AltSportsData MCP Server
MCP-compatible server that gives AI agents access to alternative sports data across 30+ leagues — odds, events, probabilities, settlement, and futures for prediction markets, DFS platforms, and sportsbooks.
Quick Start
# Install
cd apps/altsportsdata-mcp
uv pip install -e ../altsportsdata-sdk
uv pip install -e .
# Run (stdio)
ALTSPORTSDATA_API_KEY=your_key altsportsdata-mcp
# Run (HTTP/SSE)
ALTSPORTSDATA_API_KEY=your_key altsportsdata-mcp --sse --port 8080
Connect to Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"altsportsdata": {
"command": "uv",
"args": [
"run",
"--directory",
"/path/to/altsportsdata-mcp",
"python",
"-m",
"altsportsdata_mcp.server"
],
"env": {
"ALTSPORTSDATA_API_KEY": "your_api_key"
}
}
}
}
Restart Claude Desktop. The 29 tools will appear in the tool picker (🔧 icon).
Connect to Claude Code (CLI)
Claude Code discovers MCP servers from .mcp.json in your project root:
{
"mcpServers": {
"altsportsdata": {
"command": "uv",
"args": [
"run",
"--directory",
"/path/to/altsportsdata-mcp",
"python",
"-m",
"altsportsdata_mcp.server"
],
"env": {
"ALTSPORTSDATA_API_KEY": "your_api_key"
}
}
}
}
Or register globally:
claude mcp add altsportsdata \
--command "uv" \
--args "run" "--directory" "/path/to/altsportsdata-mcp" "python" "-m" "altsportsdata_mcp.server" \
--env ALTSPORTSDATA_API_KEY=your_api_key
Verify with:
claude mcp list
Connect to Cursor
Cursor supports MCP servers via its settings. Two options:
Option A: Project-level (.cursor/mcp.json)
Create .cursor/mcp.json in your project root:
{
"mcpServers": {
"altsportsdata": {
"command": "uv",
"args": [
"run",
"--directory",
"/path/to/altsportsdata-mcp",
"python",
"-m",
"altsportsdata_mcp.server"
],
"env": {
"ALTSPORTSDATA_API_KEY": "your_api_key"
}
}
}
}
Option B: Global (Cursor Settings)
- Open Cursor → Settings → MCP
- Click Add new MCP server
- Enter:
- Name:
altsportsdata - Command:
uv run --directory /path/to/altsportsdata-mcp python -m altsportsdata_mcp.server
- Name:
- Add environment variable
ALTSPORTSDATA_API_KEY
Option C: SSE/HTTP (Remote)
Run the server with HTTP transport:
ALTSPORTSDATA_API_KEY=your_key altsportsdata-mcp --sse --port 8080
Then in .cursor/mcp.json:
{
"mcpServers": {
"altsportsdata": {
"url": "http://localhost:8080/mcp"
}
}
}
This also works for any MCP client that supports HTTP/SSE transport (Windsurf, Continue, etc.).
Connect to OpenClaw
Add to your OpenClaw config (openclaw config edit):
mcp:
servers:
altsportsdata:
command: uv
args:
- run
- --directory
- /path/to/altsportsdata-mcp
- python
- -m
- altsportsdata_mcp.server
env:
ALTSPORTSDATA_API_KEY: your_api_key
Installation via npm/PyPI (coming soon)
# When published to PyPI
pip install altsportsdata-mcp
# When published to npm (npx wrapper)
npx altsportsdata-mcp
Environment Variables
| Variable | Required | Description |
|---|---|---|
ALTSPORTSDATA_API_KEY |
Yes | Your AltSportsData API key |
ALTSPORTSDATA_BASE_URL |
No | Override API base URL |
ODDS_FORMAT |
No | Default odds format: american (default), decimal, probability |
Tools (29)
Discovery
| Tool | Description |
|---|---|
list_leagues |
List all 27+ alternative sports leagues with archetypes and markets |
get_league_info |
Detailed league info — archetype, data shape, contract hints, market menu |
get_market_catalog |
Browse market types by league or archetype |
Events
| Tool | Description |
|---|---|
get_events |
List events with filters (league, status, date range, sort) |
get_event |
Single event details |
get_event_summary |
Comprehensive event summary with participants and market overview |
get_participants |
Competitors/athletes for an event |
Odds & Markets
| Tool | Description |
|---|---|
get_odds |
Get odds for any market type (17 types supported) |
get_all_markets |
All available markets for an event in one call |
get_moneylines |
Winner/moneyline odds |
get_matchups |
Head-to-head matchup odds |
get_totals |
Over/under totals |
get_player_props |
Player prop bets |
get_exactas |
Exacta combinations (2, 3, or 4 way) |
get_podiums |
Podium finish odds |
get_heat_winners |
Heat/round winner odds |
get_fastest_lap |
Fastest lap odds (racing) |
Analytics & Probabilities
| Tool | Description |
|---|---|
get_market_probabilities |
Implied win probabilities (vig-removed) |
get_fair_probabilities |
Fair probabilities for any market type |
get_favorites |
Top N favorites by odds |
calculate_sgp |
Same Game Parlay probability calculator |
convert_odds |
Convert between American, decimal, and probability formats |
Settlement & Results
| Tool | Description |
|---|---|
get_settlement |
Settlement/grading data for completed events |
get_settled_results |
Final results and standings |
Futures
| Tool | Description |
|---|---|
list_futures |
Available futures markets |
get_futures_odds |
Season futures odds (winner, top 2/3/5/10) |
Specialty
| Tool | Description |
|---|---|
get_jaialai_matches |
Jai Alai match and set details |
get_jaialai_odds |
Jai Alai odds |
get_heat_scores |
Scores/lap times for a specific heat or round |
MCP Resources
Static resources for context injection:
| URI | Description |
|---|---|
altsportsdata://leagues |
All leagues with metadata |
altsportsdata://leagues/{code} |
Single league details |
altsportsdata://catalog |
Full market catalog |
Supported Leagues
27+ alternative sports including:
| Category | Leagues |
|---|---|
| Surf/Skate | WSL (Surfing), SLS (Skateboarding) |
| Racing | F1, MotoGP, Supercross, Nitrocross, NHRA, Formula Drift, MotoAmerica, USAC, High Limit Racing, World Outlaws, Super Motocross |
| Combat | BKFC, Power Slap, BYB Extreme, LUX Fight League, Real American Freestyle |
| Team | MASL (Arena Soccer), NLL (Lacrosse), Athletes Unlimited, Goal Soccer |
| Precision | Disc Golf (DGPT), World Jai Alai |
| Multi | X Games, Major League Table Tennis |
API Reference
This MCP server wraps the AltSportsData Public API.
- Swagger/OpenAPI: https://api.altsportsdata.com/public/docs/swagger
- Documentation: https://api.altsportsdata.com/public/docs/
License
MIT
Metadata
Release files for altsportsdata-mcp 1.0.0
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 |
|---|---|---|---|---|
| altsportsdata_mcp-1.0.0.tar.gz | 8.1 kB | Without provenance | Details for altsportsdata_mcp-1.0.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| altsportsdata_mcp-1.0.0-py3-none-any.whl | Python 3 | none | any | Details for altsportsdata_mcp-1.0.0-py3-none-any.whl |
Total release size: 17.7 kB
Release files / altsportsdata_mcp-1.0.0.tar.gz
| Download URL | altsportsdata_mcp-1.0.0.tar.gz |
|---|---|
| Size | 8.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
f3f64727bf29e442ab4d793329f8a391739119deb2d19ed3d9523d8bf39a6d18
|
|
BLAKE2b-256 checksum How to use checksums |
9b728219d5b013f28a062470b5c30571feb0109eb998ab55eca00df855513979
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.9.6
|
Release files / altsportsdata_mcp-1.0.0-py3-none-any.whl
| Download URL | altsportsdata_mcp-1.0.0-py3-none-any.whl |
|---|---|
| Size | 9.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b435d175b1b8ba605345457ae1209477da10d8caba39b0403d486173c1cf472f
|
|
BLAKE2b-256 checksum How to use checksums |
a7ff62ce0cf64bfa6c141d0991c121f0ad61f9f0af89eaa7e2eeccdc9559319c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.9.6
|
Security for altsportsdata-mcp 1.0.0
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.