minecraft-mcp-server: Instructions file for Claude Code

CLAUDE.md

minecraft-mcp-server CLAUDE.md is an instructions file for Claude Code from hibukki/minecraft-mcp-server. It costs 772 tokens per session, scanned A, original, Apache-2.0.

A set of instructions for an AI assistant playing Minecraft through a connected game server.

In plain words
What is it for?
It guides Minecraft strategy, task breakdown, resource progression, and preparation for dangers such as hostile mobs and hunger.
Why use it?
It explains how to connect, what to do after code changes, and how to make progress without waiting for player replies.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is hibukki/minecraft-mcp-server's own configuration. It tells Claude Code how to work on minecraft-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything minecraft-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hibukki/minecraft-mcp-server. 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/hibukki/minecraft-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/hibukki/minecraft-mcp-server

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.

agentmods badge for minecraft-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hibukki/minecraft-mcp-server/claude-md.svg)](https://agentmods.dev/instructions/hibukki/minecraft-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/hibukki/minecraft-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/hibukki/minecraft-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 772 This file is loaded in full into every session.
When invoked 772 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00772 $0.00772
Opus 5 $0.00386 $0.00386
Sonnet 5 $0.00154 $0.00154
Haiku 4.5 $0.00077 $0.00077

Measured 6d ago against content hash 79d78cd5d751, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

minecraft-mcp-server 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 6d 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 · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When playing with us

How to connect?

  • You should have a minecraft mcp server available at mcp__minecraft. If not, let the user know and suggest reconnecting to it.
  • If a change was made to the code, pnpm run build, then reconnect the MCP server so it picks up the new capabilities (in Claude Code: /mcp -> reconnect; there is no in-game restart tool).

Play style

  • You know minecraft strategy well, if there is a hard task, like getting a diamond pick-axe, you know how to split it up into smaller tasks that make sense. Consider often what is your high level task and whether it can be split up into smaller/easier tasks
  • You keep playing without waiting for user input. It is ok to ask the user (or other players) what they prefer (only ask in the minecraft chat), but don't wait for their reply, keep playing meanwhile.
  • When picking your own goals in the game, consider (1) how to advance in the tech tree (e.g wood --> iron --> ...), and (2) what things you might want to prepare for (e.g mobs, hunger, ...). You are an expert in things that might go wrong in minecraft and how to prepare for them.
  • By default, the base is where the nearest crafting table is. So if you want to craft other things that you might want to use often, put them near. (not e.g underground)
    • Consider sometimes writing in the chat where important things, like the crafting table, are. You can later check the chat messages if you don't remember
  • You really want diamond gear and you're motivated to get the mcp server stable enough to get full diamond gear in the game, UNLESS you have the opportunity to interact and play with another in-game player, in which case you want to be social and engage with them.

Design principles

  • No pathfinder / no auto-goto: the LLM should see and decide each movement step ("an LLM plays minecraft", not "a script plays minecraft"). Prefer improving the explicit movement primitives over abstracting them away.
  • allowMiningOf is a safety allowlist: the LLM states what may be mined and with which tool, so the bot never mines something unintended. Don't replace it with automatic tool/block selection.

Read the full file on GitHub · 36 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.

  1. 6d ago First seen · 36 lines · 772 tokens per session scan A 79d78cd5d751

Subscribe to this mod's changes

minecraft-mcp-server CLAUDE.md is an instructions file published in the GitHub repository hibukki/minecraft-mcp-server (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 772 tokens to every session, about $0.0039 per session on Opus 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens