MCP-Riot是一个由社区开发的模型上下文协议（MCP）服务器，集成了拳头游戏API，通过自然语言查询向AI助手提供《英雄联盟》数据。

该项目使AI模型能够检索玩家信息、排名统计、冠军精通度以及近期比赛摘要。

免责声明： 这是一个开源项目 与拳头游戏无关或未获其认可。 英雄联盟®是拳头游戏公司注册商标。

---

演示

✨ 特色

🧾 球员简介

“目前丛林中隐藏的排名和顶级冠军是什么？”

为玩家提供：

• 水平
• 排名单人段
• 顶级冠军大师
• 近期比赛历史

🔝 顶级冠军

“他最擅长哪些冠军？”

根据掌握点数返回前N名冠军。

🎯 冠军大师

“这个玩家和阿璃配合得有多好？”

返回特定英雄的详细精通数据。

🕹️ 近期比赛

“显示该召唤师最近的3场比赛”

列出近期比赛，包括使用冠军、击倒/死亡/A和结果。

📊 比赛摘要

“为给定匹配ID总结此匹配”

MCP Riot Server

MCP-Riot is a community-developed Model Context Protocol (MCP) server that integrates with the Riot Games API to provide League of Legends data to AI assistants via natural language queries.

This project enables AI models to retrieve player information, ranked stats, champion mastery, and recent match summaries.

Disclaimer: This is an open-source project not affiliated with or endorsed by Riot Games. League of Legends® is a registered trademark of Riot Games, Inc.

---

Demo

✨ Features

🧾 Player Summary

“What’s the current rank and top champions of Hide on bush?”

Provides the player’s:

• Level
• Ranked Solo Tier
• Top champion masteries
• Recent match history

🔝 Top Champions

“What champions is he best at?”

Returns the top N champions based on mastery points.

🎯 Champion Mastery

“How good is this player with Ahri?”

Returns detailed champion mastery data for a specific champion.

🕹️ Recent Matches

“Show the last 3 matches for this summoner”

Lists recent matches including champion used, K/D/A, and result.

📊 Match Summary

“Summarize this match for a given match ID”

Returns the player’s match stats, such as KDA, damage, wards, and result.

---

🚀 Quick Start

1. Clone & Install

git clone https://github.com/jifrozen0110/mcp-riot.git
cd mcp-riot

# Install dependencies (using uv or pip)
uv sync

2. Get Your API Key and Set Environment

Create .env file with your Riot API key:

RIOT_API_KEY=your_riot_api_key

You can get your key from https://developer.riotgames.com/

3. Configure MCP Client

Register this server in your MCP client (e.g., Claude for Desktop).

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
    "mcpServers": {
        "amadeus": {
            "command": "/ABSOLUTE/PATH/TO/PARENT/FOLDER/uv",
            "args": [
                "--directory",
                "/ABSOLUTE/PATH/TO/PARENT/FOLDER",
                "run",
                "--env-file",
                "/ABSOLUTE/PATH/TO/PARENT/FOLDER/.env",
                "riot.py"
            ]
        }
    }
}

Replace /ABSOLUTE/PATH/TO/PARENT/FOLDER/ with the actual path to your project folder.

my case:

{
    "mcpServers": {
        "amadeus": {
            "command": "/Users/jifrozen/.local/bin/uv",
            "args": [
                "--directory",
                "/Users/jifrozen/mcp-riot/src/",
                "run",
                "--env-file",
                "/Users/jifrozen/mcp-riot/.env",
                "server.py"