How to Use the Chess.com MCP in OpenAI Agents SDK

Q: How do I handle Chess.com player stats with the OpenAI Agents SDK?

Use the getplayerstats tool inside your agent's tool declaration. The SDK automatically registers the schema, allowing your agent to fetch rapid, blitz, and bullet ratings in a single run.

Q: Can I trace Chess.com game downloads in the OpenAI Agents SDK dashboard?

Yes, every call to getplayermonthlygames goes through the standard OpenAI tracing pipeline. You can see the raw PGN data returned from the MCP Server and monitor how your agent processes the match history.

Pipe Chess.com player telemetry directly into your OpenAI Agents SDK workflows with strict runtime safety validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Chess.com MCP to OpenAI Agents SDK

Create your Vinkius account to connect Chess.com to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Chess.com with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pull historical games safely via OpenAI Agents SDK

Build a dedicated analysis agent that pulls historical match records without risking execution errors. Your agent calls `get_player_game_archives` to locate valid monthly chunks and then pulls the actual PGNs using `get_player_monthly_games`. This MCP Server hooks into the OpenAI runtime so your agent can study openings and identify tactical mistakes. Because the SDK enforces strict tool schemas, your agent won't hallucinate invalid parameters when querying historical months. You can trace every single game fetch directly on your OpenAI developer dashboard to monitor latency and token costs.

Track real-time player activity with strict guardrails

Set up a monitoring agent that checks player status before initiating heavy analytical workflows. By calling `is_player_online` and `get_player_current_games`, your agent determines if a target user is actively playing daily matches. The OpenAI Agents SDK allows you to configure handoffs, meaning a general concierge agent can check the online status first, then hand the task over to a specialized chess engine agent if the player is active. This keeps your token footprint small and your system modular.

Build interactive training loops with tactical puzzles

Serve interactive chess puzzles directly to your users by querying the active daily challenge. Your agent calls `get_daily_puzzle` to fetch the current FEN position and the exact move sequence, or falls back to `get_random_puzzle` for infinite training loops. This MCP Server handles the connection details so your agent only has to focus on evaluating the user's responses. You can easily build a slack bot that feeds daily tactics to your team, tracking player performance over time through the SDK's native logging.

Setup guide

Set up Chess.com 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 Chess.com tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Chess.com 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="Chess.com Agent",
            instructions="You have access to Chess.com 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 Chess.com. 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 Chess.com 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 Chess.com MCP in OpenAI Agents SDK

Use the `get_player_stats` tool inside your agent's tool declaration. The SDK automatically registers the schema, allowing your agent to fetch rapid, blitz, and bullet ratings in a single run.

Yes, every call to `get_player_monthly_games` goes through the standard OpenAI tracing pipeline. You can see the raw PGN data returned from the MCP Server and monitor how your agent processes the match history.

The SDK strictly validates tool definitions before passing them to the model. When the agent attempts to run `get_player_profile`, it must supply a valid username string, preventing malformed API requests.

Yes. You can have your agent fetch the list of active grandmasters using `get_titled_players` with the 'GM' argument. Then, it can loop through the results and run `is_player_online` to see who is active.

Your data is safe. Vinkius runs this MCP Server in an isolated sandboxed environment where no credentials or personal chess records are stored. Your queries are ephemeral, passing directly from the secure endpoint to your local SDK instance.

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