> For the complete documentation index, see [llms.txt](https://docs.sportmonks.com/v3/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.sportmonks.com/v3/sportmonks-ai-docs/ai-developer-hub.md).

# AI Developer Hub

Get live football data into any AI workflow - from a conversational assistant in Claude to accurate code generation in Cursor and Copilot. Choose the integration that fits how you work.

### Claude and Cursor - MCP Server *(BETA)*

The deepest integration. Install the MCP server and your AI assistant calls the Sportmonks API live during the conversation - no copy-pasting, no manual lookups, no stale data.

> The MCP server covers a focused set of football data endpoints. It is designed for exploration and prototyping, not production API usage.

* MCP Server overview
* Quick start
* Setup for Claude Code
* Setup for Claude Desktop
* Setup for Cursor

### ChatGPT

Use the Sportmonks OpenAPI spec to create a Custom GPT with Actions. Anyone can query live football data from ChatGPT without writing a line of code.

* ChatGPT Custom GPT setup

### GitHub Copilot

Add a workspace instructions file and Copilot writes accurate Sportmonks integration code - correct endpoints, proper auth patterns, right response shapes - from the first suggestion.

* GitHub Copilot setup

### Windsurf

Cascade supports MCP natively. Install the server and Windsurf has the same live tool access as Claude.

* Windsurf setup

### Any other LLM

Paste a context block into ChatGPT, Gemini, Mistral, or anything else - and it will understand the Sportmonks API well enough to help you build, without any installation.

* Machine-readable docs

### Not sure where to start?

| I want to...                                       | Start here                     |
| -------------------------------------------------- | ------------------------------ |
| Query live data by asking questions                | MCP Server                     |
| Build Sportmonks integrations faster in my editor  | Cursor Rules or GitHub Copilot |
| Give non-technical users a football data assistant | ChatGPT Custom GPT             |
| Explore what's possible in a weekend               | Example Builds                 |


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.sportmonks.com/v3/sportmonks-ai-docs/ai-developer-hub.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.