AppClaw — security grade SAFE, quality 69/100

Security audit verdict: SAFE · quality 69/100

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 AppiumTestDistribution · MCP Server · ★ 91

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

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

About AppClaw

AppClaw AI-powered mobile automation agent for Android and iOS. Tell it what to do in plain English — it figures out what to tap, type, and swipe. Prerequisites Node.js 18+ Device connected — USB, emulator, or simulator LLM API key from any supported provider (Anthropic, OpenAI, Google, Groq, or local Ollama) Installation From npm Create a file in your working directory: Local development Edit based on your preferred mode: Vision mode (recommended) Screenshot-first mode using Stark (df-vision + Gemini) for element location. Requires a Gemini API key. env LLMPROVIDER=gemini LLMAPIKEY=your-gemini-api-key LLMMODE

agentai-agentai-agentsandroidappiumappium-mcpcloudiosllmmcp

Quick Facts

Stars91
Forks17
LanguageTypeScript
CategoryMCP Server
LicenseApache-2.0
Quality Score69.3380732598876/100
Open Issues4
Last Updated2026-07-07
Created2026-03-23
Platformsmcp, node
Est. Tokens~17k

Compatible Skills

These tools work well together with AppClaw for enhanced workflows:

  • ClawMobile — semantic(0.32)+complementary+rare_topics+same_lang+similar_pop+shared_platform (61%)

AppClaw alternative? Top 6 similar tools

Looking for a AppClaw alternative? If you're comparing AppClaw 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.

  • AppClaw by appclawhq · ⭐ 115

    AI-powered mobile automation agent — describe what you want in plain English, AppClaw reads the screen, reason

  • agnix by agent-sh · ⭐ 422

    The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug

  • droidmind by hyperb1iss · ⭐ 434

    Control your Android devices with AI using Model Context Protocol

  • mobileClaw by eggbrid2 · ⭐ 410

    Open Android AI agent runtime for phone control, app automation, VLM screen reading, skill routing, mini apps,

  • Context-Engine by Context-Engine-AI · ⭐ 402

    Context-Engine MCP - Agentic Context Compression Suite

  • flutter-skill by ai-dashboad · ⭐ 362

    AI-powered E2E testing for 10 platforms. 253 MCP tools. Zero config. Works with Claude, Cursor, Windsurf, Copi

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is AppClaw?

AppClaw is AI-powered mobile automation agent — describe what you want in plain English, AppClaw reads the screen, reasons, and acts. LLM-agnostic, open-source, zero telemetry.. It is categorized as a MCP Server with 91 GitHub stars.

What programming language is AppClaw written in?

AppClaw is primarily written in TypeScript. It covers topics such as agent, ai-agent, ai-agents.

How do I install or use AppClaw?

You can find installation instructions and usage details in the AppClaw GitHub repository at github.com/AppiumTestDistribution/AppClaw. The project has 91 stars and 17 forks, indicating an active community.

What license does AppClaw use?

AppClaw is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to AppClaw?

The top alternatives to AppClaw on Agent Skills Hub include AppClaw, agnix, droidmind. 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