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

Q: Can I index tournament broadcasts from Lichess.org Open Chess Intelligence into LlamaIndex?

Yes. You can write a pipeline that calls listbroadcasts, parses the tournament data, and indexes the text descriptions into your vector store for semantic search.

Index live Lichess player statistics and tournament games into LlamaIndex vector stores for semantic chess search.

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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live chess games for semantic retrieval

The `get_user_games` tool extracts raw match histories so LlamaIndex can index them into searchable vector stores. Instead of just displaying the moves, your application converts the match history into vector embeddings. You can then query your index to find games where a player struggled against specific pawn structures. This approach eliminates the hallucination issues common in chess analysis. Your query engine pulls directly from the indexed Lichess data, ensuring that tactical breakdowns are grounded in actual moves played on the server.

Build a real-time chess RAG pipeline

The `get_user_activity` tool feeds recent player behavior logs directly into your LlamaIndex RAG pipelines. Your RAG pipeline can retrieve historical opening theory from your vector store while simultaneously calling `get_player_data` to check a player's current rating and performance. This gives your agent a complete view of a player's current form. You can also analyze recent player behavior. This lets you ask your LlamaIndex query engine complex questions about whether a player's tactical sharpness is declining based on their recent puzzle-solving speed.

Analyze active tournament broadcasts via MCP Server

The `list_broadcasts` tool monitors live chess events to build real-time query engines in LlamaIndex. By calling `list_broadcasts` and `get_tv_channels` through the MCP Server, your LlamaIndex agent monitors top-tier games as they happen, indexing the moves into a temporary vector store for instant analysis. This setup allows you to build real-time search tools for live events. Users can ask questions about active games, and the RAG engine will pull the latest board states directly from the indexed stream data.

Setup guide

Set up Lichess.org Open Chess Intelligence MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Lichess.org Open Chess Intelligence MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Lichess.org Open Chess Intelligence tools.",
)
response = await agent.run("List recent Lichess.org Open Chess Intelligence data")

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 LlamaIndex

You initialize the MCP client with your Vinkius URL and wrap it using the LlamaIndex tool spec helper. This exposes tools like `get_leaderboards` directly to your function-calling agents.

Yes. You can write a pipeline that calls `list_broadcasts`, parses the tournament data, and indexes the text descriptions into your vector store for semantic search.

LlamaIndex does not cache API responses by default, but you can persist the generated vector index. This saves you from repeatedly calling `get_player_data` for the same user, reducing API overhead.

You can use the allowed tools filter when defining the tool spec. This lets you restrict the agent to only calling `get_daily_puzzle` if you want a simple daily tactic app.

The server only accesses public tournament broadcasts and public team rosters. Vinkius processes these requests in ephemeral sandboxes, meaning no chess data or API queries are stored permanently.

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