nba-stats-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NBA_MCP_RETRIES | No | Retries for transient failures (429 / 5xx / network). Default is 2. | 2 |
| NBA_MCP_LOG_LEVEL | No | Controls logging verbosity. Default is WARNING. | WARNING |
| NBA_MCP_TLS_VERIFY | No | TLS verification enabled. Set to 0 to disable. Default is 1. | 1 |
| NBA_MCP_MAX_CONCURRENCY | No | Max concurrent outbound NBA API requests. Default is 8. | 8 |
| NBA_MCP_CACHE_TTL_SECONDS | No | Cache TTL for stats endpoints in seconds. Default is 120. | 120 |
| NBA_MCP_HTTP_TIMEOUT_SECONDS | No | Per-request timeout in seconds. Default is 30. | 30 |
| NBA_MCP_LIVE_CACHE_TTL_SECONDS | No | Cache TTL for live endpoints in seconds. Default is 5. | 5 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| resolve_team_idA | Resolve team name/city/nickname to team_id. Returns top matches. |
| resolve_player_idA | Resolve player name to player_id. Returns top matches with active/inactive status. |
| get_scoreboardB | Games for a date (YYYY-MM-DD or YYYYMMDD). Defaults to today. |
| find_gameB | Find game_id by team matchup and optional date. Accepts team names. |
| get_game_detailsC | Detailed game info. Accepts game_id. |
| get_box_scoreB | Full box score with player stats. Accepts game_id. |
| get_player_infoB | Player bio/profile. Accepts player name or ID. |
| get_player_statsC | Player stats. stat_type: season (default), career, game_log, hustle, defense, advanced. Accepts player name or ID. |
| get_player_awardsB | Player awards/accolades. Accepts player name or ID. |
| get_shooting_dataC | Shooting data. data_type: splits (default) or chart. Accepts player name or ID. |
| get_team_rosterB | Team roster. Accepts team name or ID. |
| get_standingsC | League standings by conference. |
| get_leadersC | League leaders. scope: current_season (default), all_time, hustle. category: points, assists, rebounds, etc. |
| get_scheduleC | Team upcoming schedule. Accepts team name or ID. |
| get_season_awardsC | Major award winners for a season (MVP, etc.). |
| get_team_advanced_statsB | Team advanced metrics (ORtg, DRtg, pace, net rating). Accepts team name or ID. |
| get_play_by_playC | Play-by-play data for a game. |
| get_game_rotationC | Player rotation/substitution data for a game. |
| compare_playersC | Compare two players side by side. Accepts names or IDs. |
| daily_summaryB | All games + scores for a date. Defaults to today. |
| team_overviewA | Team overview: roster + record + upcoming schedule. Accepts team name or ID. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 21 tools
Most tools have clear distinct purposes, but daily_summary and get_scoreboard both provide games for a date, creating slight overlap. Additionally, get_leaders and get_season_awards both relate to awards/leaders though they differ in scope.
Naming conventions are mixed: many tools use a 'get_' prefix, but some like compare_players, daily_summary, and find_game omit it, and resolve_player_id/team_id use a 'resolve_' prefix. This inconsistency could confuse an agent.
With 21 tools covering players, teams, games, and leagues, the count is on the higher side but remains reasonable for a comprehensive NBA stats server. It's well-scoped without being excessive.
The tool set covers a wide range of NBA data including player info/stats, team rosters/schedules, game details, and league leaders. Minor gaps exist, such as missing team basic stats or historical data, but core workflows are well-supported.