How to Use the Lichess.org Open Chess Intelligence MCP in LangChain

Chain real-time Lichess data directly into LangChain runnables to analyze active tournaments and player profiles on the fly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lichess.org Open Chess Intelligence MCP to LangChain

Create your Vinkius account to connect Lichess.org Open Chess Intelligence 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 Lichess.org Open Chess Intelligence with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build chess reasoning chains in LangChain

The `get_daily_puzzle` tool lets your LangChain agents pull the latest chess challenge directly into their reasoning chains. Your agent can analyze the tactical themes and then fetch a player's recent matches using `get_user_games` to see if they fall for similar tactical motifs. This creates a multi-step analysis pipeline that runs on actual live data. By using this MCP Server, your agent transitions from guessing chess patterns to executing real-time data checks. The output of one tool feeds directly into the next, allowing your runnables to evaluate player performance across different time controls without manual intervention.

Debug and trace chess tool execution with LangSmith

Using the `get_player_data` tool allows you to monitor how your chess agent reasons through player histories in LangSmith. When your LangChain pipeline checks `get_users_online_status`, LangSmith tracks the latency and token cost of each step. You see the exact input parameters and raw JSON payloads returned from the Lichess API. This deep visibility helps you optimize complex multi-tool sequences. If your agent gets stuck in a loop trying to parse massive match histories, you can pinpoint the exact step where the JSON payload slowed down your chain.

Aggregate tournament broadcasts into active workflows

The `list_broadcasts` tool aggregates ongoing elite tournament details directly into your LangChain workflows. The agent runs this to find active elite events, pulls the current games, and matches them against historical opening databases. This lets you build automated recap bots that post game summaries as tournaments unfold. You can also track live presenters using `list_live_streamers` to alert your community when a titled player goes live. The workflow handles the API calls and structures the raw data so your language models can write instant, accurate commentary.

Setup guide

Set up Lichess.org Open Chess Intelligence 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 Lichess.org Open Chess Intelligence 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({
    "lichessorg-open-chess-intelligence-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 Lichess.org Open Chess Intelligence 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 Lichess.org. 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 Lichess.org Open Chess Intelligence 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 Lichess.org Open Chess Intelligence MCP in LangChain

Install the adapter package and initialize the client using your Vinkius endpoint URL. You then pass the tools retrieved from the server directly into your agent's tool list, allowing it to call functions like `get_leaderboards` during execution.

Yes, you should handle this in your LangChain runnables by adding retry logic or rate-limiting wrappers. When calling endpoints like `get_user_games` repeatedly, configuring exponential backoff prevents the Lichess API from blocking your client.

LangChain agents are stateless by default, but you can maintain chess session state by using memory buffers. This allows your agent to remember previous chess positions returned by `get_daily_puzzle` across multiple conversational turns.

Yes, easily. You can pass the chess tools alongside your database tools to a LangChain agent, enabling it to pull a player's rating with `get_player_data` and save it directly to your PostgreSQL database.

The MCP Server only reads public Lichess data like game records and public ratings. Vinkius runs the server in an isolated sandbox, meaning your queries are never stored or exposed to other users.

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