Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, email [email protected] and we’ll put it right.

io.github.Lucid-Systems-LLC/lucid-apple-mcp

NPM · LUCID-APPLE-MCP · SCANNED AUG 3

On-device Apple Intelligence as MCP tools for macOS — OCR, tables, entity detection, generation.

Available components

+42 this week 60 Trust /100
Trust breakdown (6 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →

Supply Chain Security74
  • No malware found by supply-chain analysis.Pass
  • Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.Partial
  • Install-script check failed: the install command fetches or executes arbitrary code (inline_eval). An install hook runs on every machine, in CI, and on transitive installs, whether or not you ever run the server. View diagnostics → Fail
  • Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency19
  • Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 44 days ago).Pass
  • Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability77
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 449 tokens (~64/item across 7 items; 7 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
  • Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · lucid-apple-mcp

# add to Claude Code
claude mcp add lucid-systems-llc-lucid-apple-mcp -- npx -y lucid-apple-mcp
# add to Codex CLI
codex mcp add lucid-systems-llc-lucid-apple-mcp -- npx -y lucid-apple-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "lucid-systems-llc-lucid-apple-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "lucid-apple-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add lucid-systems-llc-lucid-apple-mcp --command npx --arg -y --arg lucid-apple-mcp
# ~/.hermes/config.yaml
mcp_servers:
  lucid-systems-llc-lucid-apple-mcp:
    command: "npx"
    args: ["-y", "lucid-apple-mcp"]
// mcp.json
{
  "mcpServers": {
    "lucid-systems-llc-lucid-apple-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "lucid-apple-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 3 Aug 26 +4
    • Stability: unverified → 0.27 functional
  • 2 Aug 26 +40
    • Install scripts: unverified → fail security
    • Provenance: unverified → fail security
    • Known CVEs: unverified → partial security
    • Malware scan: unverified → pass security
    • Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
    • The scripts that run when this package is installed changed: postinstall security
    • Tool coverage: 100 → unverified functional
    • Schema quality: unverified → excellent functional
    • License: unverified → pass functional
    • Dependency health: unverified → partial functional
    • Maintenance: unverified → pass functional
    • MCP protocol: unverified → pass functional
    • Licence: MIT functional
  • 31 Jul 26 −6
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 −18
    • Malware scan: pass → unverified security
  • 28 Jul 26 +22
    • Tool coverage: unverified → 100 functional
    • First check of Schema quality: fail functional
    • First check of Schema quality: pass functional
    • First check of Schema quality: unverified functional
    • First check of Tool coverage: 100 functional
  • 27 Jul 26 18

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 3 Aug 2026 · Analysed npm/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Install scripts 1 script
Hook Tier Command
postinstall dangerous node -e "const{spawnSync}=require('node:child_process');if(process.platform!=='darwin'){console.warn('[lucid-apple-mcp] non-macOS host - skipping Swift helper build (this server is macOS only).');process.exit(0)}const r=spawnSync('swiftc',['-parse-as-library','helper.swift','-o','helper'],{stdio:'inherit'});if(r.status!==0)console.warn('[lucid-apple-mcp] could not build helper - install Xcode Command Line Tools (xcode-select --install), then run: npm run build');process.exit(0)"
Dependencies 94 packages

94 packages in the resolved dependency tree · 94 deprecated · 29 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 7 exposed · ~449 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.

Tool Tokens
classify ~51

Classify text into EXACTLY ONE of a provided set of labels, on-device (offline).

NameTypeReqDescription
labelsarrayyesThe allowed labels (pick exactly one).
textstringyesThe text to classify.

No output schema declared.

No examples provided.

detect ~57

Detect dates, links, phone numbers, and addresses in text (NSDataDetector — fully offline + deterministic). Returns a JSON array of items. Pairs well with extract for grounding calendar/contact data.

NameTypeReqDescription
textstringyesThe text to scan.

No output schema declared.

No examples provided.

extract ~97

Extract STRUCTURED data from text with Apple's on-device model (offline) — returns JSON. Great for pulling an event, action items, or contact fields out of an email / note / message.

NameTypeReqDescription
textstringyesThe source text.
wantstringWhat to extract, e.g. 'the meeting date, time, attendees, and location' or 'all action items'. Defaults to key fields/entities/dates/action-items.

No output schema declared.

No examples provided.

generate ~61

Ask Apple's on-device Intelligence model (offline). Good for quick answers, drafting, rewriting. Concise; not for deep reasoning.

NameTypeReqDescription
instructionsstringOptional system-style guidance (tone, role, format).
promptstringyesThe prompt / question.

No output schema declared.

No examples provided.

ocr ~58

Extract text from an image or rendered PDF page using on-device Apple Vision OCR. Fully offline, ~0.2s.

NameTypeReqDescription
pathstringyesAbsolute path to an image (png/jpg/heic/tiff) or rendered PDF page.

No output schema declared.

No examples provided.

recognize_document ~91

STRUCTURED document OCR via Apple Vision (RecognizeDocumentsRequest, offline). Returns JSON {transcript, tables} and preserves TABLES as rows/cells + reading order — unlike `ocr`, which flattens layout. Use for tables, forms, receipts, and multi-column documents.

NameTypeReqDescription
pathstringyesAbsolute path to an image (png/jpg/heic/tiff) or rendered PDF page.

No output schema declared.

No examples provided.

summarize ~34

Summarize text concisely using Apple's on-device Intelligence model (offline).

NameTypeReqDescription
textstringyesThe text to summarize.

No output schema declared.

No examples provided.