
"mcpServers": {
"statsplus": {
"command": "node",
"args": ["/path/to/StatsPlus-MCP/dist/index.js"],
"env": {
"STATSPLUS_LEAGUE_URL": "<your-league-url>",
"STATSPLUS_COOKIE": "sessionid=<sessionid>;csrftoken=<csrftoken>"
}
}
}
Replace:
/path/to/StatsPlus-MCP— the absolute path where you cloned this repo<your-league-url>— your league's URL slug (e.g.myleague,mlb2025)<sessionid>— thesessionidcookie value from your browser<csrftoken>— thecsrftokencookie value from your browser
Alternatively, with the Claude Code CLI:
claude mcp add statsplus \
-e STATSPLUS_LEAGUE_URL=<your-league-url> \
-e "STATSPLUS_COOKIE=sessionid=<sessionid>;csrftoken=<csrftoken>" \
-- node /path/to/StatsPlus-MCP/dist/index.js
Available Tools
| Tool | Description | Parameters |
|---|---|---|
get_player_batting_stats |
Player batting statistics | year?, pid?, split? |
get_player_pitching_stats |
Player pitching statistics | year?, pid?, split? |
get_player_fielding_stats |
Player fielding statistics by position | year?, pid?, split? |
get_team_batting_stats |
Team batting statistics with rate stats | year?, split? |
get_team_pitching_stats |
Team pitching statistics with rate stats | year?, split? |
get_players |
Player roster with names and team assignments | team_id?, org_id? |
find_player |
Search players by name (partial, case-insensitive) | name |
start_ratings_job |
Start the async ratings export; returns poll_url immediately |
— |
get_ratings |
Collect ratings results (pass poll_url to avoid re-starting the job) |
poll_url?, player_ids? |
get_game_history |
All major league games with scores, hits, errors, and pitcher IDs | — |
get_contracts |
All current and active player contracts | team_id?, player_id? |
get_contract_extensions |
Signed extensions taking effect in future seasons | — |
get_teams |
Team list with IDs and abbreviations | — |
get_draft |
Draft picks | lid? |
get_exports |
CSV export of all league games | — |
Split IDs: 1 = Overall, 2 = vs Left-handed, 3 = vs Right-handed
Usage tips
-
Name-to-ID resolution: Use
find_player(name)for quick name → ID lookups without downloading the full roster. For a full org's players, useget_players(org_id)which filters byParent Team ID. -
Ratings workflow: The ratings export is an async job that takes 60–90 seconds. To avoid blocking mid-workflow, call
start_ratings_job()first, do your other lookups while it processes, then callget_ratings(poll_url)to collect results:start_ratings_job() → { poll_url: "..." } get_player_batting_stats(...) ← runs concurrently get_contracts(team_id: ...) get_ratings(poll_url: "...") → results ready, no extra waitCalling
get_ratings()without apoll_urlstarts a new job and blocks until complete. Ratings columns include batting attributes (Cntct,Gap,Pow,Eye,Ks) with L/R splits,Pot*potential counterparts, and positional grades. Key encoding notes:- Star ratings are stored as
stars × 2— e.g. 3.5 stars =7, 5 stars =10 - International complex players have a negative
Leaguevalue (e.g.-100) - Column names are not guaranteed to be stable across OOTP versions
- Star ratings are stored as
-
Preseason / empty responses: During preseason, all stat endpoints return HTTP 204 with no data for the upcoming year. Always pass
year=<most recent completed season>to get data. -
Fielding:
get_player_fielding_statsreturns one row per player per position per split. A player who appeared at multiple positions will have multiple rows — one for each. -
Game history:
runs0/hits0/errors0are the home team;runs1/hits1/errors1are the away team.winning_pitcher,losing_pitcher,starter0, andstarter1are numeric player IDs.save_pitcheris0when there is no save pitcher. -
Contracts:
salary0is the current season salary,salary1is next season, and so on throughsalary14. Unpopulated years are0.is_majorandno_tradeare0/1integers.contract_team_idis the MLB org that holds the contract (use this with theteam_idfilter).get_contract_extensionsuses the same schema for deals already signed but not yet in effect. -
Splits: All stat endpoints that accept a
splitparameter use1= Overall,2= vs Left-handed,3= vs Right-handed. Omittingsplitreturns all three rows per player/team.
Development
npm run build # Compile TypeScript
npm test # Run tests
npm run test:watch # Run tests in watch mode
npm run lint # Type-check without emitting
License
MIT
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.