get_player_summaryLABSCO SUMMARY
Player questions answered from live match data.
Rank, mastery and the last few games come back in one exchange — the lookup people currently do on a third-party stats site, run against Riot's own API instead.
What it is
A community server over the Riot Games API, not affiliated with Riot. Name a summoner and it returns level, ranked solo tier, top champion masteries and recent match history; name a match and it returns that game's stats.
What you get
- get_player_summary returns level, ranked solo tier, top masteries and recent matches in a single answer
- get_top_champions_tool ranks a player's champions by mastery points
- get_champion_mastery_tool returns detailed mastery on one named champion
- get_recent_matches_tool lists recent games with champion, K/D/A and result
- get_match_summary breaks one match down by ID: KDA, damage, wards and result
Requirements
Python with uv, and your own Riot API key from developer.riotgames.com, kept in a .env file that the client points the server at when it launches.
Setup effort
Build from source — git clone https://github.com/jifrozen0110/mcp-riot.git
USE CASES
01
Sizing up a player before a game
One call covers rank, best champions and recent form together.
02
Finding out what someone actually plays
Mastery points rank their champions, and one champion can be examined on its own.
03
Reviewing how the last few games went
Champion, K/D/A and result per match, without opening a tracker site.
04
Breaking down one match
A match ID returns KDA, damage and wards — enough to argue about it with evidence.
5 tools
Listed in project docs. Your client may show a different list.
get_top_champions_toolget_champion_mastery_toolget_recent_matches_toolget_match_summaryBEFORE YOU INSTALL
What to know first
Tools you get
5 tools named in the project's documentation.
Requires
- uv
- Python 3.13+
- RIOT_API_KEY in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
git clone https://github.com/jifrozen0110/mcp-riot.git
cd mcp-riot
uv syncCreate .env file with your Riot API key:
FILE · .env
RIOT_API_KEY=<YOUR_RIOT_API_KEY>MCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"riot": {
"command": "<YOUR_PATH_TO_UV>",
"args": [
"--directory",
"<YOUR_PATH_TO_MCP_RIOT>/src",
"run",
"--env-file",
"<YOUR_PATH_TO_MCP_RIOT>/.env",
"server.py"
]
}
}
}<YOUR_PATH_TO_UV> is the full path of your uv binary (the author's is /Users/jifrozen/.local/bin/uv), and <YOUR_PATH_TO_MCP_RIOT> is the full path of the folder the git clone step creates. The server itself is src/server.py, and it reads RIOT_API_KEY from the .env file you created in that folder.
