SportWizzard MCP Server
Enables AI agents to query live sports betting data including odds, edges, arbitrage opportunities, player/team stats, and reference data using the SportWizzard API.
README
SportWizzard MCP Server
Query live sports-betting data — odds, edges, arbitrage, player/team stats and reference data — from any MCP-capable AI agent (Claude Desktop, Cursor, Claude Code, etc.) using your SportWizzard API key.
This is a Model Context Protocol stdio server. It wraps the SportWizzard REST v1 API in a curated set of tools your agent can call.
Status: publishing to npm is pending. Until then, run it from a local checkout (see From source). The
npx sportwizzard-mcpcommand below works once the package is published.
Quick start
npx -y sportwizzard-mcp
Set your API key via the SPORTWIZZARD_API_KEY environment variable. Get a key at https://sportwizzard.com/account.
While SportWizzard is in its pre-billing public phase the data endpoints are open, so the tools also work without a key. Once metering is enabled a missing/invalid key returns a clear error.
Claude Desktop
Add this to your claude_desktop_config.json
(macOS: ~/Library/Application Support/Claude/claude_desktop_config.json,
Windows: %APPDATA%\Claude\claude_desktop_config.json):
{
"mcpServers": {
"sportwizzard": {
"command": "npx",
"args": ["-y", "sportwizzard-mcp"],
"env": {
"SPORTWIZZARD_API_KEY": "sk_your_key_here"
}
}
}
}
Restart Claude Desktop. You'll see the SportWizzard tools available in the chat.
Try it without a key (mock mode)
Set SPORTWIZZARD_MOCK=1 to return canned sample responses — no key, no network. Great for wiring things up before you have a key:
{
"mcpServers": {
"sportwizzard": {
"command": "npx",
"args": ["-y", "sportwizzard-mcp"],
"env": { "SPORTWIZZARD_MOCK": "1" }
}
}
}
Configuration
| Env var | Default | Purpose |
|---|---|---|
SPORTWIZZARD_API_KEY |
(none) | Your SportWizzard API key, sent as the X-Api-Key header. |
SPORTWIZZARD_BASE_URL |
https://api.sportwizzard.com |
Override the API base URL (e.g. for local testing). |
SPORTWIZZARD_MOCK |
(off) | Set to 1 to return canned sample data instead of calling the API. |
Tools
| Tool | Endpoint | What it does |
|---|---|---|
list_events |
GET /api/v1/events |
List events/fixtures — the spine. Filter by league, team_id, status, starts_after/before; paginate with cursor. |
get_event |
GET /api/v1/events/{id} |
Full event detail: venue, season, scores, and game context (weather, lineups, probable pitchers, officials). |
get_event_stats |
GET /api/v1/events/{id}/stats |
The box score: every player's stat line + the team result row for one event. |
get_event_odds |
GET /api/v1/events/{id}/odds |
Every sportsbook price for one event (flat rows: book × market × selection). |
get_odds |
GET /api/v1/odds |
Core odds query, scoped by event_id / player_id / team_id / sportsbook / market / league. |
get_player_odds |
GET /api/v1/players/{id}/odds |
All current prices for one player (props). |
get_team_odds |
GET /api/v1/teams/{id}/odds |
All current prices for one team. |
get_edges |
GET /api/v1/edges |
+EV edges vs. devigged fair market. Filter by league, source, min_edge, event_id. |
get_arbitrage |
GET /api/v1/arbitrage |
Arbitrage opportunities with legs + stake fractions. Filter by type (two_way/three_way), min_profit. |
list_players |
GET /api/v1/players |
Players reference. Filter by league/team. |
list_teams |
GET /api/v1/teams |
Teams reference. Filter by league. |
get_player_stats |
GET /api/v1/players/{id}/stats |
Player season/historical stats. |
get_team_stats |
GET /api/v1/teams/{id}/stats |
Per-game team stats/results, optionally scoped to a season. |
get_player_game_logs |
GET /api/v1/stats/players |
Bulk per-game player stat rows (game logs) by player/team/event — the model-training feed. |
get_account_usage |
GET /api/v1/account/usage |
Your plan tier, rate limit, and monthly usage. |
download_snapshot |
GET /api/v1/snapshot |
Downloads the FULL live board (tens of MB gzip, 80k+ markets) to a file — you provide save_path; it never enters the context window. .gz path keeps gzip, otherwise decompressed JSON. Returns path/bytes/etag; pass the etag back to skip unchanged downloads (304). |
list_sportsbooks |
GET /api/v1/sportsbooks |
Sportsbooks/DFS platforms tracked, with live market counts. |
list_leagues |
GET /api/v1/leagues |
Leagues currently covered. |
list_markets |
GET /api/v1/markets |
Supported market types, with live counts. |
status |
GET /api/v1/status |
Total live markets + active sportsbook count. |
Every response uses the SportWizzard envelope { success, data, nextCursor, meta }. When a nextCursor is present the tool appends a _paging hint so the agent knows to call again with cursor=....
From source
git clone https://github.com/adamruehle/sportwizzard-mcp.git
cd sportwizzard-mcp
npm install
npm run build
SPORTWIZZARD_MOCK=1 node dist/index.js # or set SPORTWIZZARD_API_KEY
Point your MCP client's command at node and args at the absolute path to dist/index.js.
License
MIT © SportWizzard LLC
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.