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.
curl -O https://raw.githubusercontent.com/IotA-asce/minecraft-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/IotA-asce/minecraft-mcpWrote 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.
[](https://agentmods.dev/instructions/iota-asce/minecraft-mcp/claude-md)<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.
<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>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 | $0.01095 | $0.01095 |
| Opus 5.5 | $0.00438 | $0.00438 |
| Sonnet 5.5 | $0.00219 | $0.00219 |
| Haiku 4.5 | $0.00110 | $0.00110 |
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 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.
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.
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 · 121 lines · 1,095 tokens per session scan A e512be346f26
minecraft-mcp CLAUDE.md is an instructions file published in the GitHub repository IotA-asce/minecraft-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,095 tokens to every session, about $0.0044 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 2026-09-05.
minecraft-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| minecraft-mcp CLAUDE.mdIotA-asce/minecraft-mcp | Instructions file | 0 | 2mo ago | MIT | A | 1,095 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 8,130 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 283k | today | MIT | A | 4,342 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |