lucid-apple-mcp
Provides tools for performing OCR, text detection, document recognition, and using on-device large language models via Apple's Vision, NSDataDetector, and FoundationModels frameworks.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
lucid-apple-mcp
MCP server that gives Claude and local LLMs access to Apple's on-device frameworks — Vision OCR, NSDataDetector, and Apple Intelligence FoundationModels. Everything runs on your Mac. Nothing leaves.
Zero tokens consumed · Zero data leaves your Mac.
Tools
Tool | Engine | Needs Apple Intelligence | Input | Returns |
| Vision | No |
| plain text |
| Vision | No |
|
|
| NSDataDetector | No |
| JSON array |
| FoundationModels | Yes |
| JSON object |
| FoundationModels | Yes |
| one label |
| FoundationModels | Yes |
| summary string |
| FoundationModels | Yes |
| reply string |
Three capability tiers:
ocr+detect— run on any Apple Silicon Mac. No Apple Intelligence, no macOS 26 required.recognize_document— requires macOS 26 (Vision'sRecognizeDocumentsRequest), but not Apple Intelligence.extract,classify,summarize,generate— require macOS 26 + Apple Intelligence enabled in System Settings.
Related MCP server: FreezeText MCP
Requirements
Apple Silicon Mac
Node.js 18+
Xcode Command Line Tools (
xcode-select --install) — to build the Swift helpermacOS 26+ — for
recognize_documentand the four FoundationModels toolsApple Intelligence enabled — for
extract,classify,summarize,generateonly
Install
git clone https://github.com/Lucid-Systems-LLC/Lucid-Apple-MCP.git
cd Lucid-Apple-MCP
npm install # compiles helper.swift → ./helper automatically (postinstall)npm install builds the Swift helper for you. On a non-Mac, or a Mac without the Xcode tools, it skips the build with a note instead of failing — run npm run build once the toolchain is present.
Add to Claude Code (CLI)
claude mcp add lucid-apple "$(which node)" "$(pwd)/server.mjs"$(which node) bakes in the absolute path to your Node binary — which matters (see the note below).
Add to Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"lucid-apple": {
"command": "/absolute/path/to/node",
"args": ["/absolute/path/to/lucid-apple-mcp/server.mjs"]
}
}
}Use an absolute path to node — Claude Desktop is launched from the GUI and does not inherit your shell PATH, so a bare "node" fails with spawn node ENOENT (common with nvm or Homebrew). Find yours with which node (e.g. /Users/you/.nvm/versions/node/v20.20.0/bin/node). Use the absolute path to server.mjs too.
Restart Claude Desktop. The tools appear in the MCP panel.
Architecture
Node.js MCP server (server.mjs, stdio transport) spawns a compiled Swift binary (helper) once per tool call — one JSON request on stdin, one JSON result on stdout. The Swift binary bridges:
Vision (
VNRecognizeTextRequest,RecognizeDocumentsRequest) → OCRNSDataDetector → deterministic entity detection
FoundationModels → Apple's on-device LLM
Stateless per call. No persistent process. Safe in air-gap when used with a local LLM client.
Privacy
Computation is fully on-device — files and text never leave the Mac. One honest caveat: when driving this from a cloud assistant (e.g. Claude Desktop), tool results are returned to that assistant and become part of the cloud conversation. For an end-to-end offline pipeline, drive the MCP from a local client like Voical.
Limitations
recognize_documentrequires macOS 26;extract,classify,summarize, andgeneraterequire macOS 26 with Apple Intelligence enabled. On older macOS these return a clean "requires macOS 26" error —ocranddetectkeep working.Apple's on-device model is fast and private — not a frontier model. Use it for short answers, drafts, and rewrites.
ocrandrecognize_documentrequire absolute file paths.macOS only. No Windows or Linux support.
License
MIT — see LICENSE.
Built by Lucid Systems LLC · Veteran owned · No VC · No cloud
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Hosted Apple Health MCP for Claude and ChatGPT, works outside the US. iPhone app, no local server.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
Connect ChatGPT and Claude to your Mac, Windows or Linux with secure MCP remote access.
Related MCP Servers
- AlicenseBqualityDmaintenanceA local vision-language MCP server that enables Claude Code to perform image analysis, OCR, and UI-to-code generation using the Qwen3 VL 4B model via LM Studio. It provides privacy-focused visual processing by running entirely on the user's local hardware without external API dependencies.336 npm1MIT
- AlicenseAqualityCmaintenanceMCP server for FreezeText — OCR anything on your Mac screen from Claude, Cursor, or any MCP client. Freeze the screen and extract text via Apple Vision (videos, popups, protected PDFs), OCR a region or a base64 image, and manage a searchable capture history. 12 tools. Bridge open-source (MIT), FreezeText app is free.121MIT
- AlicenseNot gradedqualityCmaintenanceExposes Apple's on-device 3B parameter LLM to Claude Code and Claude Desktop via MCP. Zero API cost, fully private, runs on Neural Engine.39 PyPI1MIT
- FlicenseAqualityDmaintenanceLocal multimodal MCP server for vision, document, audio, video, and GUI automation, all processed locally on Apple Silicon for privacy and security.9-