Apple Deep Docs MCP
Provides comprehensive access to Apple's development documentation ecosystem including hidden Xcode docs, Swift Evolution proposals, GitHub repositories, and WWDC session notes. Enables developers to search and retrieve advanced Apple development resources not available through public channels.
README
Apple Deep Docs MCP
Access hidden Xcode documentation and Apple developer resources through the Model Context Protocol.
Overview
This MCP server provides comprehensive access to Apple's development documentation ecosystem, including:
- Hidden Xcode Documentation: Searches the
AdditionalDocumentationfolder inside Xcode.app containing advanced SwiftUI patterns, Liquid Glass design guides for iOS 26+, and framework-specific implementation details not available on Apple's public developer site - Apple Developer API: Fetches and parses structured documentation from developer.apple.com
- Swift Evolution Proposals: Searches 500+ proposals to understand the "why" behind language features
- Swift Open Source Repositories: Searches across all Apple/SwiftLang GitHub repositories for implementation examples
- WWDC Session Notes: Accesses community-curated WWDC session summaries for performance optimization and architecture patterns
Requirements
- Python 3.10+
- Xcode installed (for local documentation features)
Installation
- Clone this repository:
git clone https://github.com/yourusername/appledeepdocs-mcp.git
cd appledeepdocs-mcp
- Set up the Python environment:
# Create virtual environment
python3 -m venv venv
# Install dependencies
./venv/bin/pip install fastmcp
Configuration
Add to your Claude Desktop config file:
{
"mcpServers": {
"apple-deep-docs": {
"command": "/path/to/appledeepdocs-mcp/run.sh"
}
}
}
Replace /path/to/appledeepdocs-mcp with the full path where you cloned this repository. The run.sh script automatically handles the virtual environment.
Config file locations:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
After updating the config, restart Claude Desktop to load the MCP server.
Project Structure
├── main.py # Entry point for the MCP server
├── config.py # Configuration and Xcode path discovery
├── tools.py # MCP tool definitions and input validation
├── docs/ # Documentation access modules
│ ├── local_docs.py # Xcode's hidden local documentation
│ └── apple_docs.py # Apple Developer website API access
├── evolution/ # Swift language evolution
│ └── swift_evolution.py
├── repos/ # GitHub repository searching
│ └── swift_repos.py
├── suggestions/ # Intelligent suggestion system
│ └── suggestions.py # Centralized suggestion engine
├── wwdc/ # WWDC session resources
│ └── wwdc_notes.py
└── pyproject.toml # Package configuration
Available Tools
Local Documentation
search_docs- Search Xcode's hidden documentationget_document- Retrieve full content of a specific documentlist_documents- List all available documentation filesget_xcode_versions- Get installed Xcode versions with documentation
Apple Developer Resources
fetch_apple_documentation- Fetch structured docs from developer.apple.comsearch_apple_online- Search both local and online Apple documentationget_framework_info- Get direct documentation URL for any framework
Swift Evolution
search_swift_evolution- Search Swift Evolution proposalsget_swift_evolution_proposal- Get details of a specific proposal
GitHub Resources
search_swift_repos- Search across all Apple/SwiftLang repositoriesfetch_github_file- Fetch source code from GitHub repositories
WWDC Resources
search_wwdc_notes- Search WWDC session notes and transcriptsget_wwdc_session- Get WWDC session URLs from session ID
Environment Variables
XCODE_DOC_PATH: Override default Xcode documentation search path
License
MIT
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。