Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/rice-awa/mc-mcp-serverWrote 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/rules/rice-awa/mc-mcp-server/project-rule)<a href="https://agentmods.dev/rules/rice-awa/mc-mcp-server/project-rule"><img src="https://agentmods.dev/badge/rules/rice-awa/mc-mcp-server/project-rule/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/rules/rice-awa/mc-mcp-server/project-rule"><img src="https://agentmods.dev/badge/rules/rice-awa/mc-mcp-server/project-rule.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 | $0.00010 | $0.00813 |
| Opus 5.5 | $0.00004 | $0.00325 |
| Sonnet 5.5 | $0.00002 | $0.00163 |
| Haiku 4.5 | $0.00001 | $0.00081 |
Grade A, and why
project-rule 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 1mo 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.
What it actually says
Minecraft MCP服务器文档索引
项目概述
Minecraft MCP服务器是一个集成系统，由两个核心组件组成：AIAgent(MCP-server)负责管理AI工具和处理LLM交互，以及基于WebSocket和脚本API的MC服务器负责处理游戏交互。系统支持两种请求路径：外部MCP客户端调用和游戏内聊天监听。
文档目录
1. 项目需求文档
- 项目需求描述文档 (PRD) - 详细描述项目的核心功能、请求路径、用户交互流程和验收标准
2. 技术规范文档
- 技术架构文档 - 描述系统的整体架构、核心组件和技术栈
- WebSocket通信规范 - 定义客户端与服务器之间的WebSocket通信协议和脚本API集成
- MCP集成规范 - 说明如何集成Model Context Protocol标准和两种请求路径
- development_guidelines.md - 开发的边界限制
3. 外部参考文档
- MCP Python SDK - Model Context Protocol的Python实现参考
- Minecraft脚本API文档 - Minecraft脚本API官方文档
系统组件
- AIAgent (mc-server) - 基于WebSocket和脚本API的服务器，处理游戏交互
- MCP服务器 - 负责管理AI工具和处理LLM交互，通过MCP前端服务器实现外部MCP客户端的访问
请求路径
-
外部MCP客户端路径 - 外部MCP客户端通过AIAgent与Minecraft交互
-
游戏内聊天路径 - 玩家通过游戏内聊天触发AIAgent
项目结构规范
mc-mcp-server/
├── server/
│ ├── __init__.py
│ ├── mc_server.py # WebSocket服务器实现
│ ├── agent_server.py # Agent服务器实现
│ └── utils/
│ ├── __init__.py
│ ├── auth.py # 认证相关工具
│ ├── llm.py # 大语言模型调用工具
│ └── logging.py # 日志工具
│
├── resources/ # MCP资源定义
│ ├── __init__.py
│ ├── player.py
│ └── world.py
├── tools/ # MCP工具定义
│ ├── __init__.py
│ ├── commands.py
│ └── messages.py
├── config/ # 配置文件
│ ├── default.json
│ └── production.json
├── tests/ # 测试目录
│ ├── __init__.py
│ ├── test_mc_server.py
│ └── test_mcp_server.py
├── docs/ # 文档目录
├── main.py # 主入口文件
├── mcp_frontend_server.py # MCP服务器前端
├── requirements.txt # 依赖声明
└── README.md # 项目说明
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.
- 1mo ago First seen · 76 lines · 10 tokens per session scan A 33a26a685250
project-rule is a cursor rule published in the GitHub repository rice-awa/mc-mcp-server (4 stars, last pushed 1y ago), licensed MIT. It adds 10 tokens to every session and 813 once invoked, about $0.0000 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.
Other cursor rules, from other repositories
performance-optimization
A guide to improving the speed and responsiveness of frontend applications.
ddd-design-guide
Apply when designing or refactoring domain models, services, stores, or discussing DDD (Domain-Driven Design) architecture. Also apply when working on business logic layers, API modules, or planning domain boundaries and migrations.
spec-for-ut
Unit testing is essential to ensure the reliability and stability of code, especially for React components and functions. Adhering to best practices and ensuring high test coverage is critical to maintaining a robust codebase.
instruct-ut
A rule for turning a user's goal into a to-do list and carrying out the tasks in order. It describes a step-by-step way to organize requested work.
git_workflow
Git Workflow and Configuration for AGB SDK.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.