Chess UCI
Connect to UCI-compatible chess engines like Stockfish to play and analyze games. Requires a local chess engine binary.
chess-uci-mcp
An MCP bridge that provides an interface to UCI chess engines (such as Stockfish).
Dependencies
You need to have Python 3.10 or newer, and also uv/uvx installed.
Usage
To function, it requires an installed UCI-compatible chess engine, like Stockfish (has been tested with Stockfish 17).
In case of Stockfish, you can download it from https://stockfishchess.org/download/.
On macOS, you can use brew install stockfish.
You need to find out the path to your UCI-capable engine binary; for further example configuration, the path is e.g. /usr/local/bin/stockfish (which is default for Stockfish installed on macOS using Brew).
The further configuration should be done in your MCP setup;
for Claude Desktop, this is the file claude_desktop_config.json (find it in Settings menu, Developer, then Edit Config).
The full path on different OSes
- macOS:
~/Library/Application\ Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%/Claude/claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
Add the following settings to your MCP configuration (depending on the way to run it you prefer):
Uvx (recommended)
Uvx is able to directly run the Python application by its name, ensuring all the dependencies, in a automatically-created virtual environment.
This is the preferred way to run the chess-uci-mcp bridge.
Set up your MCP server configuration (e.g. Claude Desktop configuration) file as following:
"mcpServers": {
"chess-uci-mcp": {
"command": "uvx",
"args": ["chess-uci-mcp@latest", "/usr/local/bin/stockfish"]
}
}
To pass options to the engine, add them to the args array. For example, to set the Threads and Hash options for Stockfish:
"mcpServers": {
"chess-uci-mcp": {
"command": "uvx",
"args": [
"chess-uci-mcp@latest",
"/usr/local/bin/stockfish",
"-o", "Threads", "4",
"-o", "Hash", "128"
]
}
}
Uv
Use it if you have the repository cloned locally and run from it:
"mcpServers": {
"chess-uci-mcp": {
"command": "uv",
"args": ["run", "chess-uci-mcp", "/usr/local/bin/stockfish"]
}
}
Similarly, to pass options when running with uv:
"mcpServers": {
"chess-uci-mcp": {
"command": "uv",
"args": [
"run",
"chess-uci-mcp",
"/usr/local/bin/stockfish",
"-o", "Threads", "4",
"-o", "Hash", "128"
]
}
}
Command-line Options
The application accepts the following command-line options:
ENGINE_PATH: (Required) The path to the UCI-compatible chess engine executable.--uci-optionor-o: Set a UCI option. This option can be used multiple times. It takes two arguments: the option name and its value (e.g.,-o Threads 4).--think-time: The default thinking time for the engine in milliseconds. Defaults to1000.--debug: Enable debug logging.
Available MCP Commands
The bridge provides the following MCP commands:
analyze- Analyze a chess position specified by FEN stringget_best_move- Get the best move for a chess positionset_position- Set the current chess positionengine_info- Get information about the chess engine
Development
# Clone the repository
git clone https://github.com/AnglerfishChess/chess-uci-mcp.git
# ... or
# git clone [email protected]:AnglerfishChess/chess-uci-mcp.git
cd chess-uci-mcp
# Create a virtual environment
uv venv --python python3.10
# Activate the virtual environment
source .venv/bin/activate # On Unix/macOS
# or
.venv\Scripts\activate # On Windows
# Install the package in development mode
# uv pip install -e .
# or, with development dependencies
uv pip install -e ".[dev]"
# Resync the packages:
uv sync --extra=dev
# Run tests
pytest
# Check code style
ruff check
Release process
- Bump version in
pyproject.toml,chess_uci_mcp/__init__.pyanduv.lock. - Build and publish:
uv build
uv-publish
We use uv-publish (install via uvx uv-publish or as dev dependency) because it automatically reads PyPI credentials from ~/.pypirc.
- Tag and push:
git tag v0.x.x
git push && git push --tags
Related sites
관련 서버
Actual Budget MCP
Docker MCP server connecting Claude Desktop/LibreChat/LobeChat to Actual Budget for natural-language budgeting, transaction management, and financial insights.
Aegntic MCP Servers
A collection of Model Context Protocol (MCP) servers for various tasks and integrations, supporting both Python and Node.js environments.
Bitnovo Pay
MCP server for Bitnovo Pay integration with AI agents. Provides cryptocurrency payment capabilities through Bitnovo Pay API. Features include payment creation, status checking, QR code generation, and webhook management with support for multiple tunnel providers (ngrok, zrok, manual).
DICOM MCP Server
Enables AI assistants to query, read, and move data on DICOM servers like PACS and VNA.
Lcontext
An MCP server that exposes user behavior as queryable data for AI coding agents.
Texas Holdem MCP Server
A Texas Hold'em poker game server with an MCP API, built using Node.js and TypeScript.
Questrade MCP Server
An unofficial server to integrate with the Questrade API, providing access to trading accounts, market data, and portfolio information.
Hit The Road Rentals
Search motorhomes, RVs and campervans worldwide — instant results from 300+ rental companies across AU, NZ, US, CA, UK and more.
anneal-memory
Two-layer memory for AI agents with an immune system — episodes compress into identity through citation-validated graduation. Zero dependencies, 5 MCP tools.
SentinelGate
Open-source MCP proxy for AI agent access control. CEL policies, RBAC, full audit trail, content scanning, Admin UI.