Duck Framework MCP

Official Duck Framework MCP server for AI-assisted development and project scaffolding.

我该使用它吗

质量与安全性

A
描述质量
95%
模式完整度
63%
命名质量
92%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

发现(2)

  • LOWTool 'get_blueprint_locations' description lacks action verb在 get_blueprint_locations 中
  • LOWTool 'get_project_structure' description lacks action verb在 get_project_structure 中

基于对工具定义和协议合规性的自动分析。

上下文开销

~1,126token 数(工具定义)
~284 B典型响应大小
对注意力有中等影响(占 128k 上下文窗口的 0.88%)

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": {
    "duckframework-mcp": {
      "url": "https://duckframework.com/mcp"
    }
  }
}

远程端点

https://duckframework.com/mcpstreamable-http

它能做什么

工具清单

工具(13)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢fetch_ai_guide(guide)

Fetch an official Duck Framework AI guide. Use this after get_ai_guides() to retrieve the full guide content for AI-assisted Duck Framework development. Always read the relevant guide before generating code instead of relying on memory.

输入模式

{
  "type": "object",
  "properties": {
    "guide": {
      "type": "string"
    }
  },
  "required": [
    "guide"
  ]
}
🟢get_ai_guides

List available Duck Framework AI guides. Use this to discover available guides before fetching one with fetch_ai_guide(). Returns guide identifiers and their descriptions.

输入模式

{
  "type": "object",
  "properties": {},
  "required": []
}
🟢get_blueprint_locations

Explain where Duck Framework blueprints can be located. Describes the supported blueprint layouts and when each organization approach is appropriate.

输入模式

{
  "type": "object",
  "properties": {},
  "required": []
}
🟢get_blueprint_structure

Return the standard internal structure of a Duck Framework blueprint. Use this before generating a new blueprint or adding files to an existing one to understand where components, pages, templates, automations, and views belong.

输入模式

{
  "type": "object",
  "properties": {},
  "required": []
}
🟢get_component_api(component_name)

Look up a built-in Duck Framework component API. Returns the confirmed import path, container type, and supported keyword arguments for a component without requiring the full HTML components guide to be loaded. Use this before using any component that has not already been confirmed. Returns close-name suggestions when the component does not exist.

输入模式

{
  "type": "object",
  "properties": {
    "component_name": {
      "type": "string"
    }
  },
  "required": [
    "component_name"
  ]
}
🟢get_project_structure

Return the standard Duck Framework project directory structure. Use this before creating or modifying projects to understand where files and directories belong.

输入模式

{
  "type": "object",
  "properties": {},
  "required": []
}
🟢lint_component_code(code)

Check Duck Framework component or page code for common mistakes. Detects known patterns such as incorrect component imports, invalid page imports, incorrect Heading usage, leading-underscore method names, and separator comments. This is a pattern check for known issues, not a complete correctness validator. An empty result only means no known issues were detected. Run this on generated component code before presenting it as final.

输入模式

{
  "type": "object",
  "properties": {
    "code": {
      "type": "string"
    }
  },
  "required": [
    "code"
  ]
}
🟢list_doc_categories(version)

List all Duck Framework documentation categories and their pages. Use this when browsing available documentation without a specific search query.

输入模式

{
  "type": "object",
  "properties": {
    "version": {
      "type": "string"
    }
  },
  "required": []
}
🟡plan_feature(request, version)

Analyze a Duck Framework feature request and create an implementation plan. Returns relevant documentation to read and a suggested order of operations before writing code. Use this before implementing non-trivial Duck Framework features.

输入模式

{
  "type": "object",
  "properties": {
    "request": {
      "type": "string"
    },
    "version": {
      "type": "string"
    }
  },
  "required": [
    "request"
  ]
}
⚪reindex_docs(version)

Rebuild the Duck Framework documentation index. Crawls the live documentation sitemap for a given version and merges the result in: curated tags/summary/category are preserved, new pages are added, and pages no longer in the sitemap are removed. Requires the admin scope.

输入模式

{
  "type": "object",
  "properties": {
    "version": {
      "type": "string"
    }
  },
  "required": []
}
🟡scaffold_blueprint(blueprint_name, urlpatterns, enable_template_dir, enable_static_dir, prepend_name_to_urls)

Scaffold a new Duck Framework blueprint. Generates a blueprint structure containing blueprint.py, views.py, and optional UI, template, and static directories following the documented Duck blueprint conventions. Returns generated file contents and the settings configuration needed to register the blueprint. This tool does not write files.

输入模式

{
  "type": "object",
  "properties": {
    "blueprint_name": {
      "type": "string"
    },
    "urlpatterns": {
      "type": "string"
    },
    "enable_template_dir": {
      "type": "string"
    },
    "enable_static_dir": {
      "type": "string"
    },
    "prepend_name_to_urls": {
      "type": "string"
    }
  },
  "required": [
    "blueprint_name"
  ]
}
🟡scaffold_project(project_name, features)

Scaffold a new Duck Framework project. Returns the required CLI commands and generated file contents for supported features with confirmed APIs. Unsupported features return documentation guidance instead of generated code to avoid guessing framework APIs. This tool does not write files. It only returns generated content for the calling client to add to the user's project directory.

输入模式

{
  "type": "object",
  "properties": {
    "project_name": {
      "type": "string"
    },
    "features": {
      "type": "string"
    }
  },
  "required": [
    "project_name"
  ]
}
🟢search_docs(query, top_k, category, version)

Fuzzy-search the Duck Framework documentation. Use this whenever the correct documentation page for a feature is unknown. Returns ranked matches containing title, URL, category, summary, and relevance score.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string"
    },
    "top_k": {
      "type": "string"
    },
    "category": {
      "type": "string"
    },
    "version": {
      "type": "string"
    }
  },
  "required": [
    "query"
  ]
}

社区

评价此服务器

证据

最近观测

已验证未记录版本13 个工具