League of Legends MCP Server
MCP server exposing 30 tools for League of Legends player analysis, match review, and training-plan generation.
README
League of Legends MCP Server
MCP server exposing 30 tools for League of Legends player analysis, match review, and training-plan generation.
Installation
Via npm (recommended)
npm install -g lol-mcp-server
Via npx (no install)
npx lol-mcp-server
From source
git clone https://github.com/rexlManu/lol-mcp-server.git
cd lol-mcp-server
pnpm install
pnpm build
Setup
cp .env.example .env
# Edit .env and add your RIOT_API_KEY
Get your Riot API key at https://developer.riotgames.com/
MCP Client Configuration
Add to your MCP client config (Cursor, Claude Desktop, etc.):
{
"mcpServers": {
"league-of-legends": {
"command": "lol-mcp-server",
"env": {
"RIOT_API_KEY": "your-api-key-here"
}
}
}
}
Or if installed from source:
{
"mcpServers": {
"league-of-legends": {
"command": "node",
"args": ["/path/to/lol-mcp-server/dist/index.js"],
"env": {
"RIOT_API_KEY": "your-api-key-here"
}
}
}
}
Stack
- Runtime: Node.js 20+, TypeScript
- Package manager: pnpm
- MCP SDK:
@modelcontextprotocol/sdk - Validation: zod
- Scraping: cheerio (Lolalytics, League Wiki)
- Static data: Data Dragon API
- Testing: vitest
pnpm dev # Run with tsx (hot reload)
pnpm build # Compile to dist/
pnpm start # Run compiled server
pnpm test # Run tests
pnpm typecheck # Type checking
MCP Client Configuration
Cursor / VS Code
{
"mcpServers": {
"league-of-legends": {
"command": "node",
"args": ["dist/index.js"],
"env": {
"RIOT_API_KEY": "your-api-key-here"
}
}
}
}
opencode
{
"mcpServers": {
"league-of-legends": {
"command": "node",
"args": ["dist/index.js"],
"env": {
"RIOT_API_KEY": "your-api-key-here"
}
}
}
}
Tools (30 total)
Account & Profile (4)
| Tool | Description |
|---|---|
lol_get_account |
Get Riot account info by Riot ID |
lol_get_summoner |
Get summoner info (level, icon) by PUUID |
lol_get_ranked |
Get ranked stats (tier, rank, LP, win rate) |
lol_get_player_profile |
Complete player profile in one call |
Match History (3)
| Tool | Description |
|---|---|
lol_get_match_history |
Get recent match IDs (with filters) |
lol_get_match_details |
Get detailed match data (batch supported) |
lol_get_match_timeline |
Get minute-by-minute match timeline |
Champion & Live (4)
| Tool | Description |
|---|---|
lol_get_champion_mastery |
Get champion mastery data |
lol_get_live_game |
Check if player is in game |
lol_get_champion_rotation |
Get free champion rotation |
lol_get_featured_games |
Get featured games |
League & Clash (7)
| Tool | Description |
|---|---|
lol_get_league_by_id |
Get league info by ID |
lol_get_league_entries |
Get league entries by summoner |
lol_get_league_entries_exp |
Get league entries (paginated, by queue/tier/division) |
lol_get_league_top |
Get top players (challenger/grandmaster/master) |
lol_get_clash_tournaments |
Get active Clash tournaments |
lol_get_clash_player |
Get Clash player info |
lol_get_clash_team |
Get Clash team info |
Challenges & Status (3)
| Tool | Description |
|---|---|
lol_get_challenges |
Get all challenge configurations |
lol_get_player_challenges |
Get player challenge progress |
lol_get_server_status |
Get server status (maintenance/incidents) |
Static Game Data (4)
| Tool | Description |
|---|---|
lol_get_all_champions |
List all champions (from Data Dragon) |
lol_get_champ_info |
Detailed champion info (Data Dragon + Wiki) |
lol_get_all_items |
List all items with stats, cost, build path |
lol_get_runes |
Get rune trees with keystones and descriptions |
Lolalytics (1)
| Tool | Description |
|---|---|
lol_get_builds_for_champion |
Scrape Lolalytics for builds, runes, counters, meta |
AI Analysis (4)
| Tool | Description |
|---|---|
lol_analyze_performance |
Analyze recent performance with recommendations |
lol_analyze_champion |
Analyze performance on a specific champion |
lol_get_improvement_tips |
Get personalized improvement tips |
lol_compare_players |
Compare stats between two players |
Region Support
User-facing regions: euw, eune, na, kr, br, lan, las, oce, ru, tr, jp, ph2, sg2, th2, tw2, vn2
Platform routing: euw1, eun1, na1, kr, jp1, br1, la1, la2, oc1, tr1, ru
Regional routing: europe, americas, asia, sea
Caching
| Data Type | TTL |
|---|---|
| Live game / server status | 15-30s |
| Account / summoner / ranked | 60s |
| Champion mastery / match history | 2min |
| Lolalytics pages | 5min |
| Match details / timelines | 1h |
| Static data (champions/items/runes) | 24h |
Error Handling
| Error | Description |
|---|---|
not found (404) |
Player/match not found |
rate limited (429) |
Auto-retry with backoff |
forbidden (403) |
Private data or restricted access |
invalid key (401) |
Invalid Riot API key |
scrape_layout_changed |
Lolalytics page structure changed |
network failure |
Connection/API error |
invalid region |
Unknown region code |
Project Structure
src/
index.ts # Entry point, MCP server setup
config.ts # Environment config
riot/
client.ts # Riot API HTTP client with rate limiting
regions.ts # Region routing maps
types.ts # Core Riot API types
types-extra.ts # Additional Riot API types
cache/
cache.ts # TTL-based in-memory cache
static-data/
dataDragon.ts # Data Dragon API client
wikiScraper.ts # League Wiki scraper (cheerio)
types.ts # Static data types
lolalytics/
scraper.ts # Lolalytics page fetcher
parser.ts # HTML parser (cheerio)
types.ts # Lolalytics types
tools/
account.ts # Account, summoner, ranked, profile, match tools
champion.ts # Mastery, live game, rotation, featured games
league.ts # League, clash, challenges, status
staticData.ts # Champions, items, runes
lolalytics.ts # Lolalytics builds
analysis.ts # Performance analysis, tips, comparison
analysis/
performance.ts # Performance analysis engine
championReview.ts # Champion-specific analysis
trainingPlan.ts # Improvement tips generator
compare.ts # Player comparison
tests/
regions.test.ts # Region mapping tests
cache.test.ts # Cache tests
lolalytics-parser.test.ts # Parser tests
analysis.test.ts # Analysis engine tests
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。