Peekaboo — security grade SAFE, quality 76/100

Security audit verdict: SAFE · quality 76/100

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 openclaw · MCP Server · ★ 5.2k

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

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

About Peekaboo

Peekaboo 🫣 — Mac automation that sees the screen and does the clicks. Peekaboo is a macOS CLI and menu-bar app for screen capture, accessibility inspection, and native UI automation. Use it directly, let its agent plan multi-step work, or expose the same tool

aimacosmcpscreenshotsswift

Quick Facts

Stars5,185
Forks399
LanguageSwift
CategoryMCP Server
LicenseMIT
Quality Score76.4516869402906/100
Open Issues5
Last Updated2026-09-19
Created2025-05-22
Platformscli, mcp
Est. Tokens~16k

Compatible Skills

These tools work well together with Peekaboo for enhanced workflows:

  • Peekaboo — semantic(1.00)+rare_topics+same_lang+similar_pop+shared_platform (65%)
  • wb — semantic(0.18)+complementary+same_lang+shared_platform (46%)
  • AXorcist — semantic(0.18)+complementary+same_lang+shared_platform (46%)

Peekaboo alternative? Top 6 similar tools

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

  • Peekaboo by steipete · ⭐ 3.2k

    Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, o

  • Kiln by Kiln-AI · ⭐ 5.1k

    Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation,

  • amical by amicalhq · ⭐ 1.5k

    🎙️ AI Dictation App - Open Source and Local-first ⚡ Type 3x faster, no keyboard needed. 🆓 Powered by open so

  • CodexBar by steipete · ⭐ 21.7k

    Show usage stats for OpenAI Codex and Claude Code, without having to login.

  • trigger.dev by triggerdotdev · ⭐ 16.3k

    Trigger.dev – build and deploy durable AI agents and workflows

  • ida-pro-mcp by mrexodia · ⭐ 12.1k

    AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Swift Agent Tools

Frequently Asked Questions

What is Peekaboo?

Peekaboo is Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI mo. It is categorized as a MCP Server with 5.2k GitHub stars.

What programming language is Peekaboo written in?

Peekaboo is primarily written in Swift. It covers topics such as ai, macos, mcp.

How do I install or use Peekaboo?

You can find installation instructions and usage details in the Peekaboo GitHub repository at github.com/openclaw/Peekaboo. The project has 5.2k stars and 399 forks, indicating an active community.

What license does Peekaboo use?

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

What are the best alternatives to Peekaboo?

The top alternatives to Peekaboo on Agent Skills Hub include Peekaboo, Kiln, amical. 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