minecraft-mcp: Instructions file for Claude Code

CLAUDE.md

minecraft-mcp CLAUDE.md is an instructions file for Claude Code from IotA-asce/minecraft-mcp. It costs 1,095 tokens per session, scanned A, original, MIT.

A set of instructions for connecting a coding agent to a specific live Minecraft Java world over a local network. It records the required game version, connection details, safe operating rules, and a tested bot setup.

In plain words
What is it for?
Use it when inspecting or operating the named Minecraft world with a bot, including setting up the compatible connection and verifying saved-world data.
Why use it?
It reduces connection mistakes and helps the agent avoid confusing the live world with a different local server or changing repository files.

Instructions file for Claude Code

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

This is IotA-asce/minecraft-mcp's own configuration. It tells Claude Code how to work on minecraft-mcp 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 configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/muinnasif/Library/Application.

Reuse

Borrowing it

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

agentmods badge for minecraft-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/iota-asce/minecraft-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/iota-asce/minecraft-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/iota-asce/minecraft-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/iota-asce/minecraft-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.

agentmods 80×15 button for minecraft-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/iota-asce/minecraft-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/iota-asce/minecraft-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,095 This file is loaded in full into every session.
When invoked 1,095 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01095 $0.01095
Opus 5 $0.00548 $0.00548
Sonnet 5 $0.00219 $0.00219
Haiku 4.5 $0.00110 $0.00110

Measured 4d ago against content hash e512be346f26, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

minecraft-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 4d 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 · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instructions for Claude Code: connect to the owner's live Minecraft world

Current world

The owner is running Minecraft Java Edition 26.2 with the single-player world nz open to LAN. The live LAN server is on this same Mac at:

  • host: 127.0.0.1
  • port: 5056
  • dimension: minecraft:overworld

The world must be open and LAN must still be enabled before connecting. Cheats are enabled by the LAN session. This is a vanilla integrated server; the repository's Paper/plugin bridge at ws://127.0.0.1:8765 is not the connection used for this world and may not be running.

Connection that is known to work

The current Mineflayer release does not negotiate this 26.2 session correctly. The verified workaround is Mineflayer 26.1 with protocol version 776 forced in the custom auth callback. Use a username of 16 characters or fewer.

From a temporary helper directory (do not add the helper or its dependencies to the repository):

mkdir -p /tmp/claude-minecraft-lan
cd /tmp/claude-minecraft-lan
npm init -y
npm install [email protected] prismarine-nbt

Create a small .mjs helper with this connection setup:

import mineflayer from 'mineflayer'

const bot = mineflayer.createBot({
  host: '127.0.0.1',
  port: 5056,
  version: '26.1',
  username: 'ClaudeLAN',
  auth: (client, options) => {
    client.username = 'ClaudeLAN'
    client.uuid = '00000000-0000-0000-0000-000000000020'
    options.auth = 'offline'
    options.protocolVersion = 776
    options.connect(client)
  }
})

const wait = ms => new Promise(resolve => setTimeout(resolve, ms))

bot.once('spawn', async () => {
  await bot.waitForChunksToLoad()
  bot.chat('/save-all flush')
  await wait(1500)
  // Work here. Commands are sent with bot.chat('/...').
})

bot.on('error', error => console.error(error.message))
bot.on('kicked', reason => console.error('KICKED', reason))

The protocol shim can emit harmless partial packet warnings while still connecting successfully. A successful spawn event is the meaningful test. If the server rejects the login with a serverbound/minecraft:hello decoder error, check that the username is at most 16 characters and that the exact version: '26.1' plus options.protocolVersion = 776 workaround is present.

Read the full file on GitHub · 121 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. 4d ago First seen · 121 lines · 1,095 tokens per session scan A e512be346f26

Subscribe to this mod's changes

minecraft-mcp CLAUDE.md is an instructions file published in the GitHub repository IotA-asce/minecraft-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 1,095 tokens to every session, about $0.0055 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 2026-09-05.

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 · 5,153 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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens