ChessAgine MCP
Offers community support through a Discord server for ChessAgine users to get help and engage with other chess enthusiasts.
Integrates with GitHub for project hosting, issue tracking, feature requests, and accessing releases including the MCPB installation files.
Provides access to Lichess's extensive chess database including 3+ million tactical puzzles with theme filtering, master game statistics, opening explorer data, and user game history retrieval for comprehensive chess analysis and training.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ChessAgine MCPanalyze this chess position: r1bqkbnr/pppp1ppp/2n5/4p3/4P3/5N2/PPPP1PPP/RNBQKB1R w KQkq - 2 3"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ChessAgine MCP
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
Related MCP server: Lichess MCP
Installation
ChessAgine MCP is aimed at chess players as much as developers — if you're not sure whether you have Node.js/npm installed, see the prerequisites note in install.md before picking an option below.
Option 1: Config File (Recommended, most reliable)
This is currently the most stable way to connect ChessAgine MCP to Claude Desktop.
Prerequisites
Node.js 22+
npm or yarn package manager
Anthropic MCP Bundle CLI (npm install -g @anthropic-ai/mcpb)
Clone and Setup
git clone https://github.com/jalpp/chessagine-mcp.git
cd chessagine-mcp
npm install
npm run buildConfigure Claude Desktop
MacOs
Add to ~/Library/Application Support/Claude/claude_desktop_config.json
Windows
Run (Get-AppxPackage *Claude*).PackageFamilyName to find the virtualized Claude Desktop folder
Add to %LOCALAPPDATA%\Packages\Claude_virtualized_folder\LocalCache\Roaming\Claude\claude_desktop_config.json
Linux
Add to ~/.config/Claude/claude_desktop_config.json
macOS/Linux:
{
"mcpServers": {
"chessagine-mcp": {
"command": "node",
"args": ["/absolute/path/to/chessagine-mcp/build/runner/stdio.js"],
"env": {
"LICHESS_API_TOKEN": "optional-your-lichess-api-token",
"CHESSBOARD_MAGIC_PAT": "optional-your-chessboardmagic-pat",
"POSIRA_API_KEY": "optional-your-posira-api-key"
}
}
}
}Windows:
{
"mcpServers": {
"chessagine-mcp": {
"command": "node",
"args": ["C:\\absolute\\path\\to\\chessagine-mcp\\build\\runner\\stdio.js"],
"env": {
"LICHESS_API_TOKEN": "optional-your-lichess-api-token",
"CHESSBOARD_MAGIC_PAT": "optional-your-chessboardmagic-pat",
"POSIRA_API_KEY": "optional-your-posira-api-key"
}
}
}
}Option 2: Using MCPB File (experimental — currently less stable)
The .mcpb install path has known rough edges in some Claude Desktop versions. If it fails to load, use Option 1 above instead. Its one advantage: Claude Desktop runs it with its own bundled Node runtime, so you don't need Node.js/npm installed yourself for this option.
Download the chessagine-mcp.mcpb file and install it directly in Claude Desktop:
Download the latest release from GitHub releases
Open Claude Desktop
Go to Settings → Extensions → Install from file
Select the
chessagine-mcp.mcpbfileRestart Claude Desktop
To make sure its working correctly ask it to render the chessboard or a specific chess query
Option 3: Connect to the Hosted Remote Server (No Install)
Skip the build entirely and point any MCP-compatible client at the hosted deployment:
https://chessagine-mcp.vercel.app/mcpThis is a Streamable HTTP endpoint — no API key or local setup required. Exact steps differ by client (config file vs. UI), so see install.md for copy-pasteable setup steps covering Claude Desktop, Claude Code, LibreChat, Open WebUI, AnythingLLM, Jan, Goose, Cursor, Windsurf, Cline, VS Code, Continue.dev, Zed, and other MCP-compatible GUIs — both open source and proprietary — for both the remote URL and the local stdio server.
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:
Fork this repo
Go to vercel.com/new and import your fork
No environment variables needed — just deploy
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 madeLicense
This project is licensed under the MIT License, the /themes and /protocol are under GPL. See the LICENSE file for details.
Authors
@jalpp
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Appeared in Searches
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/jalpp/chessagine-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server