MCP ServerHTTPOfficialv2.9.0

Apple Rag MCP Server

Search Apple's official documentation, WWDC transcripts, and code examples using semantic, keyword, and hybrid search with AI reranking. Built for iOS/macOS developers who need fast, accurate answers from Apple's developer resources.

com.apple-rag/mcp-server

Hosted URL

https://mcp.apple-rag.com

Transport

HTTP

Auth

No auth required

Apple Rag repository at a glance

Live signal from GitHub, refreshed weekly.

Stars

121

Last commit

Apr 28, 2026

License

MIT

Language

TypeScript

What the Apple Rag MCP server does

How models use it and what it is built for.

Search Apple's official documentation, WWDC transcripts, and code examples using semantic, keyword, and hybrid search with AI reranking. Built for iOS/macOS developers who need fast, accurate answers from Apple's developer resources.

Connect to Apple Rag

Hosted endpoint โ€” paste into any MCP client.

https://mcp.apple-rag.com

Resources

Where to find authoritative docs and source for Apple Rag.

Example prompts for Apple Rag

Paste any of these into Agent Studio after connecting Apple Rag.

  • Search for SwiftUI state management best practices and show me code examples
  • Find documentation on implementing Core Data migrations for iOS apps
  • What WWDC sessions cover async/await patterns in Swift? Show me transcripts
  • Search for visionOS spatial computing APIs and their usage examples

Documentation from project README

View on GitHub

Excerpted from the project's README โ€” boilerplate sections (license, changelog, contributing) omitted for clarity.

The Apple docs MCP your AI actually deserves.

Apple docs. WWDC transcripts. Semantic + keyword + hybrid search. One clean tool.

Install MCP Server

Install in VS Code Install in VS Code Insiders

๐ŸŒ Website โ€ข ๐Ÿ“Š Dashboard

English | ไธญๆ–‡


Not Just Another Docs Tool

Others give you keyword search. We give you that, plus semantic understanding, plus AI-powered hybrid search that combines both intelligently. Every search mode you need, working together.

Minimal footprint. Maximum signal. Our MCP tools are designed to be leanโ€”no bloated responses, no wasted tokens, no noise cluttering your agent's context. Just the information that matters.


Start in Seconds

One click:

Install MCP Server

Install in VS Code Install in VS Code Insiders

Click the button above and your editor will automatically configure everything for you in seconds.

Option 2: Manual Setup for Other MCP Clients

JSON Configuration (Copy & Paste):

{
  "mcpServers": {
    "apple-rag-mcp": {
      "url": "https://mcp.apple-rag.com"
    }
  }
}

Manual Configuration Parameters:

  • MCP Type: Streamable HTTP
  • URL: https://mcp.apple-rag.com
  • Authentication: Optional (MCP Token for higher limits)
  • MCP Token: Get yours at apple-rag.com for increased quota

Supported Clients: Cursor, Claude Desktop, Cline, and all MCP-compatible tools.

Note: No MCP Token required to start! You get free queries without any authentication. Add an MCP Token later for higher usage limits.

๐ŸŒŸ Why Developers Love Apple RAG MCP

โšก Fast & Reliable

Get quick responses with our optimized search infrastructure. No more hunting through docs.

๐ŸŽฏ AI-Powered Hybrid Search

Advanced search technology combining Semantic Search for RAG, Keyword Search, and Hybrid Search with vector similarity and technical term matching provides accurate, contextual answers from Apple's documentation.

๐Ÿ”’ Always Secure

MCP authentication ensures trusted access for your AI agents with enterprise-grade security.

๐Ÿ“ Code Examples

Get practical code examples in Swift, Objective-C, and SwiftUI alongside documentation references.

๐Ÿ”„ Real-time Updates

Our documentation index is continuously updated to reflect the latest Apple developer resources.

๐Ÿ†“ Completely Free

Start immediately with no MCP Token required. Get an MCP Token for higher usage limits - all managed at apple-rag.com.

๐ŸŽฏ Features

  • ๐Ÿ” Semantic Search for RAG - Vector similarity with semantic understanding for intelligent retrieval
  • ๐Ÿ”Ž Keyword Search - Precise technical term matching for API names and specific terminology
  • ๐ŸŽฏ Hybrid Search - Combined semantic and keyword search with AI reranking for optimal results
  • ๐Ÿ“š Complete Coverage - iOS, macOS, watchOS, tvOS, visionOS documentation
  • ๐ŸŽฌ WWDC Videos - Full transcripts from Apple Developer videos and WWDC sessions
  • โšก Fast Response - Optimized for speed across all content types
  • ๐Ÿš€ High Performance - Multi-instance cluster deployment for maximum throughput
  • ๐Ÿ”„ Always Current - Synced with Apple's latest docs and video content
  • ๐Ÿ›ก๏ธ Secure & Private - Your queries stay private
  • ๐ŸŒ Universal MCP - Works with any MCP-compatible client

๐Ÿง  Agent Skill

We provide an Agent Skill that teaches AI agents how to use this MCP server effectively โ€” including query best practices, search-then-fetch workflow, result completeness handling, and rate limit guidance.

Install: Copy the skills/apple-dev-docs/ directory to your agent's skill location:

Platform Destination
Cursor ~/.cursor/skills/apple-dev-docs/
Codex ~/.codex/skills/apple-dev-docs/

Once installed, your AI agent will automatically know when and how to use Apple RAG MCP for Apple development questions.

Continue reading on GitHub

Apple Rag MCP server โ€” FAQ

Common questions about connecting and running Apple Rag.

  • What documentation does this MCP server cover?

    It indexes iOS, macOS, watchOS, tvOS, and visionOS official Apple documentation, plus full transcripts from WWDC videos and Apple Developer sessions. The index is continuously updated to reflect the latest Apple resources.

  • Do I need authentication to use Apple RAG MCP?

    Noโ€”you can start immediately with free queries and no MCP Token required. Add an MCP Token from apple-rag.com later if you need higher usage limits.

  • How does the search workโ€”is it just keyword matching?

    It combines three search modes: semantic search (vector similarity for understanding), keyword search (precise API/term matching), and hybrid search with AI reranking. This gives you both conceptual answers and exact technical matches.

  • What MCP clients are supported?

    The README lists Cursor, Claude Desktop, and Cline as supported clients, plus 'all MCP-compatible tools.' It uses HTTP transport, so any client supporting MCP should work.

  • Does this server include code examples?

    Yesโ€”the README states it provides practical code examples in Swift, Objective-C, and SwiftUI alongside documentation references, though the README does not detail how comprehensively examples are indexed.

Run Apple Rag across 60+ AI models, side-by-side

Connect Apple Rag to Claude, GPT, Gemini, DeepSeek and 60+ AI models in MCP Agent Studio. Compare answers side-by-side, save reusable agent presets, share runs โ€” all in your browser, no install required.

Open Agent Studio

Related servers

More on MCP Playground