How to Use the Chess.com MCP in AutoGen

Q: How do I set up AutoGen agents to analyze a Chess.com player?

Use mcpservertools to get the tool list for your agents. Then, give a UserProxyAgent a task like, 'Find Magnus Carlsen's last 20 blitz games on Chess.com and tell me his most common opening.' The agents will figure out how to use the tools to get it done.

Q: Can my AutoGen agents find and solve the Chess.com daily puzzle?

Yes. One agent can call getdailypuzzle to get the position and solution. You can then have another agent try to solve it without seeing the solution, and a third agent can act as a critic to check the answer.

Q: Is it possible for an AutoGen team to find the top players on Chess.com?

Absolutely. An agent can call getleaderboards to get the top players. Another agent could then take that list and use getplayerstats on each one to create a detailed report, debating which player is truly the best.

Q: How does my agent group authenticate with this MCP Server?

It's handled by the autogen-extmcp library and your Vinkius endpoint token. Your agents just declare which tools they need; the connection and authentication are automatic.

Deploy AutoGen agent teams that debate and analyze Chess.com data with this MCP server to find the best move.

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 AutoGen

Create your Vinkius account to connect Chess.com to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble an Agent Team to Prep for a Match

Prepare for your next opponent with a team of AutoGen agents. A 'Scout' agent can use `get_player_profile` and `get_player_stats` to get the target's basic info. It passes that to an 'Analyst' agent. The Analyst agent then digs deeper, using `get_player_monthly_games` to pull recent games. A 'Strategist' agent reviews the PGNs and debates with the Analyst about opening weaknesses and common mistakes. You get a consensus-driven game plan, not just a data dump.

Have Agents Debate Tactical Solutions

This isn't just about finding the answer; it's about understanding why. An 'Initiator' agent fetches a position with `get_daily_puzzle` or `get_random_puzzle`. It then presents the FEN to a group of solver agents. One agent might propose a move, while another challenges it, pointing out a flaw. They converse, using the puzzle's context to argue their points until they agree on the best line. It's a way to model the process of tactical calculation with this MCP server.

Let AutoGen Agents Find Your Next Club

Finding a good club is subjective. Let an AutoGen team figure it out. A 'Finder' agent can use `get_player_clubs` on a player you respect. It passes the list of clubs to a 'Reviewer' agent from your MCP-enabled team. The Reviewer agent uses `get_club_info` and `get_club_members` to check activity levels and member strength. A 'Social' agent might even check if the club has streamers using `get_streamers`. They discuss the pros and cons in a conversation, giving you a final recommendation.

Setup guide

Set up Chess.com MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Chess.com tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Chess.com_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Chess.com data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Chess.com_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Chess.com data")
    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 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 AutoGen

Use `mcp_server_tools` to get the tool list for your agents. Then, give a `UserProxyAgent` a task like, 'Find Magnus Carlsen's last 20 blitz games on Chess.com and tell me his most common opening.' The agents will figure out how to use the tools to get it done.

Yes. One agent can call `get_daily_puzzle` to get the position and solution. You can then have another agent try to solve it without seeing the solution, and a third agent can act as a critic to check the answer.

Absolutely. An agent can call `get_leaderboards` to get the top players. Another agent could then take that list and use `get_player_stats` on each one to create a detailed report, debating which player is truly the best.

It's handled by the `autogen-ext[mcp]` library and your Vinkius endpoint token. Your agents just declare which tools they need; the connection and authentication are automatic.

The agents use public data like leaderboards, player stats, and club rosters. Each tool call is an independent, stateless request through the Vinkius sandbox, which doesn't retain any of your agent conversation history or data.

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