What is chessceo-mcp CLAUDE.md?

Project instructions for a TypeScript MCP server that connects AI hosts such as Claude Desktop, claude.ai, and ChatGPT to chess.ceo.

Use them when editing tool handlers, shipping engine and strategy guides, or working on the chess.ceo MCP integration.

They explain the server’s layout, authentication model, safety role, and experimental status so agents change the correct layer without assuming backwards compatibility.

How chessceo/chessceo-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to chessceo/chessceo-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/chessceo/chessceo-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/chessceo/chessceo-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/chessceo/chessceo-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/chessceo/chessceo-mcp/claude-md)

Your own site

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

Per session 4,606 This file is loaded in full into every session.

When invoked 4,606 The same file — it is already loaded in full.

Security scan D 3 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	$0.04606	$0.04606
Opus 5.5	$0.01842	$0.01842
Sonnet 5.5	$0.00921	$0.00921
Haiku 4.5	$0.00461	$0.00461

Measured 2mo ago against content hash 9ca07eab8dbc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

chessceo-mcp CLAUDE.md scanned grade D with 3 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

--force`, nuke the npx cache dir, wait 20s for CDN propagation, `sudo systemctl restart`, then verify both the running version (reads

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

`deploy-mcp.sh` nukes `~/.npm/_npx` itself before every restart, so this trap is closed for the normal deploy flow. It's still live for anyone (including future-Claude) who restarts the unit directly without going throug

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **curl/scripts** → same as either of the above

CLAUDE.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chess.ceo MCP server

Model Context Protocol server that exposes chess.ceo to LLM hosts (Claude Desktop, claude.ai, ChatGPT). Every tool here is a thin wrapper on a chess.ceo backend endpoint; this package's job is LLM ergonomics, not business logic.

Repo layout (tool defs split out of index.ts in v0.44 — it's no longer a single monolithic file):

src/index.ts             Handlers + transport (stdio + streamable-HTTP) + auth. callToolInner's
                         switch is the source of truth for what each tool actually does.
src/tools.ts             All tool schemas (TOOLS[] — pure data, name/description/inputSchema).
src/prompts.ts           The three prep-workflow prompts (PROMPTS[]).
src/pgn/                 PGN parse/export/describe, node-id ↔ path resolution (paths.ts),
                         and the mutation primitives (mutations.ts: addLine, addMove,
                         deleteSubtree, promoteVariation, setAnnotations/Comment/Nags/Tag,
                         setCeoEval[Many]).
src/prep/                Prep-file library (list/search/read), and mutation orchestration
                         separate from raw pgn/mutations.ts primitives.
src/analysis/            auto_evaluate / deep_analyse job lifecycle (auto.ts, deep.ts),
                         file_handle.ts, response shaping.
src/courses.ts           find_position_in_courses / read_course_at_position — read-only
                         reference courses, distinct from the user's own prep files.
src/http.ts              Streamable-HTTP transport plumbing.
src/response_transforms.ts  UCI→SAN and other LLM-facing reshaping (see "Where this fits").
src/warnings.ts          Grounding/guardrail text injected into tool responses.
docs/*.md                Bundled at build time, served via read_*_guide tools + matching
                         prompts: engine-usage.md, prep-strategy.md, prep-files-guide.md,
                         pgn-authoring.md, summary-authoring.md.
docs/examples/*.pgn      Worked PGN examples (italian-fried-liver, najdorf-6-f4-white),
                         bundled the same way, referenced from pgn-authoring.md.
tools/fenfind/           Python side-tool (polyglot Zobrist index) that find_position_in_courses
                         shells out to. tools/sf_eval/ — local Stockfish eval helper.
package.json             files: ["dist","docs","README.md","tools"]. docs/ and tools/ must
                         ship or the doc tools and find_position_in_courses degrade/fallback.
Dockerfile               For Glama listing's automated safety checks (not for prod).
.claude-plugin/          Claude Code marketplace manifest, unrelated to the npm package.
CLAUDE.md                This file.

Read the full file on GitHub · 244 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 Changed · +43 lines · +1,088 tokens per session 9ca07eab8dbc
2mo ago First seen · 201 lines · 3,518 tokens per session scan D f6b2743bc2f7

Subscribe to this mod's changes

chessceo-mcp CLAUDE.md is an instructions file published in the GitHub repository chessceo/chessceo-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 4,606 tokens to every session, about $0.0184 per session on Opus 5.5. A static security scan graded it D with 3 findings (asks for root, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

chessceo-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
chessceo-mcp CLAUDE.mdchessceo/chessceo-mcp	Instructions file	0	1mo ago	MIT	D	4,606	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	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	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

chessceo-mcp: Instructions file for Claude Code