What is chess-mcp CLAUDE.md?

Project instructions for chess-mcp, a program that lets an AI interact with chess through the Model Context Protocol (MCP) and shows a web chessboard.

Use it when developing, formatting, linting, or understanding the Express-based MCP server and its chess tools.

It gives contributors the project’s development commands, architecture, and server patterns so they can change the code consistently.

How ibuildthecloud/chess-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ibuildthecloud/chess-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ibuildthecloud/chess-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ibuildthecloud/chess-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ibuildthecloud/chess-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/ibuildthecloud/chess-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ibuildthecloud/chess-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ibuildthecloud/chess-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ibuildthecloud/chess-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ibuildthecloud/chess-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 686 This file is loaded in full into every session.

When invoked 686 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00686	$0.00686
Opus 5.5	$0.00274	$0.00274
Sonnet 5.5	$0.00137	$0.00137
Haiku 4.5	$0.00069	$0.00069

Measured 2mo ago against content hash a8f1a4a013fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

chess-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

This is a Model Context Protocol (MCP) server that implements an interactive chess game. It exposes chess functionality through MCP tools and provides a web-based chessboard interface using MCP-UI.

Development Commands

npm run dev - Start the development server (runs tsx src/server.ts)
npm run format - Format code with Biome
npm run lint - Lint and fix code with Biome

The server runs on http://localhost:3000/mcp

Architecture

MCP Server with Express Integration

This project uses a custom MCP middleware framework that integrates MCP servers with Express.js. Understanding this architecture is critical:

Server Creation Pattern (src/server.ts:76-130):
- newServer() creates a new McpServer instance for each session
- Tools are registered using server.registerTool() with Zod schemas for validation
- Tool handlers receive arguments and a context object with sessionId
Custom MCP Middleware (src/lib/mcp/middleware.ts):
- Middleware(newServer) function wraps the server creation function
- Manages session lifecycle and transport layer
- Maps HTTP requests to MCP protocol using StreamableHTTPServerTransport
- Session IDs come from mcp-session-id header (see src/lib/mcp/header.ts)
- Maintains a registry of active transports keyed by session ID
Game State Management (src/lib/store.ts):
- Games persist to ./games/{sessionId}.json as FEN strings
- loadGame(sessionId) retrieves existing games or returns null
- saveGame(sessionId, game) persists the current game state
- Session ID from MCP context ties games to specific clients

MCP Tool Implementation

Two tools are exposed:

chess_get_board_state: Returns current board state (no arguments)
chess_move: Makes a move or starts new game
- Takes move string (algebraic notation like "e4" or "new")
- Validates moves using chess.js library

Read the full file on GitHub · 69 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 69 lines · 686 tokens per session scan A a8f1a4a013fa

Subscribe to this mod's changes

chess-mcp CLAUDE.md is an instructions file published in the GitHub repository ibuildthecloud/chess-mcp (5 stars, last pushed 1y ago), licensed Apache-2.0. It adds 686 tokens to every session, about $0.0027 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Game development

chess-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
chess-mcp CLAUDE.mdibuildthecloud/chess-mcp	Instructions file	5	1y ago	Apache-2.0	A	686	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

chess-mcp: Instructions file for Claude Code