AIBase
EN
Explore
Cupertino
C

Cupertino

Cupertino is a Swift - based localization tool used to crawl, index, and provide Apple developer documentation to AI agents through the Model Context Protocol (MCP). It supports offline access to over 230,000 pages of Apple platform documentation, Swift proposals, design guidelines, and sample code, and enables fast retrieval through the SQLite FTS5 search engine.
Developer toolsSearch tools#Apple Documentation#Local Search#AI Assistant#Offline Development.swift
2.5 points
6.0K
Open Site

Overview

Installation

Content Details

Alternatives

What is Cupertino?

Cupertino is a local Apple documentation system designed specifically for AI assistants. It can automatically crawl, index, and store Apple's official developer documentation offline. Then, through the Model Context Protocol (MCP), AI assistants like Claude can accurately query Apple API information, avoiding AI hallucination issues.

How to use Cupertino?

Cupertino offers three usage methods: 1) One - click installation to download a pre - built database (the fastest, about 30 seconds); 2) Stream - build from GitHub (about 45 minutes); 3) Full manual crawling (about 20 - 48 hours). After installation, configure Claude Desktop to start using it.

Applicable scenarios

Cupertino is most suitable for the following scenarios: 1) When you need to consult Apple documentation during offline development; 2) When you want AI assistants to provide accurate Apple API information; 3) When you need to quickly search for Swift Evolution proposals; 4) When you are researching Apple design guidelines and best practices; 5) When you are looking for official sample code and implementation solutions.

Main Features

Multi - source documentation crawling
Supports 7 types of documentation sources, including Apple developer documentation (over 234,000 pages), Swift Evolution proposals, Swift.org documentation, Swift package metadata, Apple sample code, Apple Archive historical guidelines, and Human Interface Guidelines.
Full - text search engine
Fast search based on SQLite FTS5 and BM25 ranking, supporting stemming (e.g., 'running' matches 'run'), framework filtering, and platform version filtering. The query response time is less than 100ms.
MCP protocol integration
Provides documentation access capabilities for AI assistants through the Model Context Protocol, supporting tool calls such as search_docs, search_hig, list_frameworks, and read_document.
Fully offline access
All documentation is stored locally and can be used without an internet connection. It includes complete documentation for 287 frameworks, totaling 234,331 pages.
Sample code search
Indexes 606 official Apple sample projects and supports full - text search across more than 18,000 Swift files. You can directly view the project README and source code.
Pre - built databases
Provides a pre - built documentation database that can be downloaded with one click and installed within 30 seconds, eliminating the need for long - term crawling. It includes a Swift package directory (9,699 packages) and a sample code directory.
Advantages
Eliminate AI hallucination: Provide accurate Apple API documentation for AI assistants to avoid misinformation.
Offline development: Access complete documentation even in a network - free environment.
Deterministic search: The same query always returns the same result, which is reproducible.
Local control: Have full control over your own documentation data, and you can check the database and customize workflows.
AI - first design: Optimized specifically for AI assistant integration and seamlessly connected through the MCP protocol.
Fast installation: The pre - built database can be installed in 30 seconds without long - term waiting.
Limitations
Only supports macOS 15+: Requires the latest macOS system.
Long initial crawling time: Full crawling takes 20 - 48 hours (but the pre - built database can avoid this issue).
High disk space requirement: The complete documentation requires approximately 2 - 3GB of storage space.
Documentation update delay: Manual updates are required to obtain the latest documentation.
Limited to the Apple platform: Focuses on the Apple ecosystem and does not include documentation for other platforms.

How to Use

Install Cupertino
Choose the installation method that suits you best. It is recommended to use the one - click installation command, which is the fastest and simplest.
Download the documentation database
Use the setup command to download the pre - built documentation database. This is the fastest way.
Configure Claude Desktop
Edit the Claude Desktop configuration file and add Cupertino as the MCP server.
Restart and start using
Restart Claude Desktop. Now you can ask Claude questions about Apple - related technologies.

Usage Examples

SwiftUI development query
When developing a SwiftUI application, you need to query the usage method of specific components.
Research on Swift language features
Understand new language features in Swift Evolution proposals.
Consultation of design specifications
When designing an iOS application, you need to refer to Apple's design guidelines.
Search for sample code
You need to find official implementation examples for specific functions.
API availability check
Check the minimum system version supported by an API.

Frequently Asked Questions

Does Cupertino require an internet connection?
Why does it take so long to crawl the documentation?
Which AI assistants are supported?
How to update the documentation?
Can it be used on non - macOS systems?
Where is the documentation data stored?
Can I download documentation for specific frameworks only?
How to check if the server is running normally?

Related Resources

GitHub Repository
The source code and latest version of Cupertino
Demo Video
Function demonstration and usage tutorial of Cupertino
Model Context Protocol Official Website
Official documentation and specifications of the MCP protocol
PulseMCP List
Server list on PulseMCP
LobeHub List
Server list on LobeHub
Issue Feedback
Submit issues and feature requests
Discussion Area
Discuss usage experiences and tips with other users

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "cupertino": {
      "command": "/usr/local/bin/cupertino",
      "args": ["serve"]
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

R
Rsdoctor
Rsdoctor is a build analysis tool specifically designed for the Rspack ecosystem, fully compatible with webpack. It provides visual build analysis, multi - dimensional performance diagnosis, and intelligent optimization suggestions to help developers improve build efficiency and engineering quality.
TypeScript
8.6K
5 points
N
Next Devtools MCP
The Next.js development tools MCP server provides Next.js development tools and utilities for AI programming assistants such as Claude and Cursor, including runtime diagnostics, development automation, and document access functions.
TypeScript
9.3K
5 points
T
Testkube
Testkube is a test orchestration and execution framework for cloud-native applications, providing a unified platform to define, run, and analyze tests. It supports existing testing tools and Kubernetes infrastructure.
Go
5.7K
5 points
M
MCP Windbg
An MCP server that integrates AI models with WinDbg/CDB for analyzing Windows crash dump files and remote debugging, supporting natural language interaction to execute debugging commands.
Python
10.6K
5 points
R
Runno
Runno is a collection of JavaScript toolkits for securely running code in multiple programming languages in environments such as browsers and Node.js. It achieves sandboxed execution through WebAssembly and WASI, supports languages such as Python, Ruby, JavaScript, SQLite, C/C++, and provides integration methods such as web components and MCP servers.
TypeScript
9.7K
5 points
N
Netdata
Netdata is an open-source real-time infrastructure monitoring platform that provides second-level metric collection, visualization, machine learning-driven anomaly detection, and automated alerts. It can achieve full-stack monitoring without complex configuration.
Go
10.3K
5 points
M
MCP Server
The Mapbox MCP Server is a model context protocol server implemented in Node.js, providing AI applications with access to Mapbox geospatial APIs, including functions such as geocoding, point - of - interest search, route planning, isochrone analysis, and static map generation.
TypeScript
8.2K
4 points
U
Uniprof
Uniprof is a tool that simplifies CPU performance analysis. It supports multiple programming languages and runtimes, does not require code modification or additional dependencies, and can perform one-click performance profiling and hotspot analysis through Docker containers or the host mode.
TypeScript
7.4K
4.5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
19.3K
4.5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
31.7K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
22.4K
4.3 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
66.7K
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
29.2K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
61.0K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
21.1K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
45.3K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
English简体中文繁體中文にほんご
© 2026AIBase