Sports MCP Server
A unified MCP server that combines The Odds API and SportMonks Football API v3 to provide 28 tools for sports data like odds, scores, fixtures, standings, and predictions, enabling Claude to interact with a wide range of sports information.
README
🏟️ 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 — NBA, NFL, NHL, NCAAM, NCAAF, Soccer, Tennis, MMA, Golf, MLB | 10 tools: odds, scores, events, markets, participants, historical |
| SportMonks | Football (soccer) deep data — 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.
Quick Start
1. Install dependencies
cd sports-mcp-server
npm install
npm run build
2. 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"
}
}
}
}
⚠️ 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) — ⭐ 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:http
You should see:
🏟️ Sports MCP Server (HTTP/SSE) running on http://localhost:3456
Tools: 10 Odds API + 18 SportMonks = 28 total
Odds API key: ✅ configured
SportMonks token: ✅ configured
Step 2: Connect in Claude.ai
- Go to claude.ai → Settings (bottom-left gear icon)
- Click Integrations in the left sidebar
- Click Add Custom Integration
- Set:
- Name:
Sports Data - URL:
http://localhost:3456/sse
- Name:
- Save and enable it
That's it — 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:http
Then 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 vars - Use
https://your-server.com/sseas the integration URL - Set
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 save
For Claude Desktop (local app)
See the config under Quick Start above — 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-token
Tool Reference
The Odds API Tools (prefix: odds_)
| Tool | Description | Quota Cost |
|---|---|---|
odds_get_sports |
List all available sports and their keys | Free |
odds_get_events |
List upcoming/live events for a sport | Free |
odds_get_odds |
Primary tool — get odds for upcoming/live games (ML, spreads, totals) | markets × regions |
odds_get_scores |
Live scores + recently completed games | 1-2 |
odds_get_event_odds |
Odds for a single event — supports ALL markets including player props | unique markets × regions |
odds_get_event_markets |
Discover available market keys for an event | 1 |
odds_get_participants |
List teams/players for a sport | 1 |
odds_get_historical_odds |
Historical odds snapshot at a timestamp | 10 × markets × regions |
odds_get_historical_events |
Historical events at a timestamp | 1 |
odds_get_historical_event_odds |
Historical odds for single event — all markets | 10 × markets × 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 |
|---|---|
sm_livescores |
Live soccer scores (inplay / all today / latest updated) |
sm_fixtures |
Fixtures by ID, date, date range, team, H2H, or search |
sm_leagues |
Leagues — all, by ID, live, by country, by team, search |
sm_seasons |
Seasons — all, by ID, by team, search |
sm_standings |
League tables — by season, round, or live |
sm_teams |
Teams — all, by ID, country, season, search |
sm_players |
Players — by ID, country, search |
sm_team_squads |
Team squad (current or by season) |
sm_statistics |
Season/stage/round statistics for teams or players |
sm_topscorers |
Top scorers by season or stage |
sm_predictions |
Probabilities and value bets (SM's own model) |
sm_expected_xg |
Expected goals (xG) by team or player |
sm_odds_prematch |
Pre-match odds by fixture, bookmaker, or market |
sm_odds_inplay |
In-play odds by fixture, bookmaker, or market |
sm_schedules |
Match schedules by season, team, or both |
sm_rounds |
Round data by season or ID |
sm_markets |
List available betting markets |
sm_bookmakers |
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 types
Example Prompts
Once configured, you can ask Claude things like:
- "Get me tonight's NBA odds from DraftKings and FanDuel — 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/
├── index.ts # MCP server entry — stdio transport (Claude Desktop / Claude Code)
├── server-http.ts # MCP server entry — HTTP/SSE transport (claude.ai web)
├── odds-api.ts # The Odds API tool definitions (10 tools)
├── sportmonks.ts # SportMonks tool definitions (18 tools)
└── http.ts # Shared HTTP utility (fetch + URL builder)
License
MIT
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。