MLB Stats MCP Server
A Cloudflare Worker that provides access to MLB Statistics API data through the Model Context Protocol, supporting multiple endpoints like team info, player stats, game schedules, and live game data.
README
MLB Stats MCP Server - Enhanced with Meta-Tools
🔧 Version 2.1 - Now with Entity Resolution Meta-Tools!
A Cloudflare Worker that serves as an enhanced MCP (Model Context Protocol) server for accessing MLB Stats API data. Features meta-tools for intelligent entity resolution, comprehensive team/player mappings, and optimized data access patterns.
🎯 Enhanced Features
🔧 Meta-Tools for Entity Resolution
- resolve_team: Convert team names to canonical MLB team IDs
- resolve_player: Convert player names to canonical MLB player IDs
- Comprehensive Mappings: All 30 MLB teams with aliases and abbreviations
- Fuzzy Matching: "Yankees", "NYY", "New York Yankees" all resolve correctly
- Smart Suggestions: "Did you mean?" fallbacks for typos and partial matches
⚾ MLB Data Access
- Direct MLB API proxy with zero additional latency
- All MLB endpoints supported (teams, players, stats, schedules, etc.)
- CORS enabled for web applications
- No API keys required (MLB Stats API is public)
- Error handling and validation with detailed responses
🏗️ Architecture Benefits
- Domain logic ownership: All MLB-specific logic contained within this worker
- Service binding ready: Optimized for Cloudflare worker-to-worker communication
- Token efficient: Meta-tools reduce round-trips and enable smart caching
- Future-proof: Extensible pattern for other sports (NFL, NBA, NHL)
🛠️ Available Commands
🔧 Meta-Tools (Entity Resolution)
resolve_team - Team Name Resolution
Convert any team reference to canonical MLB team information.
Request:
{
"command": "resolve_team",
"params": {
"name": "Yankees"
}
}
Response:
{
"result": {
"id": 147,
"name": "New York Yankees",
"abbreviation": "NYY",
"query": "Yankees",
"resolved": true
}
}
Supported Inputs:
- Team names: "Yankees", "Red Sox", "Dodgers"
- Full names: "New York Yankees", "Boston Red Sox"
- Abbreviations: "NYY", "BOS", "LAD"
- Cities: "New York", "Boston", "Los Angeles"
resolve_player - Player Name Resolution
Convert any player reference to canonical MLB player information.
Request:
{
"command": "resolve_player",
"params": {
"name": "Judge"
}
}
Response:
{
"result": {
"id": 592450,
"name": "Aaron Judge",
"team": "New York Yankees",
"query": "Judge",
"resolved": true
}
}
Supported Players:
- Aaron Judge, Shohei Ohtani, Mookie Betts, Freddie Freeman
- Ronald Acuna Jr., Mike Trout, and other star players
- Both full names and last names supported
⚾ MLB Data Commands
getTeamInfo- Get team information and detailsgetRoster- Get team roster and player positionsgetPlayerStats- Get player statistics (hitting, pitching)getSchedule- Get game schedule and datesgetLiveGame- Get live game data and updatesgetStandings- Get league and division standingsgetGameBoxscore- Get detailed game boxscoregetPlayerInfo- Get player biographical informationgetSeasons- Get season information and yearsgetVenues- Get stadium and venue information
🎯 Enhanced Workflow
Traditional Approach:
// Step 1: User needs to know exact team ID
{"command": "getRoster", "params": {"pathParams": {"teamId": "147"}}}
Enhanced Meta-Tool Approach:
// Step 1: Resolve team name to ID
{"command": "resolve_team", "params": {"name": "Yankees"}}
// Returns: {"result": {"id": 147, "name": "New York Yankees"}}
// Step 2: Use resolved ID automatically (handled by sports-proxy)
{"command": "getRoster", "params": {"pathParams": {"teamId": "147"}}}
Request Format
Send POST requests to the worker endpoint with the following JSON structure:
{
"command": "getPlayerStats",
"params": {
"pathParams": {
"playerId": "660271"
},
"queryParams": {
"stats": "season",
"group": "hitting",
"season": "2024"
}
}
}
Response Format
Successful responses return:
{
"result": {
// MLB API response data
}
}
Error responses return:
{
"error": "Error message"
}
Development
-
Install Wrangler CLI:
npm install -g wrangler -
Login to Cloudflare:
wrangler login -
Deploy the worker:
wrangler deploy
📋 Complete Usage Examples
🔧 Meta-Tool Examples
Resolve Team Names
# Basic team resolution
curl -X POST https://mlbstats-mcp.your-domain.workers.dev \
-H "Content-Type: application/json" \
-d '{
"command": "resolve_team",
"params": {"name": "Yankees"}
}'
# Response: {"result": {"id": 147, "name": "New York Yankees", "abbreviation": "NYY"}}
# Handle abbreviations and cities
curl -X POST https://mlbstats-mcp.your-domain.workers.dev \
-H "Content-Type: application/json" \
-d '{
"command": "resolve_team",
"params": {"name": "LAD"}
}'
# Response: {"result": {"id": 119, "name": "Los Angeles Dodgers", "abbreviation": "LAD"}}
Resolve Player Names
# Resolve player by last name
curl -X POST https://mlbstats-mcp.your-domain.workers.dev \
-H "Content-Type: application/json" \
-d '{
"command": "resolve_player",
"params": {"name": "Ohtani"}
}'
# Response: {"result": {"id": 660271, "name": "Shohei Ohtani", "team": "Los Angeles Dodgers"}}
⚾ Data Retrieval Examples
Get Team Information
{
"command": "getTeamInfo",
"params": {
"queryParams": {
"season": "2025",
"sportId": "1"
}
}
}
Get Player Stats (with resolved player ID)
{
"command": "getPlayerStats",
"params": {
"pathParams": {
"playerId": "592450" // Aaron Judge (from resolve_player)
},
"queryParams": {
"stats": "season",
"group": "hitting",
"season": "2025"
}
}
}
Get Team Roster (with resolved team ID)
{
"command": "getRoster",
"params": {
"pathParams": {
"teamId": "147" // Yankees (from resolve_team)
},
"queryParams": {
"season": "2025"
}
}
}
Get Schedule
{
"command": "getSchedule",
"params": {
"queryParams": {
"sportId": "1",
"date": "2025-07-04",
"teamId": "147" // Optional: filter by resolved team
}
}
}
🔍 Error Handling Examples
Team Not Found
// Request: {"command": "resolve_team", "params": {"name": "Cowbays"}}
// Response:
{
"error": "Team \"Cowbays\" not found. Did you mean: cowboys, astros, royals?"
}
Player Not Found
// Request: {"command": "resolve_player", "params": {"name": "Jduge"}}
// Response:
{
"error": "Player \"Jduge\" not found. Did you mean: judge?"
}
🚀 Integration with Sports-Proxy
When used with the enhanced sports-proxy, the workflow becomes seamless:
# User input: "Get the Yankees roster"
# 1. Sports-proxy detects MLB sport
# 2. Extracts tools: resolve_team("yankees"), get_team_roster({})
# 3. MLB MCP resolves: resolve_team → {id: 147}
# 4. Sports-proxy enriches: get_team_roster({teamId: "147"})
# 5. MLB MCP returns: Complete roster data
This eliminates the need for manual entity resolution and creates a natural language interface to MLB data!
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
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.