get_player_infoLABSCO SUMMARY
An agent can answer NHL questions from live league data.
One question replaces the hop between box score, standings page and roster. For a specific game the play-by-play comes back event by event, which is the part a scoreboard cannot give you.
What it is
A wrapper over the NHL's public API. Every call is a live request to the league, so scores, standings and schedules are the current ones rather than a cached copy.
What you get
- Today's scores and the current standings
- A team's roster, schedule and club statistics, by team code
- The current skater and goalie statistical leaders
- A player's biographical information, career statistics and game log, plus the featured-player spotlight
- A game's boxscore and its full play-by-play
- The league schedule and the TV schedule for what is on tonight
- The team-code list, and a helper for the season-format arguments the API expects
Requirements
Python with fastmcp and requests installed, run as a local stdio process from your client config. No account and no key — it reads the NHL's public endpoints, so it needs network access.
Setup effort
Build from source
USE CASES
01
Catching up on last night
Read the day's scores, then open the boxscore for the game that actually mattered.
02
Settling an argument about the standings
Pull the current table and the club's own statistics, so the claim is checked against the league rather than against memory.
03
Following one player's season
Read the player's information and career totals, then walk the game log to see how the season has actually gone.
04
Seeing who is leading the league
Take the current skater and goalie leaders, with the statistical category and the number of names as arguments.
05
Working out what to watch tonight
Read the league schedule, the broadcast schedule, and one team's own fixtures together.
06
Digging into how a game actually went
Go through the play-by-play event by event and set it against the boxscore totals.
16 tools
Listed in project docs. Your client may show a different list.
get_player_game_logget_player_spotlightget_standings_nowget_club_stats_nowget_team_rosterget_team_scheduleget_daily_scores_nowget_play_by_playget_game_boxscoreget_current_skater_stats_leadersget_current_goalie_stats_leadersget_schedule_nowget_tv_schedule_nowget_team_codesget_season_format_helpBEFORE YOU INSTALL
What to know first
Tools you get
16 tools named in the project's documentation.
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone and build this one yourself.
Server setup
TERMINAL
git clone https://github.com/sanchorelaxo/mcp-server-sandbox
cd mcp-server-sandbox
pip install -r requirements.txt
python nhl_mcp_server.pyMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"nhl-api": {
"command": "python",
"args": [
"<YOUR_PATH_TO_NHL_MCP_SERVER>"
]
}
}
}
