Skip to main content
Glama
Sign In

NBA Prop Lab

by io.github.Khavel
OverviewDiscussionsAdmin

Server Details

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

If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
Repository
Khavel/proplab-mcp
GitHub Stars
0
Server Listing
NBA Prop Lab MCP Server
ChatGPT
–
Claude
PropLab

TDQS

A3.7/5.0

Scored across 10 tools

Disambiguation3/5

Most tools target distinct data, but `games` and `nba_today` overlap heavily on today's NBA games, and `daily_board`/`track_record`/`player_research` all surface model picks and results with blurry boundaries. Descriptions help but don't fully resolve which tool to call for 'today's slate' versus 'how are the picks doing', so an agent will occasionally misselect.

Naming Consistency4/5

All names use snake_case and are predominantly noun/entity phrases (`games`, `referees`, `usage_leaders`, `track_record`), which reads predictably. Minor deviations: one verb-based name (`search_players`) and ad hoc `_today` suffixes (`nba_today`, `referee_assignments_today`) even though other tools default to today implicitly.

Tool Count5/5

Ten tools is well within the sweet spot and each maps to a distinct slice of the prop-analysis workflow: find player, research player, board, matchup defense, usage, refs, games, and record. Nothing feels padded or missing from a count perspective.

Completeness4/5

The surface covers the core lifecycle — discovery (`search_players`), deep player context, boards, positional matchup defense, usage, officiating, schedules and historical performance verification. Minor gaps remain: no dedicated team-level stats/matchup tool beyond `defense_vs_position`, no slate-wide injury feed, and no forward-looking schedule beyond a single date.

Available Tools

10 tools
daily_boardDaily player-prop boardA
Read-onlyIdempotent
Inspect

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.

Inputs: league.

defense_vs_positionDefense vs positionA
Read-onlyIdempotent
Inspect

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.

Inputs: league.

gamesGames by dateA
Read-onlyIdempotent
Inspect

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

Inputs: date.

nba_todayNBA todayA
Read-onlyIdempotent
Inspect

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

Inputs: no named parameters.

player_researchPlayer researchA
Read-onlyIdempotent
Inspect

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.

Inputs: playerId (required).

referee_assignments_todayNBA referee assignments todayA
Read-onlyIdempotent
Inspect

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

Inputs: no named parameters.

refereesNBA refereesA
Read-onlyIdempotent
Inspect

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

Inputs: no named parameters.

search_playersSearch playersA
Read-onlyIdempotent
Inspect

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

Inputs: query (required).

track_recordPublic track recordA
Read-onlyIdempotent
Inspect

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.

Inputs: to, from, tier, league.

usage_leadersUsage rate leadersA
Read-onlyIdempotent
Inspect

Players ranked by explicitly observed usage percentage (0–100), not unknown/default zero values. Requires at least 10 observed qualifying games. Season and last-10 played-game observation denominators are included; missing L10 is null. Empty coverage means unavailable, not zero usage. Previous-season fallback is explicitly labelled; asOf is the query date. Minutes/points use all qualifying played games.

Inputs: league.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • PropLine

      PropLineofficial

      proplineapi
      A
      license
      A
      quality
      B
      maintenance
      Live sports betting odds, cross-book +EV, and graded player-prop resolution across 13 books.
      11
      386 npm
      1
      MIT

    • DunkAPI MCP server

      noahowsh
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to query NBA, WNBA, and men's and women's college basketball data through tools for play-by-play, shot charts, stats, odds, props, injuries, and ratings.
      MIT

    • NegativeEV

      negative-ev
      A
      license
      Not graded
      quality
      C
      maintenance
      Grades sports bets against thousands of play-by-play simulations, reporting simulated probability, implied probability, and edge.
      MIT

    • SportIntel MCP Server

      roizenlabs
      A
      license
      A
      quality
      D
      maintenance
      Provides AI-powered sports analytics for Daily Fantasy Sports (DFS) with real-time player projections, lineup optimization, live odds aggregation from multiple sportsbooks, and SHAP-based explainability to understand recommendation reasoning.
      4
      1
      MIT
    Try in Browser
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources