get_player_career_statsLABSCO SUMMARY
The argument gets settled with the actual numbers.
It covers the whole range from a career line to a fourth-quarter split, which means a question that starts casual can be followed all the way down without leaving the conversation to open a stats site.
What it is
A player-statistics service reading basketball-reference.com, organized in three depths: the core season and career numbers, then game-level and situational analytics, then trends, records and all-time rankings.
What you get
- Career statistics season by season, and any single season including its playoffs
- The same numbers in the form you want them: per game, season and career totals, or per-36-minutes for pace adjustment
- Advanced metrics — PER, true shooting, win shares, BPM, VORP — and shooting splits by volume and percentage
- Two players compared side by side, and career highlights: best seasons, milestones, achievements
- Game logs, month-by-month splits, performance against a named team, and clutch numbers in close games
- Career trend analysis, game highs and triple-doubles, milestone projections, and where a player sits in NBA history
Requirements
Network access — every answer is read from basketball-reference.com when you ask for it, so nothing is cached locally and the numbers are as current as that site is.
Setup effort
Build from source — git clone https://github.com/ziyadmir/nba-player-stats-mcp
USE CASES
01
Settling a debate about who was better
Put two players side by side across their careers, then adjust for pace with per-36 numbers so eras that played at different speeds can be compared honestly.
02
Understanding whether a hot streak is real
Read the game logs and the monthly splits rather than the season average — a strong month and a strong season look identical in a per-game line.
03
Checking whether someone actually shows up in the clutch
Pull the close-game and fourth-quarter numbers, which is where a reputation either survives contact with the record or does not.
04
Preparing for a matchup
Look at career performance against the specific opponent, plus home and away and rest-day splits, before predicting anything.
05
Following a chase for a record
Track progress toward a milestone with the projections attached, so "will he get there" has a number behind it rather than a feeling.
06
Placing a career in history
Read the all-time rankings and the year-over-year trend together, which is how a peak and a decline get separated from a total.
23 tools
Listed in project docs. Your client may show a different list.
get_player_season_statsget_player_advanced_statsget_player_per36_statscompare_playersget_player_shooting_splitsget_player_totalsget_player_playoff_statsget_player_headshot_urlget_player_career_highlightsget_player_game_logget_player_specific_statget_player_vs_team_statsget_player_awards_votingget_player_monthly_splitsget_player_clutch_statsget_player_playoffs_by_yearget_player_career_trendsget_player_game_highsget_player_situational_splitsget_player_quarter_statsget_player_milestone_trackerget_player_rankingsBEFORE YOU INSTALL
What to know first
Tools you get
23 tools named in the project's documentation.
Requires
- python on PATH
- Python 3.8
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone this one yourself.
Server setup
Clone the repository:
TERMINAL
git clone https://github.com/ziyadmir/nba-player-stats-mcp
cd nba-player-stats-mcpInstall dependencies:
TERMINAL
pip install -r requirements.txtMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"nba-player-stats": {
"command": "python",
"args": [
"<YOUR_PATH_TO_BASKETBALL>/src/server.py"
],
"cwd": "<YOUR_PATH_TO_BASKETBALL>"
}
}
}
