Riot Games MCP Server for LlamaIndex 12 tools — connect in under 2 minutes
LlamaIndex specializes in data-aware AI agents that connect LLMs to structured and unstructured sources. Add Riot Games as an MCP tool provider through Vinkius and your agents can query, analyze, and act on live data alongside your existing indexes.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
mcp_client = BasicMCPClient("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
mcp_tool_spec = McpToolSpec(client=mcp_client)
tools = await mcp_tool_spec.to_tool_list_async()
agent = FunctionAgent(
tools=tools,
llm=OpenAI(model="gpt-4o"),
system_prompt=(
"You are an assistant with access to Riot Games. "
"You have 12 tools available."
),
)
response = await agent.run(
"What tools are available in Riot Games?"
)
print(response)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Riot Games MCP Server
Connect to Riot Games API and access League of Legends player data through natural conversation.
LlamaIndex agents combine Riot Games tool responses with indexed documents for comprehensive, grounded answers. Connect 12 tools through Vinkius and query live data alongside vector stores and SQL databases in a single turn. ideal for hybrid search, data enrichment, and analytical workflows.
What you can do
- Player Lookup — Find any player by Riot ID (game name + tag line) and get their PUUID
- Summoner Profile — Get summoner level, profile icon and account details
- Match History — Browse recent matches with full details (KDA, items, runes, gold, damage)
- Ranked Stats — Check current rank, tier, LP and win/loss records for all queues
- Champion Masteries — View champion mastery levels, points and tokens
- Live Games — Check if a player is currently in-game with team compositions and bans
- Featured Games — Browse high-elo live games currently in progress
- Champion Data — Get full champion info including abilities, stats, lore and skins
The Riot Games MCP Server exposes 12 tools through the Vinkius. Connect it to LlamaIndex in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Riot Games to LlamaIndex via MCP
Follow these steps to integrate the Riot Games MCP Server with LlamaIndex.
Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Run the agent
Save to agent.py and run: python agent.py
Explore tools
The agent discovers 12 tools from Riot Games
Why Use LlamaIndex with the Riot Games MCP Server
LlamaIndex provides unique advantages when paired with Riot Games through the Model Context Protocol.
Data-first architecture: LlamaIndex agents combine Riot Games tool responses with indexed documents for comprehensive, grounded answers
Query pipeline framework lets you chain Riot Games tool calls with transformations, filters, and re-rankers in a typed pipeline
Multi-source reasoning: agents can query Riot Games, a vector store, and a SQL database in a single turn and synthesize results
Observability integrations show exactly what Riot Games tools were called, what data was returned, and how it influenced the final answer
Riot Games + LlamaIndex Use Cases
Practical scenarios where LlamaIndex combined with the Riot Games MCP Server delivers measurable value.
Hybrid search: combine Riot Games real-time data with embedded document indexes for answers that are both current and comprehensive
Data enrichment: query Riot Games to augment indexed data with live information before generating user-facing responses
Knowledge base agents: build agents that maintain and update knowledge bases by periodically querying Riot Games for fresh data
Analytical workflows: chain Riot Games queries with LlamaIndex's data connectors to build multi-source analytical reports
Riot Games MCP Tools for LlamaIndex (12)
These 12 tools become available when you connect Riot Games to LlamaIndex via MCP:
get_account_by_puuid
Returns game name, tag line and account metadata. Get player account details by PUUID
get_account_by_riot_id
Returns the PUUID (Player Universally Unique Identifier), game name, tag line and account metadata. The PUUID is required for most other API calls. Get player account by Riot ID (game name + tag line)
get_active_game
Returns game mode, game type, banned champions, all players with their champions, summoner spells, runes and team info. Returns 404 if the summoner is not in a game. Platform codes: br1, na1, euw1, eun1, kr, jp1, oc1, la1, la2, tr1, ru. Get current live game for a summoner
get_champion_details
Uses Data Dragon (static data, no API key needed). Get detailed info for a specific champion
get_champion_masteries
Returns champion ID, mastery level (1-7), mastery points, last play time, chest earned status and tokens needed for next level. Platform codes: br1, na1, euw1, eun1, kr, jp1, oc1, la1, la2, tr1, ru. Get champion mastery data for a player
get_champions
Uses Data Dragon (static data, no API key needed). Optional version (e.g. "14.1.1") and locale (e.g. "en_US", "pt_BR"). Get all League of Legends champions
get_featured_games
Returns game mode, banned champions, all players with their champions, summoner spells and game length. Platform codes: br1, na1, euw1, eun1, kr, jp1, oc1, la1, la2, tr1, ru. Get currently featured games (high elo live games)
get_league_entries
Returns tier (IRON, BRONZE, SILVER, GOLD, PLATINUM, EMERALD, DIAMOND, MASTER, GRANDMASTER, CHALLENGER), rank (I-IV), LP, wins, losses and hot/streak info. Platform codes: br1, na1, euw1, eun1, kr, jp1, oc1, la1, la2, tr1, ru. Get ranked league entries for a summoner
get_match
Requires the regional routing where the match was played (americas, europe, asia, sea). Get detailed match data by match ID
get_match_ids
Returns up to 20 match IDs by default. Use count (1-100) to get more matches and start for pagination. Regional routing: americas (NA, BR, LAN, LAS), europe (EUW, EUNE, TR, RU), asia (KR, JP), sea (PH, SG, TH, TW, VN, OCE). Get match history (match IDs) for a player
get_summoner_by_id
Returns summoner level, profile icon ID, revision date and account ID. Platform codes: br1, na1, euw1, eun1, kr, jp1, oc1, la1, la2, tr1, ru. Get League of Legends summoner profile by summoner ID
get_summoner_by_puuid
The summoner ID is needed for league and spectator queries. Platform codes: br1, na1, euw1, eun1, kr, jp1, oc1, la1, la2, tr1, ru. Get League of Legends summoner profile by PUUID
Example Prompts for Riot Games in LlamaIndex
Ready-to-use prompts you can give your LlamaIndex agent to start working with Riot Games immediately.
"Find the summoner Faker on KR server."
"What's Faker's ranked stats on KR?"
"Get Faker's last 5 match IDs."
Troubleshooting Riot Games MCP Server with LlamaIndex
Common issues when connecting Riot Games to LlamaIndex through the Vinkius, and how to resolve them.
BasicMCPClient not found
pip install llama-index-tools-mcpRiot Games + LlamaIndex FAQ
Common questions about integrating Riot Games MCP Server with LlamaIndex.
How does LlamaIndex connect to MCP servers?
Can I combine MCP tools with vector stores?
Does LlamaIndex support async MCP calls?
Connect Riot Games with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Riot Games to LlamaIndex
Get your token, paste the configuration, and start using 12 tools in under 2 minutes. No API key management needed.