NBA MCP Server
Access NBA statistics via the Model Context Protocol (MCP).
This package runs an MCP server with 21 consolidated tools — live scores, box scores, standings, player/team stats, play-by-play, shot charts, and more. All tools accept human names (not just IDs), return structured data + compact text, and default season to current.
Supports stdio, streamable HTTP, and SSE transports. No API key required.
Quick Start
With uvx (Recommended - No Install Required)
Add to your MCP client config (e.g., Claude Desktop):
MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"nba-stats": {
"command": "uvx",
"args": ["nba-stats-mcp"]
}
}
}
Restart your client and start asking!
With pip
pip install nba-stats-mcp
Then configure your MCP client:
{
"mcpServers": {
"nba-stats": {
"command": "nba-stats-mcp"
}
}
}
Response Format (v3.0)
All tools return JSON (encoded in the MCP TextContent.text field). Each response includes:
text— compact 1-3 line summary (clean, no IDs or URLs)data— structured dict with all values (primary output for programmatic use)entities— extracted IDs + asset URLs for UI rendering
Example:
{
"tool_name": "get_player_stats",
"arguments": {"player": "LeBron James", "stat_type": "season"},
"text": "LeBron James 2025-26: 25.3 PPG, 7.1 RPG, 7.8 APG (51.2% FG)",
"data": {
"player_id": 2544, "name": "LeBron James", "season": "2025-26",
"pts": 25.3, "reb": 7.1, "ast": 7.8, "fg_pct": 0.512
},
"entities": {
"players": [{"player_id": "2544", "headshot_url": "https://cdn.nba.com/headshots/nba/latest/1040x760/2544.png"}]
}
}
What You Can Ask
- "Show me today's NBA games"
- "What are LeBron James' stats this season?"
- "Compare LeBron and Curry"
- "Give me a team overview for the Lakers"
- "Who are the top 10 scorers this season?"
- "Show me all-time assists leaders"
- "When do the Celtics play next?"
Features
21 consolidated tools (optimized for LLM clients):
- All tools accept names —
get_player_stats(player="LeBron James")works - Structured
datafield for programmatic access - 3 new composite tools:
compare_players,daily_summary,team_overview - Live game scores and play-by-play
- Player stats (season, career, game log, hustle, defense, advanced)
- Team rosters and advanced metrics
- League standings and leaders (current season, all-time, hustle)
- Shot charts and shooting analytics
Full Documentation & Tool Reference
Requirements
- Python 3.10+
- An MCP-compatible client
License
MIT License - See LICENSE for details.
Metadata
Release files for nba-stats-mcp 0.3.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| nba_stats_mcp-0.3.0.tar.gz | 139.0 kB | Without provenance | Details for nba_stats_mcp-0.3.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| nba_stats_mcp-0.3.0-py3-none-any.whl | Python 3 | none | any | Details for nba_stats_mcp-0.3.0-py3-none-any.whl |
Total release size: 162.6 kB
Release files / nba_stats_mcp-0.3.0.tar.gz
| Download URL | nba_stats_mcp-0.3.0.tar.gz |
|---|---|
| Size | 139.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
9024db40bc48c45ff99faaffa6b7fca54c490d0b7f41bd274df546fda74d50d7
|
|
BLAKE2b-256 checksum How to use checksums |
864cd8d3c81847da654adbf72d2e14e3fb1e3f4465e571efd819e7f17b5cf6b3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.3
|
Release files / nba_stats_mcp-0.3.0-py3-none-any.whl
| Download URL | nba_stats_mcp-0.3.0-py3-none-any.whl |
|---|---|
| Size | 23.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
20e841be8e12df890c8efc0777d25a2e5ef465b59af5b072ffe43c3db4b0aaa7
|
|
BLAKE2b-256 checksum How to use checksums |
2b951d3654608b7543a9183566676a8b61958187a7ebed717cf7d9c401c41278
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.3
|
Security for nba-stats-mcp 0.3.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.