
Minecraft MCP Bot
Enables AI assistants to control a Minecraft bot through natural language commands using the Mineflayer library. Provides intelligent pathfinding, chat communication, entity detection, and generic access to Minecraft bot capabilities.
README
Minecraft MCP Bot
A Model Context Protocol (MCP) server that provides programmatic control of a Minecraft bot using the Mineflayer library. This project enables AI assistants to interact with Minecraft through a clean, extensible interface.
Project Goals
- AI-Controlled Minecraft Bot: Create an intelligent bot that can be controlled through natural language commands via MCP
- Full Mineflayer API Access: Provide comprehensive access to Minecraft bot capabilities through a generic command interface
- Intelligent Navigation: Implement pathfinder-based movement for precise, obstacle-aware navigation
- Extensible Architecture: Build a modular system that can be easily extended with new capabilities
- Training Environment: Establish a safe, flat-world testing ground for bot behavior development
- Clean Integration: Seamless integration with VS Code and AI assistants through MCP protocol
Features
Current Capabilities
- Generic Command Interface: Execute any Mineflayer bot command with flexible parameter handling
- Intelligent Pathfinding: Navigate to specific coordinates with obstacle avoidance
- Chat Communication: Send messages and interact with players
- Entity Detection: Scan for and interact with nearby players, mobs, and objects
- Flexible Movement: Both manual control states and intelligent pathfinding options
- Safe Testing Environment: Operates in a flat world to prevent terrain-related issues
Tools Available
execute-bot-command
: Generic interface for all Mineflayer API functionspathfind-to-position
: Intelligent navigation to specific coordinates
Technical Stack
- Mineflayer: Core Minecraft bot library
- MCP SDK: Model Context Protocol server implementation
- Pathfinder: Intelligent navigation and movement
- Zod: Schema validation for tool parameters
- Node.js: Runtime environment
Getting Started
Prerequisites
- Node.js (v20+)
- Minecraft server (configured for flat world)
- VS Code with MCP extension
Installation
npm install
Configuration
- Update server connection details in
index.js
- Configure MCP in VS Code settings (
.vscode/mcp.json
) - Ensure Minecraft server is running with flat world generation
Running
node index.js
Development
Branch Structure
main
: Stable, production-ready codeadd-pathfinder
: Pathfinding integration development- Feature branches for new capabilities
Contributing
- Create feature branches for new development
- Test thoroughly in flat world environment
- Ensure clean integration with existing MCP tools
- Commit incremental changes with clear messages
Future Enhancements
- Building and Construction: Block placement and structure creation
- Inventory Management: Item handling and crafting capabilities
- Advanced AI Behaviors: Complex task execution and planning
- Multi-Bot Coordination: Manage multiple bots simultaneously
- Real-World Integration: Connect to live Minecraft servers safely
Security Considerations
⚠️ IMPORTANT SECURITY WARNING ⚠️
This project currently provides unrestricted access to the Mineflayer API through the generic command interface. This means:
- Any Mineflayer command can be executed without validation or restrictions
- The LLM has full bot control including potentially destructive actions
- No command filtering or sandboxing is currently implemented
- Suitable for trusted environments only (local testing, controlled servers)
Current Risk Level: HIGH
- ✅ Safe for: Local development, private servers, controlled testing
- ❌ NOT safe for: Public servers, untrusted environments, production use
- 🔥 It could set your world on fire. 🔥
Recommended Security Improvements (Future Development)
- Command Whitelist: Restrict available commands to approved set
- Parameter Validation: Strict validation of command parameters
- Action Limits: Rate limiting and scope restrictions
- Audit Logging: Track all executed commands
- Permission System: Granular control over bot capabilities
- Safe Mode: Default to restricted command set
Architecture Philosophy
This project emphasizes:
- Simplicity: Clean, minimal codebase with focused functionality
- Flexibility: Generic interfaces that adapt to diverse use cases
- Controlled Testing: Safe environment for development and experimentation
- Extensibility: Modular design for easy capability expansion
- Security Awareness: Recognizing and documenting security implications
推荐服务器

Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。