agentbro — security grade SAFE, quality 64/100

Security audit verdict: SAFE · quality 64/100

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 shirenchuang · MCP Server · ★ 211

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

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

About agentbro

AgentBro 让 Agent 更好用 面向 AI 编程 Agent 的 macOS 灵动岛。 把权限请求、问题、计划、工具调用、快速回复、远程会话、完成提醒,以及 Agent 安装、Hook 和 Skills 管理,收进一个轻巧的桌面工作台。 官网 · 下载 · 隐私 · English Claude Code / Codex / Gemini CLI / Cursor / Copilot / Kimi / Qoder / OpenCode 等 AI 编程 Agent 的本地控制台。 快速开始 下载: 或 国内最新 DMG。 接入:打开 Island - Integration,运行 Hook Doctor,再安装你正在使用的 Agent Hook。 贡献:看 [](https://github.com/shirenchuang/agentbro/issues?q=is%3Aissue%20is%3Aopen%20label%3A%22good%20first%20issue%

agent-toolsai-agentsclaude-codecoding-agentcursordesktop-appdeveloper-toolsdynamic-islandgemini-clilocal-first

Quick Facts

Stars211
Forks29
LanguageRust
CategoryMCP Server
LicenseApache-2.0
Quality Score63.9928439067345/100
Open Issues5
Last Updated2026-08-04
Created2026-04-26
Platformsclaude-code, cli, codex, gemini, mcp, rust
Est. Tokens~24k

Compatible Skills

These tools work well together with agentbro for enhanced workflows:

  • EchoIsland — semantic(0.40)+complementary+rare_topics+same_lang+similar_pop+shared_platform (68%)
  • OpenCovibe — semantic(0.33)+complementary+same_lang+similar_pop+shared_platform (61%)
  • codex-trace — semantic(0.21)+complementary+same_lang+similar_pop+shared_platform (57%)
  • yapcap — semantic(0.20)+complementary+same_lang+similar_pop+shared_platform (57%)
  • VibeAround — semantic(0.20)+complementary+same_lang+similar_pop+shared_platform (57%)

agentbro alternative? Top 6 similar tools

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

  • OpenContext by 0xranx · ⭐ 729

    A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenC

  • palot by ItsWendell · ⭐ 187

    Just another desktop client for OpenCode 2. Manage projects, sessions, parallel agents, requests, and changes

  • yume by aofp · ⭐ 149

    Native desktop UI for Claude Code with orchestration, streaming, background agents, and multi-provider support

  • vibe-island by vibeislandapp · ⭐ 142

    Vibe Island — macOS notch panel for 25 AI coding agents: Claude Code, Codex, Cursor, Gemini CLI & more. Monito

  • Claude-Agent-Team-Manager by DatafyingTech · ⭐ 140

    Visual org-chart desktop app for managing Claude Code agent teams, skills, and configurations

  • mcp-gearbox by rohitsoni007 · ⭐ 62

    A modern desktop application for managing Model Context Protocol (MCP) servers across multiple AI agents

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is agentbro?

agentbro is A macOS Dynamic Island for AI coding agents: Claude Code, Codex, Gemini CLI, Cursor, hooks, skills, and local agent management.. It is categorized as a MCP Server with 211 GitHub stars.

What programming language is agentbro written in?

agentbro is primarily written in Rust. It covers topics such as agent-tools, ai-agents, claude-code.

How do I install or use agentbro?

You can find installation instructions and usage details in the agentbro GitHub repository at github.com/shirenchuang/agentbro. The project has 211 stars and 29 forks, indicating an active community.

What license does agentbro use?

agentbro 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 agentbro?

The top alternatives to agentbro on Agent Skills Hub include OpenContext, palot, yume. 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