HomeClaw — security grade SAFE, quality 71/100

Security audit verdict: SAFE · quality 71/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by omarshahine · MCP Server · ★ 165

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is HomeClaw safe to install? View the security audit →

About HomeClaw

HomeClaw Control your Apple HomeKit smart home from AI assistants, the terminal, and automation tools. HomeClaw exposes your HomeKit accessories through a command-line tool, a stdio MCP server, and plugins for Claude Code and OpenClaw. It runs as a lightweight macOS menu bar app. Screenshots Settings — every preference in one place CLI — every accessory, one command away <img src="docs/images/framed-tui.png" width="700" alt="Terminal UI — accessory tree with live st

claudehomekitmacosmcpsmart-homeswift

Quick Facts

Stars165
Forks24
LanguageSwift
CategoryMCP Server
LicenseMIT
Quality Score71.2602118366983/100
Open Issues6
Last Updated2026-09-06
Created2026-02-24
Platformsclaude-code, mcp
Est. Tokens~26k

Compatible Skills

These tools work well together with HomeClaw for enhanced workflows:

  • robsonfelix-hass-addons — semantic(0.47)+complementary+rare_topics+similar_pop+shared_platform (56%)
  • openpaw — semantic(0.33)+complementary+rare_topics+similar_pop+shared_platform (51%)
  • home-mind — semantic(0.39)+complementary+rare_topics+similar_pop (48%)

HomeClaw alternative? Top 6 similar tools

Looking for a HomeClaw alternative? If you're comparing HomeClaw with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • Homekit by bolivestilo · ⭐ 66

    Homekit gives any AI agent direct, physical control over Apple Home. Flip lights. Lock doors. Read sensors. Th

  • claude-code-apple-skills by rshankras · ⭐ 606

    Claude Code skills for Apple platform development (iOS, macOS, iPadOS) — product validation, code generation,

  • CoWork-OS by CoWork-OS · ⭐ 451

    Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and ar

  • mcp-linker by milisp · ⭐ 323

    mcp store manager, add & syncs MCP server configurations across clients like Claude code, Cursor💡mcphub

  • mac_messages_mcp by carterlasalle · ⭐ 322

    An MCP server that securely interfaces with your iMessage database via the Model Context Protocol (MCP), allow

  • hass-mcp by voska · ⭐ 312

    Control and query Home Assistant from Claude and other LLMs — a Model Context Protocol (MCP) server.

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Swift Agent Tools

Frequently Asked Questions

What is HomeClaw?

HomeClaw is HomeKit smart home control via MCP — lights, locks, thermostats, and scenes for Claude Desktop, Claude Code, and OpenClaw. It is categorized as a MCP Server with 165 GitHub stars.

What programming language is HomeClaw written in?

HomeClaw is primarily written in Swift. It covers topics such as claude, homekit, macos.

How do I install or use HomeClaw?

You can find installation instructions and usage details in the HomeClaw GitHub repository at github.com/omarshahine/HomeClaw. The project has 165 stars and 24 forks, indicating an active community.

What license does HomeClaw use?

HomeClaw is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to HomeClaw?

The top alternatives to HomeClaw on Agent Skills Hub include Homekit, claude-code-apple-skills, CoWork-OS. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools