Overview
What is MCP Riot Server?
MCP Riot Server is a community-developed Model Context Protocol server that integrates with the Riot Games API to provide League of Legends data to AI assistants via natural language queries. It enables AI models to retrieve player information, ranked stats, champion mastery, and recent match summaries.
How to use MCP Riot Server?
Clone the repository, install dependencies with uv sync, obtain a Riot API key from developer.riotgames.com, and create a .env file with RIOT_API_KEY. Configure your MCP client (e.g., Claude for Desktop) to point to the server script with the absolute path and the .env file.
Key features of MCP Riot Server
- Player summary: level, rank, top champions, recent matches
- Top champions by mastery points
- Champion mastery data for a specific champion
- Recent matches with champion, K/D/A, result
- Match summary with KDA, damage, wards, result
Use cases of MCP Riot Server
- Ask "What's the current rank and top champions of Hide on bush?" for a full player overview.
- Query "What champions is he best at?" to see top mastery champions.
- Inquire "How good is this player with Ahri?" for champion-specific mastery.
- Request "Show the last 3 matches for this summoner" to get recent match details.
- Summarize a specific match using its match ID.
FAQ from MCP Riot Server
How do I get a Riot API key?
You can get your API key from https://developer.riotgames.com/ and set it in the .env file as RIOT_API_KEY.
What tools does MCP Riot Server expose?
The server provides five tools: get_player_summary, get_top_champions_tool, get_champion_mastery_tool, get_recent_matches_tool, and get_match_summary.
Is MCP Riot Server affiliated with Riot Games?
No, 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.
What are the runtime requirements?
It requires Python with uv (or pip), a MCP-compatible client, and a valid Riot API key stored in a .env file.
How do I configure MCP Riot Server with Claude for Desktop?
Edit claude_desktop_config.json to use the uv binary with the --directory pointing to the project folder, --env-file pointing to .env, and run server.py. See the README for an example absolute path.
