> 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/mcp-server-beta.md).

# MCP Server (Beta)

> **This server is currently in beta.** Functionality may change and some edge cases may not be fully handled. We welcome your feedback - see the Feedback section below.

The Sportmonks Football MCP server connects AI tools like Claude and Cursor directly to the Sportmonks Football API v3.

> **Companion tool, not a production API client.** The MCP server is designed for exploration and experimentation - letting you query football data conversationally without writing integration code. It covers a focused subset of the full API and is not intended as a replacement for direct API integration in production applications.

The server exposes **11 focused tools** covering the most common football data needs.

### What is MCP?

MCP (Model Context Protocol) is an open standard that lets AI assistants call external APIs as tools. When you install an MCP server, the AI can discover its available tools and call them on your behalf during a conversation - fetching real data, not hallucinating it.

### What you can do

* Ask "who are the top scorers in the Premier League this season?" and get live data back
* Say "give me a match preview for the Arsenal vs Chelsea fixture" and get a full briefing with head-to-head history
* Ask "show me the current La Liga standings" without looking up a single ID
* Explore API responses interactively before building an integration

### Tools at a glance

| Tool                   | What it does                                              |
| ---------------------- | --------------------------------------------------------- |
| `search`               | Find players, teams, or leagues by name                   |
| `get_player`           | Full player profile by ID                                 |
| `get_team`             | Team profile by ID                                        |
| `get_league`           | League details by ID                                      |
| `get_squad`            | Current or historical squad for a team                    |
| `get_matches`          | Upcoming, live, or historic fixtures for a team or league |
| `get_match_preview`    | Fixture info plus last 5 head-to-head results             |
| `get_fixture_details`  | Detailed match data - lineups, events, statistics         |
| `get_standings`        | Live league table                                         |
| `get_historic_seasons` | All seasons for a league, newest first                    |
| `get_topscorers`       | Goals, assists, or cards leaderboard for a season         |

<figure><img src="/files/aQ7FH8M8Sfnnoh75ZS1k" alt=""><figcaption></figcaption></figure>

### Next steps

* Quick Start - get up and running in minutes
* Setup - install the MCP server for Claude Code, Claude Desktop, or Cursor
* Example Prompts - see what you can ask

### Feedback

The MCP server is in active development. If you run into issues, unexpected results, or have suggestions for new tools or improvements, send feedback to **<support@sportmonks.com>**.

Please include:

* The tool you called and the arguments you passed
* What you expected vs. what you got
* Your AI client (Claude Desktop, Claude Code, Cursor, etc.)


---

# 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/mcp-server-beta.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.