How to Use the Riot Games MCP in LangChain

Q: How do I handle 404 errors in LangChain when a player isn't in an active Riot Games session?

When getactivegame returns a 404, your LangChain chain can catch that exception within its routing logic. You can instruct the LangChain agent to fall back to getfeaturedgames or pull static data via getchampions instead.

Feed live Riot Games telemetry directly into your LangChain reasoning loops to build responsive, data-driven gaming agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Riot Games MCP to LangChain

Create your Vinkius account to connect Riot Games to LangChain — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Riot Games with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Chain Live Match Telemetry with LangChain

LangChain agents can immediately grab a player's active match status using `get_active_game` and pass the returned team roster to subsequent steps. The LangChain chain takes the raw player list and feeds each summoner ID into `get_summoner_by_puuid` to map out the entire lobby's competitive history in real time. By using this MCP Server, your LangChain agent executes these multi-step Riot Games lookups sequentially without hardcoded logic. If a query fails because a player is offline, the LangChain chain catches the 404 and pivots to `get_featured_games` to analyze high-tier matches instead.

Trace Riot API Performance in LangSmith

Debugging rate limits on the Riot Games API is painful when you run deep analytical LangChain loops. LangChain's observability tools trace every call to `get_match` and `get_match_ids` so you see exactly how many tokens your agent consumes when parsing a player's historical performance. You can monitor latency spikes on regional Riot Games routing endpoints like Europe or Americas directly in your LangChain dashboard. This visibility helps you tune your LangChain agent's prompt structure when it requests 100 Riot Games matches to calculate champion win rates.

Aggregate League Stats Across Multi-Server Flows

Combine Riot Games player data with external databases by registering this server alongside other resources in your LangChain MultiServerMCPClient. Your LangChain agent can fetch a player's ranked standing via `get_league_entries` and instantly write it to a Postgres database or compare it against discord user IDs. The LangChain setup handles the session state, so your agent remembers the player's active Riot Games PUUID from `get_account_by_riot_id` across different turns of the conversation. You get a clean, consolidated MCP tool schema for Riot Games without writing custom LangChain endpoint glue.

Setup guide

Set up Riot Games MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Riot Games tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "riot-games-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Riot Games transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Riot Games API. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Riot Games now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Riot Games MCP in LangChain

The output of one Riot Games tool serves as the input for the next in your LangChain chain. For example, your agent calls `get_account_by_riot_id` to get a player's PUUID, then immediately feeds that string into `get_champion_masteries` to check their highest-scoring champions.

Yes, you can track every single LangChain call to tools like `get_match` or `get_league_entries` using LangSmith tracing. This shows you the exact latency and input-output payloads for each Riot Games endpoint.

When `get_active_game` returns a 404, your LangChain chain can catch that exception within its routing logic. You can instruct the LangChain agent to fall back to `get_featured_games` or pull static data via `get_champions` instead.

Install the MCP adapter package and instantiate the client pointing to your Vinkius Riot Games endpoint. Register the tools with your LangChain agent executor to let the LLM decide when to call endpoints like `get_summoner_by_id`.

Vinkius runs the server in an isolated sandbox where your Riot Games API keys and retrieved PUUIDs are never exposed to the LangChain client directly. Only the processed outputs of tools like `get_account_by_puuid` reach your local runtime environment over encrypted connections.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript