
Connects Claude to The Odds API's live sportsbook data across 70+ bookmakers and 30+ leagues. Exposes three core tools: list_sports to see what's in season, get_scores for live and recent results (costs 2 API requests per call), and get_events to pull upcoming games and discover event IDs without fetching odds. Part of the Pipeworx gateway, so you can either connect to this standalone server or use the full gateway for access to 250+ data sources. Includes an ask_pipeworx helper that lets you query in plain English instead of calling tools directly. Useful when you need real sports betting lines, game schedules, or score data piped into your Claude workflow.
The Odds API MCP — sportsbook odds across 70+ books for 30+ sports leagues (NFL, NBA, MLB, NHL, soccer, MMA, golf, tennis, esports, cricket, ...).
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
list_sports(all?) — list available sports/leaguesget_odds(sport_key, regions?, markets?, odds_format?, date_format?, bookmakers?, events?) — current oddsget_event_odds(sport_key, event_id, regions?, markets?) — odds for a specific event (allows more markets like player props)get_scores(sport_key, days_from?) — live + recent final scoresget_events(sport_key, date_format?, event_ids?) — list upcoming + live eventsodds_api_quota() — credits left and used this month on the key serving the call (free; costs no upstream credit)PLATFORM_ODDS_API_KEY?_apiKey=<key> after registering at https://the-odds-api.com/Free tier: 500 requests/month. Each odds-payload market counts as 1 request. list_sports and
odds_api_quota are free — they do not draw down the balance.
When the month's credits are spent, the metered tools return upstream_throttled and a hint to
bring your own key. Upstream answers an exhausted balance with HTTP 401, the same status as a
bad key, so read the message rather than the status: odds_api_quota tells the two apart.
Credits reset on the plan anniversary, not on the 1st of the month.
https://api.the-odds-api.com/v4/ — ?apiKey= query.
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"odds-api": {
"url": "https://gateway.pipeworx.io/odds-api/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/odds-api/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Odds Api data" })
The gateway picks the right tool and fills the arguments automatically.
MIT