mcp -sandbox

This MCP server provides live access to the NHL API through the MCP protocol. Built with FastMCP, it exposes 40+ NHL API endpoints as MCP tools, enabling AI assistants and clients to query current standings, player data, team rosters, game events, schedules, and more using MCP calls. Tools are organized by category (Player, Team, Game, Statistics, Schedule, and Utility), delivering structured data for downstream agents and automated workflows. To use it, connect your MCP client to this server configuration and call the exposed tools via the MCP protocol, such as requesting current standings, player statistics leaders, or game play-by-play data. The server returns data in a consistent MCP-compatible format suitable for integration with AI assistants and automated decision-making processes.

Prerequisites:

• Python 3.8+ installed on your system
• Access to the repository containing nhl_mcp_server.py and dependencies

Step-by-step installation:

1. Clone or download the repository: git clone https://github.com/your-organization/nhl-mcp-server.git cd nhl-mcp-server

2. Create and activate a virtual environment (optional but recommended): python -m venv venv source venv/bin/activate # on macOS/Linux venv\Scripts\activate # on Windows

3. Install dependencies: pip install -r requirements.txt

4. Run the server (example path to the script): python nhl_mcp_server.py

5. Configure MCP client to connect to the server using the provided mcp_config example and point the client to the Python-based server entrypoint.

Tips and common considerations:

• Ensure the NHL API client (inside nhl_mcp_server.py) is able to reach the internet from your environment, as it fetches live data.
• If you modify the server or endpoints, update the mcp client configuration accordingly so MCP tools are correctly registered.
• Review error handling and rate limiting in the server to handle API failures gracefully.
• When testing locally, you can use the included test_client.py, test_mcp_server.py, and demo.py to validate functionality before deployment.
• If running behind a firewall or proxy, configure HTTP(S)_PROXY environment variables so the Python HTTP requests can reach the NHL API.
• Logs can be useful for debugging: enable verbose logging in the server start-up to capture MCP interactions and API responses.