NBA Prop Lab

io.github.Khavel由 GitHub 账号 Khavel 发布v1.0.0-remote更新于 Oct 30, 2026

NBA and WNBA player-prop analytics: daily board, graded track record, matchup and referee data.

已验证Streamable HTTP可网页运行金融数据与分析

概览

AI 生成的概览

面向 NBA 与 WNBA 球员数据盘口分析的远程 MCP 服务器,提供每日模型榜单、已结算战绩、对位、使用率、裁判与球员资料。

可以做什么
  • 读取下一场次已发布的球员盘口榜单,以及上一期榜单的结算结果
  • 按联赛、等级和日期范围查看模型已结算的战绩
  • 查看各队对位防守数据、使用率排行、今日裁判组与裁判犯规数据
  • 按日期查询 NBA 与 WNBA 赛程、今日比赛与分区排名
  • 按姓名搜索球员,并获取某位球员的比赛日志、盘口赔率、伤病状态与模型选择
适用场景
适合让助手回答有关 NBA 或 WNBA 球员盘口、对位、使用率、裁判执法或球员近期状态的问题,并查看某个公开模型的选股历史结算表现。
运行要求
远程服务器无需安装:流式 HTTP 端点,无需认证、密钥或环境变量。可选的本地 stdio 版本需要 Node.js 与 npm,回测、选股与球员研究工具需在 PROPLAB_API_KEY 中提供 API 密钥。
安装前请注意
仅为体育信息分析,明确不是投注建议;提供方不接受下注,历史结果也不能预测未来。远程服务器无状态、不保存对话内容,但会接收联赛、日期、球员姓名或 ID 等工具参数,网页服务器保留常规访问日志。本地版本通过 HTTPS 调用公开 API,并从环境变量读取密钥;密钥仅在创建时显示一次,可随时撤销。

安装

在 SourceWeft 中

  1. 打开 控制台中的 NBA Prop Lab,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.Khavel%2Fproplab/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "nba-prop-lab": {
      "type": "http",
      "url": "https://nbaproplab.com/mcp"
    }
  }
}

README

PropLab MCP Server

Model Context Protocol server for PropLab: NBA and WNBA player-prop analytics. You get the daily board the model publishes before tip-off, its public record graded against the official box score, defense vs position, usage, referees and player research.

There are two ways to use it:

  • Remote server: works now, nothing to install, no key. https://nbaproplab.com/mcp
  • Local stdio package, built from this repository. It adds backtests and on-demand pick evaluation, which need an API key. It is not yet published on npm.

The data is informational sports analysis, not betting advice. PropLab does not take wagers, link to sportsbooks or guarantee outcomes, and past results do not predict future ones.

Remote server (recommended)

Streamable HTTP, stateless, no authentication. Every tool is read-only and returns the same public data shown on nbaproplab.com.

Claude (claude.ai, desktop, mobile): Settings → Connectors → Add custom connector. Name: PropLab. URL: https://nbaproplab.com/mcp. Authentication: none.

Claude Code:

bash
claude mcp add --transport http proplab https://nbaproplab.com/mcp

Codex:

bash
codex mcp add proplab --url https://nbaproplab.com/mcp

or in ~/.codex/config.toml:

toml
[mcp_servers.proplab]url = "https://nbaproplab.com/mcp"

Any other client that supports streamable HTTP can point at the same URL.

Tools

ToolParametersReturns
daily_boardleague (nba or wnba)The published player-prop board for the next slate (player, stat, line, direction, tier, model score) and how the previous board settled
track_recordleague?, tier? (Premium or Standard), from?, to?Settled record by tier and stat. The published record is the Premium tier (premiumHitRate, goodPicks) and Standard (marginalPicks); overall* fields also count internal ratings that are never published. Dates before 2026-04-03 are a backtest
defense_vs_positionleaguePoints, rebounds and assists each team allows to guards, forwards and centers relative to the league average, with defensive rating, pace and ranks
usage_leadersleaguePlayers ranked by usage rate this season, with last-10-games usage, minutes and points
nba_today—Today's NBA games with tip-off times, yesterday's scores and the standings
gamesdate? (yyyy-MM-dd)NBA and WNBA games on a date (default: today, US Eastern)
referee_assignments_today—The crew of each NBA game today, once the league publishes it the morning of game day
referees—NBA referees this season with games worked and fouls per game against the league average
search_playersqueryNBA and WNBA players by name, accents optional ("Jokic" finds Jokić)
player_researchplayerIdRecent game logs, current prop lines across books with hit rates, injury status, next-game context and the model's picks on that player

Example prompts:

  • "Which NBA teams allow the most rebounds to centers, and do any of them play today?"
  • "How has PropLab's published Premium tier done in the WNBA since April, by stat?"
  • "Search for Jokic and show his last 10 games and injury status."

Invalid arguments, for example league: "nfl", return a tool error that explains the valid values.

Local stdio package

Not yet published on npm, so build it from this repository:

bash
git clone https://github.com/Khavel/proplab-mcp.gitcd proplab-mcpnpm installnpm run build      # compiles src/index.ts → dist/index.js

Then register it in your MCP client with the absolute path to the build:

json
{  "mcpServers": {    "proplab": {      "command": "node",      "args": ["/absolute/path/to/proplab-mcp/dist/index.js"],      "env": {        "PROPLAB_API_KEY": "…"      }    }  }}

PROPLAB_API_KEY is optional: without it the public tools still work. For local development with hot reload, run npm run dev.

Environment variables

VariableRequired forDescription
PROPLAB_API_URLNoAPI base URL (default: https://nbaproplab.com)
PROPLAB_API_KEYBacktest, pick and research toolsBearer API key

The key is minted at nbaproplab.com → Account → API keys. It is shown once at creation and can be revoked from the same screen.

Tools

Public, no key:

ToolEndpointKey params
proplab_track_recordGET /api/v1/track-recordleague?, tier?, statType?, from?, to?
proplab_dashboardGET /api/v1/dashboard/todaydate?, league?
proplab_gamesGET /api/v1/gamesdate?
proplab_search_playersGET /api/v1/players/searchq
proplab_system_statusGET /api/v1/health—

With PROPLAB_API_KEY:

ToolEndpointKey params
proplab_backtest_summaryGET /api/v1/backtest/summaryfrom?, to?, league?
proplab_backtest_dailyGET /api/v1/backtest/dailyfrom?, to?, league?
proplab_backtest_by_ratingGET /api/v1/backtest/by-ratingfrom?, to?, league?
proplab_backtest_by_statGET /api/v1/backtest/by-statfrom?, to?, league?
proplab_pick_detailsGET /api/v1/picks/{id}id
proplab_evaluate_pickPOST /api/v1/picks/evaluateplayerName, statType, line, direction, opponentTeam?
proplab_player_researchGET /api/v1/research/player/{playerId}playerId

Verify locally

bash
npx @modelcontextprotocol/inspector node dist/index.js

Then call proplab_system_status, which needs no key and should return the live system status.

Data and privacy

  • Remote server: it keeps no state and stores nothing from your conversations. It only receives the arguments of each tool call (a league, a date, a player name or id), and the web server keeps its standard access logs.
  • Local package: it calls the public nbaproplab.com API over HTTPS and reads the key only from the environment, never logging it. No tool reads database credentials or app settings, or opens a shell.
  • Inputs are validated with zod and responses are truncated at 40,000 characters. Every tool is read-only except proplab_evaluate_pick, which scores a hypothetical pick and stores nothing.
  • Privacy policy: nbaproplab.com/legal/privacy. Responsible gambling: nbaproplab.com/responsible-gambling.

Support

Open an issue at github.com/Khavel/proplab-mcp/issues.

来源:README.md,提交 50b17ef

工具

10

daily_board

Daily player-prop board

The published NBA or WNBA player-prop board for the next slate (player, stat, line, direction, tier, model score) and how the last settled board did (hits, misses, voids). Informational analysis, not betting advice.

输入参数league

track_record

Public track record

Settled record of the model's picks with optional filters. Reading it: the overall*/total* fields count every pick the engine evaluated, including Weak ratings that are never published; the published record is the PREMIUM tier (premiumHitRate, goodPicks) and STANDARD (marginalPicks). Dates before 2026-04-03 are a backtest; use from=2026-04-03 for live picks only.

输入参数tofromtierleague

defense_vs_position

Defense vs position

How many points, rebounds and assists each team allows to guards, forwards and centers relative to the league average, with defensive rating, opponent pace and ranks.

输入参数league

usage_leaders

Usage rate leaders

Players ranked by usage rate this season, with last-10-games usage, minutes and points.

输入参数league

referee_assignments_today

NBA referee assignments today

Officiating crew of each NBA game today (published by the league the morning of game day) with each referee's fouls per game.

无需输入参数。

referees

NBA referees

All NBA referees this season with games worked, fouls per game and fouls above the league average.

无需输入参数。

nba_today

NBA today

Today's NBA games with tip-off times, yesterday's final scores and the current standings by conference.

无需输入参数。

games

Games by date

NBA and WNBA games on a date (defaults to today, US Eastern).

输入参数date

search_players

Search players

Find NBA and WNBA players by name; returns their ids for player_research.

输入参数query必填

player_research

Player research

A player's recent game logs, today's prop lines across books with hit rates, injury status, next game context and the model's picks on that player.

输入参数playerId必填

版本历史

1
  1. v1.0.0-remote最新Oct 22, 2026

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分