stat-api — Sports Data

com.stat-api由 stat-api.com 發布官方發布者v1.0.1更新於 Oct 24, 2026

NFL/NBA/MLB/NHL/PGA + DFS and prediction-market data. Browse free; query with a free API key.

已驗證Streamable HTTP可網頁執行金融資料與分析

服務詳細資訊

識別碼: com.stat-api/sports-data
傳輸: Streamable HTTP
執行環境: Web executable
信任: Verified
發布於: Sep 16, 2026

安全提示

MCP 服務會接收對話中的工具呼叫請求，並可能執行外部操作。啟用前請先了解該服務能做什麼，並只授予它所需的權限。

註冊中心已驗證此服務的命名空間屬於 stat-api.com，且該網域同時執行其端點。這可以確認發布者，但並不代表該服務的工具是安全的。

SourceWeft 的檢查只涵蓋條目是否完整、端點是否回應；不審查伺服器的程式碼，也不審查其工具的行為。

在 README 中新增徽章

向讀者展示該 MCP 服務已收錄於 SourceWeft，徽章連結到本頁。

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/com.stat-api%2Fsports-data.svg)](https://sourceweft.com/mcp/com.stat-api%2Fsports-data?utm_source=readme&utm_medium=badge)

概覽

AI 產生的概覽

stat-api 體育資料遠端 MCP 伺服器：可瀏覽 NFL、NBA、MLB、NHL、PGA、DFS 與預測市場資料表，並用免費 API 金鑰查詢。

可以做什麼: 瀏覽目錄：列出聯盟與資料分組、列出某聯盟的所有資料表、查看資料表的欄位、篩選條件與分頁限制
依欄位篩選與鍵集分頁查詢資料表，或用 GraphQL 做跨比賽、球隊、球員與賠率的關聯查詢
依主鍵取得單筆紀錄，並支援容錯的球員姓名搜尋
查詢某日期的比賽，以及與該比賽連結的預測市場合約
查看帳戶方案、已用配額與重設日期
適用情境: 當助理需要結構化的體育統計資料、賽程、攻守數據、DFS 薪資或預測市場價格（NFL、NBA、MLB、NHL、PGA），並希望先自行了解資料表結構再查詢時適用。
執行需求: 遠端 streamable HTTP 端點，不需本機執行環境或安裝套件。目錄類工具可匿名使用；資料類工具需要免費的 stat-api API 金鑰，透過 Authorization Bearer 標頭傳送。需要能連線至該端點的網路。

安裝前請注意

API 金鑰透過 Authorization 標頭傳送，應妥善保密。資料呼叫會消耗帳戶配額（get_record、search_players 與 api_usage 各計 1 筆紀錄），大量查詢可能用盡免費額度；依賴前請先查看 api_usage 與定價。

安裝

在 SourceWeft 中

開啟儀表板中的 stat-api — Sports Data，將其新增到工作區。
為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/com.stat-api%2Fsports-data/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "stat-api-sports-data": {
      "type": "http",
      "url": "https://api.stat-api.com/mcp"
    }
  }
}

README

STAT API — Sports Data MCP Server

Remote MCP server (streamable HTTP) for stat-api.com: NFL, NBA, MLB, NHL, and PGA data — players, games, box scores, play-by-play — plus DFS salaries/slates and prediction-market prices from Kalshi and Polymarket.

Endpoint: https://api.stat-api.com/mcp

Listed in the official MCP Registry as com.stat-api/sports-data.

Setup

Works anonymously out of the box; add a free API key to unlock the data tools.

Claude Code

bash

claude mcp add --transport http stat-api https://api.stat-api.com/mcp \  --header "Authorization: Bearer <YOUR_API_KEY>"

claude mcp add --transport http stat-api https://api.stat-api.com/mcp \  --header "Authorization: Bearer <YOUR_API_KEY>"

JSON config (Claude Desktop, Cursor, and most other clients)

json

{  "mcpServers": {    "stat-api": {      "type": "streamable-http",      "url": "https://api.stat-api.com/mcp",      "headers": { "Authorization": "Bearer <YOUR_API_KEY>" }    }  }}

{  "mcpServers": {    "stat-api": {      "type": "streamable-http",      "url": "https://api.stat-api.com/mcp",      "headers": { "Authorization": "Bearer <YOUR_API_KEY>" }    }  }}

Omit the headers block to connect without credentials — the catalog tools still work, and the server tells you where to get a key when you call a data tool.

Tools

No credentials needed (browse the catalog):

Tool	What it does
`list_leagues`	All leagues/data groups (nfl, nba, mlb, nhl, pga, dfs, kalshi, polymarket, reference) with table counts
`list_tables`	Every queryable table in one league, one-line summary each
`describe_table`	Full contract for a table: fields, types, accepted filters and operators, page limits, a runnable example

Free API key required (get one at stat-api.com):

Tool	What it does
`query_table`	Query any table with filters (`field__gte`, `__between`, `__like`, …) and keyset pagination
`get_record`	Fetch a single row by primary key
`search_players`	Typo-tolerant player-name search
`games_on_date`	Games on one calendar date (US-Eastern)
`game_markets`	Kalshi/Polymarket contracts linked to a specific game
`graphql_query`	Relational queries — game → teams → players → odds in one call
`api_usage`	Your key's plan, quota used/remaining, and reset date

Data coverage

NFL / NBA / MLB / NHL / PGA — teams, players, games, box scores, play-by-play, odds, injuries, news
DFS — DraftKings/FanDuel slates, salaries, contest results
Prediction markets — Kalshi and Polymarket events, markets, prices, and trades, linked to the underlying games

~200 tables total. list_leagues → list_tables → describe_table walks the whole catalog.

Other access methods

REST — OpenAPI 3.1 spec · interactive docs
GraphQL — POST https://api.stat-api.com/api/v1/graphql · SDL · IDE
Clients — @sports-db/client (npm) · sports-db (PyPI)

工具

list_leagues

List leagues

List every league/data group this API serves (nfl, nba, mlb, nhl, pga, dfs, reference) with table counts and availability. No credentials needed. Start here, then call list_tables.

無需輸入參數。

list_tables

List tables

List every queryable table in one league with a one-line summary each. No credentials needed. Follow with describe_table before querying.

輸入參數league必填

describe_table

Describe table

Full contract for one table: fields with types and descriptions, the filters query_table accepts (with operators like __gte/__lte/__between/__like and required filter combinations), page-size limits, primary key, and a runnable example URL. No credentials needed. Always call this before query_table — filters not listed here are rejected.

輸入參數table必填league必填

query_table

Query table

Query any table. Returns `{"<table>": [rows], "limit": N, "next_from_id": M|null, "has_more": bool}`. To read every row, start with from_id=0 and re-call with from_id set to the previous next_from_id until it is null. A call without from_id returns the first page in the table's default sort with next_from_id null. filters is a flat object of `field` or `field__op` keys from describe_table (e.g. {"season_id": 2024, "day__between": "20250101,20250131"}). Requires a stat-api account: sign in when the app asks (free account at https://stat-api.com), or send an API key as Authorization: Bearer <key>. Every returned row counts against the monthly record quota.

輸入參數limittable必填league必填filtersfrom_id

get_record

Get record

Fetch a single row by primary key. Returns the row object. Requires a stat-api sign-in or API key; costs 1 record of quota.

輸入參數id必填table必填league必填

search_players

Search NBA players

Fuzzy player-name search (typo-tolerant). Currently NBA only — for other leagues query the players table with a name filter via query_table. Returns player rows ordered by match quality. Requires a stat-api sign-in or API key; rows count against quota.

輸入參數name必填limitleague

games_on_date

Games on date

Games scheduled/played on one calendar date (US-Eastern) for nba, mlb, or nhl; defaults to today. Returns the same envelope as query_table on the games table. NFL is week-based, not date-based — for nfl, use query_table on nfl/games with season_id + week filters instead. Requires a stat-api sign-in or API key; rows count against quota.

輸入參數dateleague必填

graphql_query

GraphQL query

Run a GraphQL query against the same data with relations — nest from a game to its teams/players/odds in one call. Root fields are leagues (nfl, nba, …), each exposing its tables with the same filter arguments as REST plus `first`/`after` pagination. Do NOT send introspection queries (the schema is huge) — use describe_table instead; the SDL is at https://api.stat-api.com/api/v1/graphql/sdl. Requires a stat-api sign-in or API key; every row resolved anywhere in the tree counts against quota.

輸入參數query必填variables

api_usage

API usage

Your account's quota position: plan, monthly record limit, records used, remaining, and when the quota resets. Requires a stat-api sign-in or API key; costs 1 record.