Spark
Sign In
MCP Connector

Analyze Chess Games and Puzzles with Stockfish

MCP server giving LLMs chess awareness: Stockfish and neural-engine analysis, opening databases, Lichess games, and rendered board positions.

Connect
Works with githublichessnode.js
jalpp
Maintainer?
91
Spark score
out of 100
Updated last month
Version chessagine-mcp-v0.7.
Models
universal
Add to Favorites

Why it matters

Enhance your chess understanding and playing strength by leveraging advanced analysis powered by the Stockfish engine, opening databases, and tactical training.

Outcomes

What it gets done

01

Perform deep chess engine analysis with customizable depth.

02

Analyze thematic elements and variations within games.

03

Access and filter Lichess puzzles for targeted tactics training.

04

Generate interactive game visualizations and board representations.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/vb-chessagine-mcp | bash

Capabilities

Tools your agent gets

analyze_position

Analyzes a chess position using Stockfish engine with customizable search depth.

thematic_analysis

Evaluates positional themes including material, mobility, space, and king safety.

variation_analysis

Compares multiple chess lines and tracks positional changes across variations.

validate_move

Checks move legality and generates board state descriptions.

analyze_game

Performs comprehensive game analysis with theme progression and critical moments.

visualize_board

Generates HTML chess board visualization for any position.

create_game_viewer

Creates interactive game replay viewer with move navigation capabilities.

get_tactics_puzzle

Retrieves tactical puzzles from Lichess database with theme filtering.

+2 tools

Overview

Chessagine MCP Server

An MCP server giving LLMs real chess engine access - Stockfish plus neural engines Maia2, Leela, and Elite Leela - alongside Lichess game history, opening databases, and rendered board/PGN visualization for position and game analysis. Use for chess-specific analysis: comparing engine evaluations, reviewing Lichess games, or studying opening repertoires. Requires Node.js 22+ locally or a Vercel deployment to self-host.

What it does

ChessAgine MCP is a Model Context Protocol server that gives LLMs deep chess awareness by exposing real-time board state, Stockfish analysis, opening databases, Lichess games, and neural chess engines including Maia2, Leela, and Elite Leela. It renders individual positions and full PGN games for visual analysis, letting an AI agent reason about positions, evaluate variations, detect tactical or strategic themes, explore game databases, and interact directly with chess engines rather than reasoning about chess text alone.

Documented usage patterns include pulling a user's last Lichess game by username and analyzing it with Stockfish, comparing and contrasting what Stockfish thinks of a given FEN position against Leela and Maia's neural evaluations, and analyzing an opening repertoire from a chessboard. A companion .skill file in the chessagine-skill/ folder is meant to be given to the LLM so it knows how to properly use the MCP server's capabilities.

git clone https://github.com/jalpp/chessagine-mcp.git
cd chessagine-mcp
npm install
npm run build

When to use - and when NOT to

Use this connector when you want an AI assistant to analyze chess positions or games with real engine backing - comparing classical search-based evaluation (Stockfish) against neural, human-style engines (Maia2, Leela, Elite Leela) - or to pull and review Lichess game history and render boards visually rather than describing positions in text. It's suited to chess study, opening-repertoire review, and engine-comparison workflows. It is less useful outside of chess-specific analysis, and self-hosted deployment requires either Node.js 22+ locally or a Vercel deployment, so environments without either path cannot run it.

Capabilities

Accepts a FEN position, a Lichess username and game, or an opening line as a chess query, and returns engine evaluations from Stockfish and the neural engines (Maia2, Leela, Elite Leela), rendered board or PGN visualizations, and opening-database or game-history data for the AI agent to reason over.

How to install

Installs into Claude Desktop either as a prebuilt .mcpb extension file or via a local Node.js build (Node.js 22+) registered in claude_desktop_config.json, or can be self-hosted by forking the repository and deploying to Vercel with no environment variables required, exposing the server at https://your-project.vercel.app/mcp. For local development: npm run build:mcp builds the MCP server layer and generates the .mcpb file, npm run build:ui builds the ChessAgine UI HTML, npm run start starts the server, and npm run debug opens the MCP Inspector to verify changes. The project is MIT-licensed, except the /themes and /protocol directories, which are licensed under the GPL.

Who it's for

Chess players and analysts who want an AI assistant to evaluate positions and games using real chess engines, compare classical versus neural engine assessments, review Lichess game history, or study opening repertoires with visual board rendering instead of text-only chess discussion.

Source README

ChessAgine MCP

ChessAgine

ChessAgine MCP is a Model Context Protocol server that gives LLMs deep chess awareness by exposing real-time board state, Stockfish analysis, opening databases, Lichess games, and neural engines including Maia2, Leela, and Elite Leela.

It also renders individual positions and full PGN games for in-depth visual analysis-enabling AI agents to reason about positions, evaluate variations, detect themes, explore game databases, and interact directly with chess engines.

Preview

ChessAgine Preview

Installation

Option 1: Using MCPB File (Recommended)

Download the chessagine-mcp.mcpb file and install it directly in Claude Desktop:

  1. Download the latest release from GitHub releases
  2. Open Claude Desktop
  3. Go to Settings → Extensions → Install from file
  4. Select the chessagine-mcp.mcpb file
  5. Restart Claude Desktop

Option 2: Local Development Setup

Prerequisites
  • Node.js 22+
  • npm or yarn package manager
Clone and Setup
git clone https://github.com/jalpp/chessagine-mcp.git
cd chessagine-mcp
npm install
npm run build
Configure Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

macOS/Linux:

{
  "mcpServers": {
    "chessagine-mcp": {
      "command": "node",
      "args": ["/absolute/path/to/chessagine-mcp/build/runner/stdio.js"]
    }
  }
}

Windows:

{
  "mcpServers": {
    "chessagine-mcp": {
      "command": "node", 
      "args": ["C:\\absolute\\path\\to\\chessagine-mcp\\build\\runner\\stdio.js"]
    }
  }
}

Usage:

  • show me my last Lichess game I played, I'm insert_your_username there, also analyze the game using Stockfish
  • given fen compare and constrast what stockfish thinks vs Leela and Maia
  • analyze my opening rep from Chessboard magic.

ChessAgine.Skill

to properly use ChessAgine MCP, give LLM access to how to properly use the it via .skill file in ./chessagine-skill/ folder

Deploy your own instance

You can deploy your own copy to Vercel in a few clicks:

  1. Fork this repo
  2. Go to vercel.com/new and import your fork
  3. No environment variables needed - just deploy
  4. Your server will be at https://your-project.vercel.app/mcp

Dev commands

npm run build:mcp  # Builds the mcp server layer which generates mcpb file
npm run build:ui   # Builds the ChessAgine MCP UI html files
npm run build      # Builds entire project, use for local development
npm run start      # starts the MCP server
npm run debug      # opens MCP inspector to inspect new changes made

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.