How to Use the Chess.com MCP in LangChain

Q: How do I analyze a Chess.com player's recent games with LangChain?

Use createagent with the Chess.com tools. Chain getplayergamearchives to find the latest month, then pass that to getplayermonthlygames to get the PGNs. LangSmith will show you the whole flow.

Q: Can I find a list of grandmasters on Chess.com using LangChain?

Yes. Your agent can call the gettitledplayers tool with the title set to 'GM'. You can then chain this with getplayerprofile to get more details on each one.

Q: What's the best way to find a club on Chess.com with my LangChain agent?

Start with a player you admire. Use getplayerclubs to see their affiliations. Then, feed those club IDs into getclubinfo to get descriptions and member counts to decide if you want to join.

Build LangChain agents that analyze Chess.com players, games, and stats in a single, observable chain.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Tool Calls for Deep Player Scouting

Start with just a username. Your LangChain agent can use `get_player_profile` to confirm they exist, then immediately call `get_player_stats` to check their ratings. It doesn't have to stop there. The agent uses those results to decide the next step. Maybe it calls `get_player_game_archives` to see which months have games, then `get_player_monthly_games` to pull every PGN from their last tournament. Each step is a logical link in your chain, all traced in LangSmith.

Create Custom Tactical Training Workflows

Go beyond the standard puzzle of the day. Build a LangChain agent that generates a personalized tactics session based on your current rating. The agent can check your stats with `get_player_stats`, then fetch a `get_random_puzzle` within your target rating range. You can chain this further. Have the agent log the puzzle's FEN and solution, or even cross-reference the source game's players using `get_player_profile`. It's a simple way to build a custom training loop that adapts to you.

Find Opponents and Clubs with a LangChain MCP Server

Don't just browse the site. Deploy an agent to find your next opponent. It could start by getting a list of grandmasters with `get_titled_players`, check who's online with `is_player_online`, and then pull their current games with `get_player_current_games`. This isn't just for individuals. The same chain can discover communities. Use `get_player_clubs` to see where a strong player hangs out, then use `get_club_info` and `get_club_members` to see if it's a good fit. Your agent does the legwork; this MCP Server gives it the tools.

Setup guide

Set up Chess.com 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 Chess.com 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({
    "chesscom-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 Chess.com 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 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 LangChain

Use `create_agent` with the Chess.com tools. Chain `get_player_game_archives` to find the latest month, then pass that to `get_player_monthly_games` to get the PGNs. LangSmith will show you the whole flow.

Yes. Your agent can call the `get_titled_players` tool with the title set to 'GM'. You can then chain this with `get_player_profile` to get more details on each one.

Start with a player you admire. Use `get_player_clubs` to see their affiliations. Then, feed those club IDs into `get_club_info` to get descriptions and member counts to decide if you want to join.

You don't have to worry about it. The Vinkius MCP endpoint token handles all the auth against the Chess.com API. Your LangChain agent just calls the tools.

It only touches public Chess.com data like player profiles, game archives, and club member lists. Your Vinkius endpoint is sandboxed and ephemeral, so your request context is isolated and disappears after the job is done.

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