CleanSlice

Architecture docs and patterns for NestJS + Nuxt full-stack apps

我该使用它吗

质量与安全性

B
描述质量
100%
模式完整度
63%
命名质量
77%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

发现(3)

  • LOWTool 'get-started' doesn't follow camelCase/snake_case在 get-started 中
  • LOWTool 'list-categories' doesn't follow camelCase/snake_case在 list-categories 中
  • LOWTool 'read-doc' doesn't follow camelCase/snake_case在 read-doc 中

基于对工具定义和协议合规性的自动分析。

上下文开销

~565token 数(工具定义)
~1.2 KB典型响应大小
对注意力的影响极小(占 128k 上下文窗口的 0.44%)

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中:

{
  "mcpServers": {
    "mcp": {
      "url": "https://mcp.cleanslice.org/mcp"
    }
  }
}

远程端点

https://mcp.cleanslice.org/mcpstreamable-http

它能做什么

工具清单

工具(4)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢get-started

⚠️ CRITICAL: request this tool first before creating any code! Returns essential slice creation rules. READ THIS FIRST before creating any slices! Contains the MOST IMPORTANT naming rule: ALWAYS use SINGULAR names (user/ not users/).

输入模式

{
  "type": "object",
  "properties": {},
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢list-categories

List all available documentation categories. Use this to discover what categories are available before searching.

输入模式

{
  "type": "object",
  "properties": {},
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢search(query, framework, sliceName, phase, feature, ...)

Search for relevant documentation. Use `list-categories` first to see available categories. Filter by query text, framework, phase, feature, category, or tags. Returns documents sorted by relevance.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Search query text (searches in document names, descriptions, and keywords)"
    },
    "framework": {
      "type": "string",
      "description": "Framework identifier (e.g., nestjs, nuxt)"
    },
    "sliceName": {
      "type": "string",
      "description": "Name of the slice to find documentation for"
    },
    "phase": {
      "type": "string",
      "enum": [
        "initialization",
        "setup",
        "implementation",
        "testing",
        "deployment"
      ],
      "description": "Development phase to filter by"
    },
    "feature": {
      "type": "string",
      "description": "Feature name (e.g., authentication, user-management, file-upload)"
    },
    "workingOn": {
      "type": "string",
      "enum": [
        "api",
        "app",
        "admin",
        "full-stack"
      ],
      "description": "Which application you are currently working on"
    },
    "category": {
      "type": "string",
      "description": "Category filter (e.g., quickstart, pattern, best-practices)"
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Array of tags to filter by"
    },
    "limit": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "description": "Max results to return (default: 5)"
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "description": "Number of results to skip for pagination (default: 0)"
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢read-doc(path)

Read the full content of a specific document by path. Use this after `search` to get the complete document when snippets are not enough.

输入模式

{
  "type": "object",
  "properties": {
    "path": {
      "type": "string",
      "description": "Document path from search results"
    }
  },
  "required": [
    "path"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

社区

评价此服务器

证据

最近观测

已验证未记录版本4 个工具
已验证未记录版本4 个工具
已验证未记录版本4 个工具