Sandbox
@joreilly/FantasyPremierLeague

MCP server for Fantasy Premier League data

This repo is a Kotlin Compose Multiplatform sample with Android, iOS, desktop, notebook, and MCP server pieces. The connector part is the `mcp-server` module, which uses the Kotlin MCP SDK to expose player and fixture tools over stdio for an agent client.

601 stars62 forksJupyter NotebookUpdated 6d ago
Who it's for

Builders who want to connect an agent to Fantasy Premier League player and fixture data.

What it delivers

You can plug an agent into a Kotlin MCP server and ask for Fantasy Premier League data through tools instead of scraping it yourself.

What it does

MCP tool endpoint

The `mcp-server` module exposes an MCP tools endpoint for player and fixture info.

Shared KMP code

The MCP server uses the same shared Kotlin Multiplatform code as the app modules.

Claude Desktop integration example

The README shows a `mcpServers` config entry that runs the built server jar over stdio.

Kotlin Notebook sample

`FantasyPremierLeague.ipynb` shows notebook-based exploration alongside the app and server code.

Multiplatform app targets

The repo also includes Android, iOS, and desktop app modules built from shared code.

README

Fantasy Premier League

kotlin-version

Compose Multiplatform project running on following

  • Android
  • iOS
  • Desktop

Also includes

  • AI agent built with Koog (Gemini + tool calling, running in shared KMP code)
  • Kotlin Notebook
  • MCP Server

It also currently makes use of the following Jetpack libraries

  • ViewModel
  • Navigation 3
  • Room
  • DataStore

Related posts:

Running the app

  • Android: open the project in Android Studio and run the app configuration
  • iOS: open ios/FantasyPremierLeague/FantasyPremierLeague.xcodeproj in Xcode and run
  • Desktop: ./gradlew :compose-desktop:run
  • MCP Server: ./gradlew :mcp-server:shadowJar (see MCP Server section below)

Note: to use the AI agent you need a Gemini API key — set apiKeyGoogle in FantasyPremierLeagueAgent.

Screenshots

Android

Screenshot_20251101_204058

iOS

Simulator Screenshot - iPhone 17 Pro - 2025-11-01 at 20 37 58

Desktop

Screenshot 2025-11-01 at 20 38 24

Kotlin Notebook

Screenshot 2024-04-06 at 11 03 15 Screenshot 2024-04-06 at 11 03 36

MCP Server

The mcp-server module uses the Kotlin MCP SDK to expose an MCP tools endpoint (returning player/fixture info) that can for example be plugged in to Claude Desktop as shown below. That module uses same KMP shared code.

Screenshot 2025-07-16 at 21 17 33

To integrate the MCP server with Claude Desktop for example you need to firstly run gradle shadowJar task and then select "Edit Config" under Developer Settings and add something like the following (update with your path)

{
  "mcpServers": {
    "fantasy-premier-league": {
      "command": "java",
      "args": [
        "-jar",
        "/Users/john.oreilly/github/FantasyPremierLeague/mcp-server/build/libs/serverAll.jar",
        "--stdio"
      ]
    }
  }
}

Full set of Kotlin Multiplatform/Compose/SwiftUI samples

Files in the repo

Repository payload20 top-level entries
  • .devcontainer
  • .github
  • app
  • art
  • common
  • compose-desktop
  • gradle
  • ios
  • mcp-server
  • .gitignore
  • build.gradle.kts
  • debug.keystore
  • FantasyPremierLeague.ipynb
  • gradle.properties
  • gradlew
  • gradlew.bat
  • LICENSE
  • README.md
  • renovate.json
  • settings.gradle.kts

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More connectors

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface

86k

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

43k

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

14k
okf-memory/
okf-agent-memory

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

547
tirth8205/
code-review-graph

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

31k
2akouwu/
reverify

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

1.1k