Datapack MCP Server
Validates Minecraft datapack JSON files (recipes, advancements, loot tables, etc.) against official Minecraft data formats using Spyglass.
README
Datapack MCP Server
[!WARNING] This project was created using GitHub Copilot Chat's Agent mode. Please use with caution and verify the functionality thoroughly.
MCP (Model Context Protocol) Server for validating Minecraft datapack JSON files using Spyglass.
This server allows AI agents to validate Minecraft datapack JSON files (recipes, advancements, loot tables, predicates, etc.) against the official Minecraft data formats.
Features
- ✅ Validates datapack JSON files using Spyglass' mcdoc type system
- 🎯 Supports all datapack JSON types (recipes, advancements, loot tables, predicates, etc.)
- 🔄 Supports any Minecraft version or pack format
- 🚀 Easy to use with MCP-compatible AI agents
Installation
Using npx (Recommended)
You can run this server directly from GitHub without installing:
npx github:sharo-jef/datapack-mcp-server
Local Installation
git clone https://github.com/sharo-jef/datapack-mcp-server.git
cd datapack-mcp-server
npm install
npm run build
Usage
With Claude Desktop
Add to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"datapack-validator": {
"command": "npx",
"args": ["-y", "github:sharo-jef/datapack-mcp-server"]
}
}
}
Or if you have it installed locally:
{
"mcpServers": {
"datapack-validator": {
"command": "node",
"args": [
"--experimental-strip-types",
"/path/to/datapack-mcp-server/src/index.ts"
]
}
}
}
With Other MCP Clients
Any MCP-compatible client can connect to this server using stdio transport.
Tool: validate_datapack_json
Validates Minecraft datapack JSON files.
Parameters
type(required): The type of datapack file- Supported types:
advancement,loot_table,predicate,item_modifier,recipe,text_component,chat_type,damage_type,dialog,dimension,dimension_type,worldgen/biome,worldgen/carver,worldgen/configured_feature,worldgen/placed_feature,worldgen/density_function,worldgen/noise,worldgen/noise_settings,worldgen/structure,worldgen/structure_set,worldgen/template_pool,tags/block,tags/item,tags/entity_type,tags/function
- Supported types:
content(required): The JSON content to validate (as a string, must be valid JSON parseable by JSON.parse)version(optional): Minecraft version (e.g.,1.21.11)packFormat(optional): Data pack format number (e.g.,48for 1.21.4-1.21.11)- Prefer
packFormatoverversionwhen available - it is more precise as multiple Minecraft versions can share the same pack format
- Prefer
Note: Either version or packFormat must be specified.
Example Usage
// Example request from an AI agent
{
"type": "recipe",
"content": "{\"type\":\"minecraft:crafting_shaped\",\"pattern\":[\"###\",\"# #\",\"###\"],\"key\":{\"#\":{\"item\":\"minecraft:stick\"}},\"result\":{\"item\":\"minecraft:chest\"}}",
"version": "1.21.11"
}
Response
Valid JSON:
✓ Valid recipe JSON for Minecraft 1.21.11
Invalid JSON:
✗ Invalid recipe JSON:
error 1:1 Unknown property 'invalid_field'
error 5:10 Expected string, got number
Development
Build
npm run build
Watch Mode
npm run dev
Run Locally
npm start
Test
npm test
Technical Details
This server uses:
- Spyglass: For JSON validation against Minecraft's mcdoc type system
- MCP SDK: For Model Context Protocol support (@modelcontextprotocol/sdk)
- TypeScript: Native execution in Node.js v20.10.0+
The validation logic is based on misode/misode.github.io's Spyglass integration.
License
This project is licensed under the MIT License - see the LICENSE file for details.
This project includes code based on misode/misode.github.io, which is also licensed under the MIT License.
Credits
- Spyglass - The validation engine
- misode - For mcmeta data and Spyglass integration code
- Model Context Protocol - MCP specification
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。