MCP Server Quickstart

Get live alternative sports data in your AI agent in under 2 minutes.

Prerequisites

Python 3.10+ and uv (recommended) or pip
An AltSportsData API Key — get one here
An MCP-compatible client: Claude Desktop, Claude Code, Cursor, or any MCP client

Install the MCP Server

uv pip install altsportsdata-mcp

pip install altsportsdata-mcp

git clone https://github.com/asd-git-master/altsportsdata-mcp.git
cd altsportsdata-mcp
uv pip install -e .

Add to Your AI Tool

Pick your tool and drop in the config:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "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. Look for the 🔧 icon — you should see 29 tools.

Option A: Project-level — add .mcp.json to 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 — register via CLI:

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: claude mcp list

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"
      }
    }
  }
}

Or go to Settings → MCP → Add new MCP server and paste the command.

Try It

Ask your AI agent something like:

"What WSL surfing events are coming up? Show me the odds for the next one."

"List all F1 events this month and give me the moneyline favorites."

"Calculate a same-game parlay for the upcoming BKFC event."

The agent will use the MCP tools automatically — you'll see tool calls for get_events, get_moneylines, get_favorites, etc.

Verify It's Working

You can test the server directly:

# Check it starts cleanly
ALTSPORTSDATA_API_KEY=your_key python -m altsportsdata_mcp.server 2>&1 | head -1

You should see the FastMCP startup message. Press Ctrl+C to stop.

Transports

Transport	Use Case	Command
stdio (default)	Claude Desktop, Claude Code, Cursor, OpenClaw	`python -m altsportsdata_mcp.server`
HTTP/SSE	Shared/remote access, Windsurf, web apps	`python -m altsportsdata_mcp.server --sse --port 8080`

For HTTP/SSE, connect using:

{
  "mcpServers": {
    "altsportsdata": {
      "url": "http://localhost:8080/mcp"
    }
  }
}

What's Next?

Tools Reference → — Detailed docs for all 29 tools with parameters and examples
API Reference → — Raw API endpoint documentation
SDKs → — TypeScript and Python SDK documentation

Quickstart

On this page