MCP Server

The Sportradar Model Context Protocol (MCP) server enables AI-powered code editors like Cursor, Windsurf, and VS Code, plus general-purpose tools like Claude Desktop, to interact directly with the Sportradar media APIs and their documentation.

Before You Begin

The Sportradar MCP server requires a valid Sportradar API key. If you don't already have one, you can create a free trial through the Sportradar Marketplace:

1. Visit the Sportradar Marketplace and register for an account.
2. Browse by sport, league, or product type and select a product to start a free 30-day trial.
3. Once your trial is approved, copy your API key from your Marketplace account — you'll use it in the MCP client configuration below.

What is MCP?

Model Context Protocol (MCP) is an open standard that allows AI applications to securely access external data sources and tools. The Sportradar MCP server provides AI agents with:

• Direct API access to Sportradar data API functionality
• Documentation search capabilities
• Documentation and schema access for your Sportradar APIs
• Code generation assistance for sports data integrations

MCP Server Setup

All Sportradar MCP tools are hosted at the same endpoint: https://developer.sportradar.com/mcp.

Configure your AI development tools to connect to this server. Your MCP client configuration may include multiple named profiles, each representing a different tool namespace.

For example, you can define profiles such as:

• sportradar-soccer
• sportradar-football
• sportradar-baseball
• sportradar-odds

Each profile points to the same URL, but allows you to organize and load only the tools relevant to the sport or product area you want to work with.

You can pass in your x-api-key authorization headers via query parameters, or however headers are configured in your MCP client.

{
  "mcpServers": {
    "sportradar-soccer": {
      "type": "http",
      "url": "https://developer.sportradar.com/mcp",
      "headers": {
        "x-api-key": "YOUR_API_KEY_HERE"
      }
    }
  }
}

Available Server Profiles and Tools

We offer several MCP server profiles, all pointing to the same endpoint (developer.sportradar.com/mcp).

This should help your AI dev tools to focus on the intended data subset. Keep this in mind when setting up your queries. For example, use the sportradar-basketball server to search for NBA data. Below are the available profiles, and their included APIs.

MCP Server Profiles

MCP Tools

The following tools are available for each of the above profiles:

• get-code-snippet
• get-endpoint
• get-request-body
• get-response-schema
• get-server-variables
• list-endpoints
• list-security-schemas
• list-specs
• search-specs

Testing Your MCP Setup

Once configured, you can test your MCP server connection:

1. Open your AI editor (Cursor, Windsurf, VS Code, etc.)
2. Connect to the appropriate server
3. Start a new chat with the AI assistant
4. Ask about our sports data! - try our query suggestions to get started

The AI should now have access to your Sportradar account data and documentation through the MCP server.

Tips & FAQs

Query Suggestions

These are just a handful of sample questions to get the ball rolling on querying our data.

• Use the sportradar-[server-profile] MCP server and tell me how to get live scoring data for [sport / API]?
• How do I get the most up-to-date standings information for [sport / API]?
• What leagues do you cover for [API]?
• What player profile information do you offer for [sport / API]?
• Generate a code snippet in Python using the MCP helper for the NFL Game Play-by-Play endpoint
• Build a [coding language] script to return the most up-to-date NFL standings data using the sportradar-football MCP server.
• Tell me what game statistics are offered for live [sport / API] games using the sportradar-[server-profile] MCP server.
• How can I set up a playoff bracket for the [sport / API] playoffs using the [MCP Server Name]?
• Use the Images API to tell me the best way to get the most up-to-date headshot of an MLB player.

❗️

Disclaimer

Please keep in mind that AI-generated responses are not curated or validated by Sportradar in any way.

We suggest using our MCP server as a building block in your integration. Always verify responses prior to using in your production environment.