DunkAPI vs Nba MCP Server
A side-by-side look at the DunkAPI and Nba MCP Server MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
D
DunkAPISportsNBA, WNBA and college basketball data: play-by-play, shot locations, box scores, odds. REST and MCP.48FairAuth: api key requiredVerdict: choose DunkAPI for sports work; choose Nba MCP Server for sports as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
DChoose DunkAPI when
- You need dedicated capabilities in the Sports domain.
- Its auth model fits you: API key required.
- You have the keys it needs:
DUNKAPI_API_KEY. - You want tools like
list_teams, search_players, list_games.
Choose Nba MCP Server when
- You need dedicated capabilities in the Sports domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You want tools like
resolve_team_id, resolve_player_id, get_scoreboard.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | D DunkAPI | |
|---|---|---|
| Category | Sports | Sports |
| Quality signal | 48/100 · Fair | 57/100 · Good |
| Install command | Not confirmed yet | Confirmed |
| Transport | — | Local subprocess (stdio) |
| Auth | API key required | No auth required |
| Pricing | Freemium | Free |
| Required env vars | DUNKAPI_API_KEY | None listed |
Tools & capabilities
DunkAPI tools 18
list_teamsTeam ids, abbreviations and colours for a seasonsearch_playersFind players by namelist_gamesGames with scores by season, date, range or teamget_scheduleUpcoming games with the median line across sportsbooksget_standingsStandings from every final game: overall, conference, home, away, last 10get_injuriesThe latest injury report: status, injury and expected return (NBA, WNBA)get_ratingsOur team Elo ratings, rankedget_gameOne game: both box scores, every player's line, each book's line, win probabilityget_playerProfile, per-season averages and shooting splits, last 10 gamesget_player_gamesA player's full game logget_leadersSeason leaders per game, by percentage or in totalget_team_statsPace, offensive, defensive and net rating, and the four factors- +6 more on the listing page
Nba MCP Server tools 21
resolve_team_idResolve team name/city/nickname to team_id. Returns top matches.resolve_player_idResolve player name to player_id. Returns top matches with active/inactive status.get_scoreboardGames for a date (YYYY-MM-DD or YYYYMMDD). Defaults to today.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
DunkAPI
No confirmed install command for DunkAPI yet — follow the setup steps linked from its listing page rather than a guessed package name.
Nba MCP Server
{
"mcpServers": {
"labeveryday-nba-mcp-server": {
"command": "uvx",
"args": [
"nba-stats-mcp"
]
}
}
}
Frequently asked questions
DunkAPI is categorized under Sports and uses an install path we have not confirmed yet. Nba MCP Server belongs to Sports and uses a local stdio subprocess. Pick DunkAPI for sports work and Nba MCP Server for sports.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client. DunkAPI has no confirmed install command yet — follow its own setup instructions.
DunkAPI is listed as freemium — a free tier with paid plans. Auth: api key required. Nba MCP Server is listed as free. Auth: no auth required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add dunkapi and labeveryday-nba-mcp-server as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, DunkAPI has a quality signal of 48/100 (Fair) with 0 views, 0 installs and 0 GitHub stars. Nba MCP Server has 57/100 (Good) with 4 views, 0 installs and 10 GitHub stars.
