Sports MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Sports MCP Server What are the odds for the Lakers vs Celtics game tonight?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ποΈ Sports MCP Server
A Model Context Protocol (MCP) server that unifies The Odds API and SportMonks Football API v3 into a single tool surface for Claude Desktop and Claude Code.
What This Does
Source | Coverage | Tools |
The Odds API | All sports β NBA, NFL, NHL, NCAAM, NCAAF, Soccer, Tennis, MMA, Golf, MLB | 10 tools: odds, scores, events, markets, participants, historical |
SportMonks | Football (soccer) deep data β EPL, La Liga, Bundesliga, Ligue 1, Serie A, Champions League, etc. | 18 tools: fixtures, standings, statistics, xG, predictions, odds, livescores, squads |
Total: 28 tools available to Claude via MCP.
Related MCP server: Sports Hub MCP Server
Quick Start
1. Install dependencies
cd sports-mcp-server
npm install
npm run build2. Set your API keys
You'll configure these in the Claude Desktop config (step 3), but for testing:
export ODDS_API_KEY="your-odds-api-key-here"
export SPORTMONKS_TOKEN="your-sportmonks-token-here"3. Configure Claude Desktop
Add this to your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"sports-data": {
"command": "node",
"args": ["/FULL/PATH/TO/sports-mcp-server/dist/index.js"],
"env": {
"ODDS_API_KEY": "your-odds-api-key-here",
"SPORTMONKS_TOKEN": "your-sportmonks-token-here"
}
}
}
}β οΈ Replace
/FULL/PATH/TO/with the actual absolute path to the project.
4. Restart Claude Desktop
After saving the config, restart Claude Desktop. You should see the sports tools available in the MCP tools menu.
For Claude.ai (Web / Chrome) β β This is what you want
The web app needs an HTTP server, not stdio. Here's how:
Step 1: Build & start the HTTP server
cd sports-mcp-server
npm install
npm run build
# Start the HTTP server with your API keys
ODDS_API_KEY=your-key-here SPORTMONKS_TOKEN=your-token-here npm run start:httpYou should see:
ποΈ Sports MCP Server (HTTP/SSE) running on http://localhost:3456
Tools: 10 Odds API + 18 SportMonks = 28 total
Odds API key: β
configured
SportMonks token: β
configuredStep 2: Connect in Claude.ai
Go to claude.ai β Settings (bottom-left gear icon)
Click Integrations in the left sidebar
Click Add Custom Integration
Set:
Name:
Sports DataURL:
http://localhost:3456/sse
Save and enable it
That's it β the 28 tools are now available in your Claude.ai conversations.
Optional: Protect with auth token
ODDS_API_KEY=xxx SPORTMONKS_TOKEN=xxx MCP_AUTH_TOKEN=my-secret npm run start:httpThen add the token in the integration config as a Bearer token.
Optional: Run on a remote server
If you want it always-on (e.g. on a VPS or Render/Railway):
Deploy the project to your server
Run
npm run start:httpwith your env varsUse
https://your-server.com/sseas the integration URLSet
MCP_AUTH_TOKENfor security
Keep it running (local)
Use pm2 or a simple background process:
# Install pm2 globally
npm install -g pm2
# Start as a daemon
ODDS_API_KEY=xxx SPORTMONKS_TOKEN=xxx pm2 start dist/server-http.js --name sports-mcp
# Auto-restart on reboot
pm2 startup
pm2 saveFor Claude Desktop (local app)
See the config under Quick Start above β uses stdio transport via dist/index.js.
For Claude Code
claude mcp add sports-data node /FULL/PATH/TO/sports-mcp-server/dist/index.js \
-e ODDS_API_KEY=your-key \
-e SPORTMONKS_TOKEN=your-tokenTool Reference
The Odds API Tools (prefix: odds_)
Tool | Description | Quota Cost |
| List all available sports and their keys | Free |
| List upcoming/live events for a sport | Free |
| Primary tool β get odds for upcoming/live games (ML, spreads, totals) | markets Γ regions |
| Live scores + recently completed games | 1-2 |
| Odds for a single event β supports ALL markets including player props | unique markets Γ regions |
| Discover available market keys for an event | 1 |
| List teams/players for a sport | 1 |
| Historical odds snapshot at a timestamp | 10 Γ markets Γ regions |
| Historical events at a timestamp | 1 |
| Historical odds for single event β all markets | 10 Γ markets Γ regions |
Common sport keys: basketball_nba, basketball_ncaab, americanfootball_nfl, americanfootball_ncaaf, icehockey_nhl, soccer_epl, soccer_germany_bundesliga, soccer_spain_la_liga, soccer_france_ligue_one, tennis_atp_*, tennis_wta_*
SportMonks Tools (prefix: sm_)
Tool | Description |
| Live soccer scores (inplay / all today / latest updated) |
| Fixtures by ID, date, date range, team, H2H, or search |
| Leagues β all, by ID, live, by country, by team, search |
| Seasons β all, by ID, by team, search |
| League tables β by season, round, or live |
| Teams β all, by ID, country, season, search |
| Players β by ID, country, search |
| Team squad (current or by season) |
| Season/stage/round statistics for teams or players |
| Top scorers by season or stage |
| Probabilities and value bets (SM's own model) |
| Expected goals (xG) by team or player |
| Pre-match odds by fixture, bookmaker, or market |
| In-play odds by fixture, bookmaker, or market |
| Match schedules by season, team, or both |
| Round data by season or ID |
| List available betting markets |
| List available bookmakers |
Using Includes (SportMonks)
SportMonks tools support an include parameter for enriched responses:
include: "participants,scores,league,statistics,events"
include: "player,position,teams"
include: "fixtures,rounds"Using Filters (SportMonks)
Some endpoints support filters:
filters: "fixtureLeagues:8" # Filter by league ID
filters: "eventTypes:14,18" # Filter event typesExample Prompts
Once configured, you can ask Claude things like:
"Get me tonight's NBA odds from DraftKings and FanDuel β spreads, moneylines, and totals"
"Pull EPL standings for this season"
"What are the live soccer scores right now?"
"Compare the historical odds movement for the Lakers game last Tuesday"
"Get Arsenal's xG data and current squad"
"Show me value bets from SportMonks predictions for today's fixtures"
"Get player props available for tonight's NFL game"
Architecture
src/
βββ index.ts # MCP server entry β stdio transport (Claude Desktop / Claude Code)
βββ server-http.ts # MCP server entry β HTTP/SSE transport (claude.ai web)
βββ odds-api.ts # The Odds API tool definitions (10 tools)
βββ sportmonks.ts # SportMonks tool definitions (18 tools)
βββ http.ts # Shared HTTP utility (fetch + URL builder)License
MIT
Available Tools
28 toolsodds_get_event_marketsA
Discover which market keys are available for a specific event from each bookmaker. Use this before odds_get_event_odds to know which markets to request. Cost: 1 quota.
Inputs: sport (required), eventId (required), regions, bookmakers.
odds_get_event_oddsA
Get odds for a SINGLE event with any available market (including player props, alternate lines, period markets). Use odds_get_events to find event IDs first. Cost = unique markets returned Γ regions.
Inputs: sport (required), eventId (required), markets, regions, +2 more.
odds_get_eventsA
List upcoming and live events for a sport. Returns event IDs, teams, and commence times. Free β no quota cost. Use sport keys from odds_get_sports.
Inputs: sport (required), eventIds, commenceTimeTo, commenceTimeFrom.
odds_get_historical_event_oddsA
Get historical odds for a SINGLE event at a specific timestamp. Supports all markets including player props (available after 2023-05-03). Cost: 10 Γ markets Γ regions. PAID PLANS ONLY.
Inputs: date (required), sport (required), eventId (required), markets, +3 more.
odds_get_historical_eventsA
List events as they appeared at a historical timestamp. Use to find event IDs for historical event odds. Cost: 1 quota. PAID PLANS ONLY.
Inputs: date (required), sport (required), eventIds, commenceTimeTo, +1 more.
odds_get_historical_oddsA
Get a snapshot of odds at a specific historical timestamp (available from June 2020, 5-min intervals from Sep 2022). Cost: 10 Γ markets Γ regions. PAID PLANS ONLY.
Inputs: date (required), sport (required), markets, regions, +2 more.
odds_get_oddsA
Get upcoming and live game odds for a sport. Returns bookmaker odds for specified markets and regions. This is the primary endpoint for pre-game odds analysis. Cost = markets Γ regions.
Inputs: sport (required), markets, regions, eventIds, +4 more.
odds_get_participantsA
List teams/players for a sport (whitelist of known participants). Cost: 1 quota.
Inputs: sport (required).
odds_get_scoresA
Get live scores and recently completed game scores. Live scores update ~every 30s. Use daysFrom (1-3) to include completed games. Cost: 1 without daysFrom, 2 with daysFrom.
Inputs: sport (required), daysFrom, eventIds.
odds_get_sportsA
List all available sports from The Odds API. Returns sport keys used in other endpoints. Free β no quota cost.
Inputs: all.
sm_bookmakersB
List available bookmakers in SportMonks. Use bookmaker IDs with odds endpoints.
Inputs: id, mode, fixtureId, searchQuery.
sm_expected_xgB
Get Expected Goals (xG) data by team or player. Requires xG add-on plan.
Inputs: id (required), mode, include.
sm_fixturesA
Get football fixtures. Supports: by ID, by date, by date range, by date range for team, head-to-head, search by name. The core endpoint for match data.
Inputs: mode (required), id, date, page, +8 more.
sm_leaguesA
Get football leagues. Modes: 'all', 'by_id', 'live' (leagues currently in play), 'by_country', 'by_team', 'search'. Returns league IDs needed for other endpoints.
Inputs: id, mode, page, teamId, +3 more.
sm_livescoresA
Get live football/soccer scores. Modes: 'inplay' (currently playing), 'all' (today's livescores), 'latest' (most recently updated). Use include param for enriched data.
Inputs: mode, include.
sm_marketsA
List available betting markets in SportMonks. Use market IDs with sm_odds_prematch and sm_odds_inplay.
Inputs: id, mode, searchQuery.
sm_odds_inplayB
Get live in-play odds from SportMonks. Modes: 'all', 'by_fixture', 'by_fixture_bookmaker', 'by_fixture_market', 'latest'.
Inputs: mode, page, include, marketId, +2 more.
sm_odds_prematchA
Get pre-match odds from SportMonks. Modes: 'by_fixture', 'by_fixture_bookmaker', 'by_fixture_market', 'latest'. Useful for comparing with The Odds API data.
Inputs: mode, page, include, marketId, +2 more.
sm_playersC
Get football players. Modes: 'by_id', 'by_country', 'search'. Rich data with includes.
Inputs: id, mode, page, include, +2 more.
sm_predictionsB
Get SportMonks predictions. Modes: 'probabilities' (all), 'by_fixture' (fixture-specific probabilities), 'value_bets', 'value_bets_by_fixture'. Great for model cross-reference.
Inputs: mode, page, include, fixtureId.
sm_roundsB
Get round information. Modes: 'by_season', 'by_id'. Round IDs are needed for standings by round.
Inputs: id, mode, include, seasonId.
sm_schedulesB
Get match schedules. Modes: 'by_season', 'by_team', 'by_season_team'. Useful for planning which fixtures to track.
Inputs: mode, page, teamId, include, +1 more.
sm_seasonsA
Get football seasons. Modes: 'all', 'by_id', 'by_team', 'search'. Season IDs are needed for standings, statistics, and topscorers.
Inputs: id, mode, page, teamId, +2 more.
sm_standingsA
Get league standings / tables. Modes: 'by_season', 'by_round', 'live' (live standings by league). Essential for form analysis.
Inputs: mode, include, roundId, leagueId, +1 more.
sm_statisticsB
Get season/stage/round statistics for a participant (team or player). Essential for form and performance analysis.
Inputs: mode, include, roundId, stageId, +2 more.
sm_teamsB
Get football teams. Modes: 'by_id', 'by_country', 'by_season', 'search'. Returns team IDs used across all endpoints.
Inputs: id, mode, page, include, +3 more.
sm_team_squadsA
Get a team's current squad or squad for a specific season.
Inputs: teamId (required), include, seasonId.
sm_topscorersA
Get top scorers for a season or stage.
Inputs: mode, include, stageId, seasonId.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
TDQS
Scored across 28 tools
The two provider prefixes (odds_ and sm_) create overlapping functionality: odds_get_odds, odds_get_event_odds, sm_odds_prematch, and sm_odds_inplay all provide odds, while odds_get_scores and sm_livescores both give scores. Although descriptions mention the source API, agents may struggle to pick the right tool when multiple options serve the same purpose.
The odds_ tools follow a verb_noun pattern (get_sports, get_events, get_odds), but the sm_ tools use bare nouns (livescores, fixtures, leagues) without verbs. This split between two naming conventions within one server is inconsistent, and compound names like sm_team_squads and sm_expected_xg further deviate from a clear pattern.
With 28 tools, the server is heavy and exceeds the typical 25-tool threshold. While it integrates two major sports APIs, the high count increases selection overhead and includes overlapping endpoints that could be consolidated or parameterized.
The server covers a broad spectrum of sports data: odds (prematch, inplay, historical, props), scores, fixtures, standings, statistics, predictions, and more. Minor gaps exist, such as no unified search across both providers, but for the stated sports data domain the coverage is nearly complete.
Maintenance
Related MCP Connectors
The Odds API MCP β sportsbook odds across 70+ books, 30+ leagues
Unified MCP Server is a remote MCP connector for AI agents and vertical AI products that provides access to 22,000+ authorized SaaS tools across 400+ integrations and 24 categories directly inside LLMs (Claude, GPT, Gemini, Cohere). Tools operate only on explicitly authorized customer connections, enabling agents to safely read and write against live third-party systems.
API-Football MCP β comprehensive soccer/football data
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
Related MCP Servers
- AlicenseBqualityBmaintenanceAn MCP server that exposes sports-data APIs from multiple providers (AFL, Sportsbet, Entain, NRL) as interchangeable tools, enabling cross-provider odds and stats comparison.500161 PyPI34MIT
- AlicenseBqualityBmaintenanceA unified MCP server that aggregates 32 sports API providers into a single service, providing 336 tools for scores, stats, odds, esports, and more across 70+ sports.14165184 npm41MIT
- FlicenseNot gradedqualityDmaintenanceAn MCP server that connects Claude Desktop to The Odds API, giving Claude real-time access to sports odds, scores, and schedules across 80+ sports and leagues worldwide.-
- FlicenseBqualityDmaintenanceMCP server that enables Claude Desktop to access real-time sports data including live scores, fixtures, standings, and NBA statistics using free APIs.10-