nba_live_scoreboardLABSCO SUMMARY
Live and historical NBA data in the same conversation.
The two questions people actually ask — what is happening right now, and how does that compare — usually mean two sources. Here the live play-by-play and a player's career splits come from one server, and teams can be named instead of looked up by ID.
What it is
A reader for NBA statistics and live game data. Live scoreboards, box scores and play-by-play come from games in progress; the historical side covers player careers, team game logs, standings and league-wide team statistics.
What you get
- Today's scoreboard with game IDs, start times, scores and broadcast details — and the scoreboard for any other date
- A live box score and live play-by-play for a game ID, including scoring plays, fouls, timeouts and substitutions
- Player biography, and career statistics per game, as totals or per 36 minutes
- A player's game logs across a date range, and the list of currently active players
- Team game logs and team statistics looked up by name, so the numeric ID is not needed
- Standings for a season and season type, and statistics for all teams across multiple seasons
- Game results for a team over a date range
Requirements
Python 3.13 and a local clone of the repository — it calls the NBA API over the network. Requests carry a timeout, so a slow call fails rather than hangs.
Setup effort
Build from source — git clone https://github.com/obinopaul/nba-mcp-server.git
USE CASES
01
Following a game in progress
Take the game IDs off today's scoreboard, then read the live box score and play-by-play for the one you care about.
02
Comparing two players
Pull each career in the same form — per game, totals or per 36 minutes — with the biography behind the numbers.
03
Looking at a player's recent form
Read the game logs over a date range instead of a season average that hides a slump.
04
Assessing a team's season
Fetch the team's game logs by name, its statistics, and where it sits in the standings.
05
Putting a team in league context
Read statistics for every team across several seasons, so one team's number has something to be measured against.
06
Checking what happened on a past date
Ask for the scoreboard on a specific day, or a team's results across a range of them.
13 tools
Listed in project docs. Your client may show a different list.
nba_live_boxscorenba_live_play_by_playnba_common_player_infonba_player_career_statsnba_list_active_playersnba_player_game_logsnba_team_game_logs_by_namenba_fetch_game_resultsnba_team_standingsnba_team_stats_by_namenba_all_teams_statsnba_list_todays_gamesBEFORE YOU INSTALL
What to know first
Tools you get
13 tools named in the project's documentation.
Requires
Python 3.13 (the README creates a conda environment with python=3.13)
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone this one yourself.
Server setup
TERMINAL
git clone https://github.com/obinopaul/nba-mcp-server.git
cd nba-mcp-server
pip install -r requirements.txtMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"nba_mcp_server": {
"command": "<YOUR_PATH_TO_PYTHON>",
"args": [
"<YOUR_PATH_TO_NBA_SERVER>"
]
}
}
}
