How to Use the Riot Games MCP in OpenAI Agents SDK

Q: How do I handle rate limits when fetching Riot Games matches with OpenAI Agents SDK?

Use the cacheToolsList=True parameter in your HTTP transport config to keep tool schemas cached. For heavy tools like getmatch, design your agent prompts to request sequential fetches rather than parallel bursts, preventing API key throttling.

Q: Can I use OpenAI Agents SDK to check if a player is currently in a Riot Games lobby?

Yes, the getactivegame tool returns active game details or a 404 if they are offline. Your agent can catch this error gracefully using the SDK's built-in validation before executing downstream analysis.

Q: How does OpenAI Agents SDK manage PUUID lookups for Riot Games accounts?

Your agent calls getaccountbyriotid to translate a player's game name and tag line into a PUUID. The SDK then passes this identifier to tools like getsummonerbypuuid to retrieve the rank profile.

Q: Can I filter champion details?

Yes, your agent can query getchampiondetails for specific static data. This tool runs on Data Dragon, so it doesn't consume your Riot API key quota.

Build production-grade agents that safely fetch League statistics using this Riot Games MCP Server with OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect Riot Games to OpenAI Agents SDK — 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Safe Live Match Tracking with OpenAI Agents SDK

The `get_active_game` tool exposes real-time match data directly to your OpenAI Agents SDK workflow using our MCP connection. Because the OpenAI Agents SDK uses strict guardrails, you can block your agent from executing calls if a League player is not in an active session, avoiding unnecessary 404 errors. This OpenAI setup lets your agent make live match decisions based on active bans and runes. Frankly, the SDK handles regional routing like na1 or euw1 automatically, so your pipeline won't stall when querying high-stakes League of Legends lobbies.

Multi-Agent Stats Analysis and Handoffs

The `get_match_ids` and `get_match` tools let you build a multi-agent system where one OpenAI Agents SDK agent fetches match lists and hands off the raw JSON to another. Honestly, with this MCP Server, your setup distributes the work of parsing 100 historical League matches without hitting rate limits. One OpenAI agent can focus on extracting PUUIDs via `get_account_by_riot_id` while another pulls specific performance metrics. The built-in tracing on your OpenAI dashboard monitors these handoffs, ensuring no League of Legends data gets lost during the transfer.

Guarded Champion Mastery Evaluations

The `get_champion_masteries` tool retrieves a player's mastery points, levels, and chest statuses directly into your OpenAI Agents SDK decision loop via MCP. Before your OpenAI Agents SDK triggers a lookup, you can configure guardrails to check if the target player's PUUID is valid. This prevents your OpenAI agent from spamming the Riot Games API with bad identifiers. By enabling the `cacheToolsList=True` option in your OpenAI Python setup, your agent quickly matches champion IDs with static Data Dragon info from `get_champions` without wasting your rate limit.

Setup guide

Set up Riot Games MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Riot Games tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Riot Games tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Riot Games tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Riot Games Agent",
            instructions="You have access to Riot Games tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Use the `cacheToolsList=True` parameter in your HTTP transport config to keep tool schemas cached. For heavy tools like `get_match`, design your agent prompts to request sequential fetches rather than parallel bursts, preventing API key throttling.

Yes, the `get_active_game` tool returns active game details or a 404 if they are offline. Your agent can catch this error gracefully using the SDK's built-in validation before executing downstream analysis.

Your agent calls `get_account_by_riot_id` to translate a player's game name and tag line into a PUUID. The SDK then passes this identifier to tools like `get_summoner_by_puuid` to retrieve the rank profile.

Yes, your agent can query `get_champion_details` for specific static data. This tool runs on Data Dragon, so it doesn't consume your Riot API key quota.

Vinkius runs the MCP Server in an isolated, zero-trust sandbox. Your Riot account metadata and PUUIDs stay protected because your local setup only needs a single secure endpoint token to execute tools.

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