NBA MCP Server
Provides tools for retrieving NBA data including live game scores, player statistics, team information, game logs, league standings, and career achievements through the nba_api.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@NBA MCP Server show me LeBron James' career stats"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
NBA MCP Server
A simple MCP (Model Context Protocol) server for getting NBA data through nba_api. This server allows LLMs to retrieve live game data, player stats, team stats, game logs, team standings, and more.
Demo
https://github.com/user-attachments/assets/ce448f94-0226-4303-95e2-19f125a83a02
Related MCP server: Sleeper API MCP
Tools
Player Tools
get_player_career_stats(player_id: str)
Gets comprehensive career statistics for a player.
get_player_awards(player_id: str)
Retrieve all awards and achievements for a player, including MVP awards, All-Star selections, championships, etc.
get_player_game_log(player_id: str, season: str, season_type: str)
Player game-by-game statistics and results.
Team Tools
get_team_details(team_id: str)
Get comprehensive team information includes championships, conference awards, division awards, history, and background.
get_team_year_by_year_stats(team_id: str)
Historical year-by-year team performance statistics.
get_team_game_log(team_id: str, season: str, season_type: str)
Team game-by-game statistics and results.
get_league_team_standings(season: str, season_type: str)
Standings for all teams in the league by season.
Live Game Tools
get_today_scoreboard()
Retrieves today's NBA games, including live scores, game statuses, and teaminformation.
get_live_game_boxscore(game_id: str)
Gets live game data, including scores, player stats, timeouts, and more.
get_live_game_play_by_play(game_id: str)
Gets live play-by-play data from a game.
Resources
nba://players
Returns a list of all NBA players (past and present).
nba://active_players
Returns a list of currently active NBA players.
nba://teams
Returns a list of all NBA teams.
Usage
To use this MCP server with Claude for Desktop, add either of the following to your Claude Desktop config file.
Via uv:
{
"mcpServers": {
"nba_mcp": {
"command": "uv",
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/PARENT/FOLDER/nba_mcp",
"run",
"server.py"
]
}
}
}Via Docker:
{
"mcpServers": {
"nba_mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"stevenyuser/nba-mcp"
]
}
}
}Available Tools
10 toolsget_league_team_standingsB
Get league team standings for a given season and season type.
Args: season: str The season in the format 'YYYY-YY'. season_type: str The type of season. Pattern: "Regular Season", "Pre Season"
Inputs: season (required), season_type (required). Returns: object
get_live_game_boxscoreA
Get the box score for a specific game by its ID. The box score includes live data for the game, such as scores, player stats, timeouts, and more.
Args: game_id: str The ID of the game.
Inputs: game_id (required). Returns: object
get_live_game_play_by_playB
Get the play-by-play data for a specific game by its ID. The play-by-play data includes detailed information about each play in the game.
Args: game_id: str The ID of the game.
Inputs: game_id (required). Returns: result
get_player_awardsB
Get awards for a player by their ID.
Args: player_id: str The id of the player.
Inputs: player_id (required). Returns: object
get_player_career_statsC
Get career stats for a player by their ID.
Args: player_id: str The id of the player.
Inputs: player_id (required). Returns: object
get_player_game_logC
Get game log for a player by their ID, season, and season type.
Args: player_id: str The id of the player. season: str The season in the format 'YYYY-YY'. season_type: str The type of season. Pattern: "Regular Season", "Pre Season", "Playoffs", "All Star"
Inputs: player_id (required), season (required), season_type (required). Returns: object
get_team_detailsB
Get details for a team by their ID. Details include championship awards, conference awards, division awards, background, history, and more.
Args: team_id: str The id of the team.
Inputs: team_id (required). Returns: object
get_team_game_logA
Get game log for a team by their ID, season, and season type.
Args: team_id: str The id of the team. season: str The season in the format 'YYYY-YY'. season_type: str The type of season. Pattern: "Regular Season", "Pre Season", "Playoffs", "All Star"
Inputs: team_id (required), season (required), season_type (required). Returns: object
get_team_year_by_year_statsC
Get year-by-year stats for a team by their ID.
Args: team_id: str The id of the team.
Inputs: team_id (required). Returns: object
get_today_scoreboardA
Get the current NBA scoreboard for today's games. The NBA scoreboard provides live data for games, including scores, game statuses, and team information.
Inputs: no named parameters. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Every tool has a clearly distinct purpose targeting specific resources (league standings, live games, players, teams, scoreboard) with no overlap. The descriptions clearly differentiate between standings, boxscores, play-by-play, awards, stats, logs, details, and scoreboard data, making misselection unlikely.
All tools follow a consistent verb_noun pattern with 'get_' prefix, followed by the resource type (e.g., league_team_standings, player_awards, team_details). The naming is uniform throughout, using snake_case consistently without any deviations or mixed conventions.
With 10 tools, the count is well-scoped for an NBA data server, covering core areas like standings, live games, players, teams, and scoreboard. Each tool earns its place by providing distinct data retrieval functions without being overly sparse or bloated.
The toolset provides comprehensive coverage for retrieving NBA data, including CRUD-like operations for players and teams (e.g., stats, logs, details) and live game information. A minor gap exists in the lack of tools for creating or updating data (e.g., posting comments or simulations), but this is reasonable for a read-only data server focused on retrieval.
Maintenance
Related MCP Connectors
A Model Context Protocol server for Wix AI tools
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
The official Model Context Protocol server for Ambee. It gives any MCP-compatible AI assistant — Claude, ChatGPT, Cursor, VS Code, Ollama, and more direct access to live air quality, pollen, and weather data. To get started, including information on signing up and obtaining your Ambee key, check out the Ambee documentation on https://docs.ambeedata.com
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
Related MCP Servers
- AlicenseBqualityDmaintenanceModel Context Protocol server that enables LLMs and AI assistants to retrieve real-time Dota 2 statistics, match data, player information, and game metrics through a standardized interface.179MIT
- FlicenseNot gradedqualityNot gradedmaintenanceThis Model Context Protocol server provides access to the Sleeper Fantasy Football API, enabling agents to fetch data about users, leagues, drafts, rosters, matchups, and player information without requiring an API key.7-
- AlicenseBqualityDmaintenanceProvides comprehensive NBA statistics via Model Context Protocol, enabling queries for player stats, game scores, team info, and advanced analytics through natural language.2111MIT
- AlicenseAqualityDmaintenanceMCP server for NBA live data and stats, providing read-only tools to query live scores, box scores, player info, standings, and more from NBA.com.1516 npm1MIT