MiniAgent — 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 ZhuLinsen · MCP Server · ★ 190

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

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

About MiniAgent

MiniAgent 🚀 5分钟手搓一个 AI Coding 助手 + 命令行版 Manus! | English 💡 核心特性 一个 核心文件,复刻 Claude Code 的编程能力 + Manus 的系统操控能力! MiniAgent 是一个极简、透明、强大的 CLI Agent 框架,拒绝臃肿的依赖和复杂的架构: 🧠 Code Agent: 像 Claude Code 一样写代码、修 Bug、跑测试 🦾 OS Agent: 像 Manus 一样操控浏览器、编辑文档、管理应用 ⚡ 极简实现: 核心引擎 完全透明可控,适合学习和魔改 🤖 全模型支持: DeepSeek、OpenAI、Gemini、Claude 等所有兼容 OpenAI 接口的模型 🔌 高扩展性: 极简装饰器模式,3行代码即可挂载自定义工具 🔄 双模式工具调用: 文本解析模式(透明可学习)+ 原生 Function Calling 模式(更可靠) 🎯 Skill 系统: 可复用的 Agent 配置,内置 coder/researcher/reviewer/tester 四个角色 🛡️ 安全防护: 危险命令自动拦截确认,防止 LLM 幻觉导致破坏性操作 💬 流式输出: 打字机效果实时输出,长对话自动压缩上下文 🔗 MCP 协议: 支持连接 MCP 工具服务器,接入社区生态 🤝 Agent 编排: 内置编排器,支持任务分解 + 多角色协同 🤔 Why MiniAgent? | OS 控制

agentclaudeclaudecodellmllmsmanusmcpopenai

Quick Facts

Stars190
Forks41
LanguagePython
CategoryMCP Server
LicenseApache-2.0
Quality Score63.8274053853193/100
Open Issues1
Last Updated2026-07-12
Created2025-04-27
Platformsclaude-code, cli, mcp, python
Est. Tokens~15k

Compatible Skills

These tools work well together with MiniAgent for enhanced workflows:

  • AGIAgent — semantic(0.30)+complementary+rare_topics+same_lang+similar_pop+shared_platform (60%)
  • planning-with-files — semantic(0.32)+complementary+rare_topics+same_lang+shared_platform (56%)
  • PocketManus — semantic(0.29)+complementary+same_lang+similar_pop+shared_platform (55%)
  • AIForge — semantic(0.25)+complementary+same_lang+similar_pop+shared_platform (54%)

MiniAgent alternative? Top 6 similar tools

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

  • argo by xark-argo · ⭐ 827

    ARGO is an open-source AI Agent platform that brings Local Manus to your desktop. With one-click model downloa

  • wcgw by rusiaaman · ⭐ 674

    Shell and coding agent on mcp clients

  • oreilly-ai-agents by sinanuozdemir · ⭐ 299

    An introduction to the world of AI Agents

  • mcp-framework by QuantGeekDev · ⭐ 930

    The Typescript MCP Framework

  • UnrealGenAISupport by prajwalshettydev · ⭐ 632

    Unreal Engine plugin for LLM/GenAI models & MCP UE5 server. OpenAI GPT-5, Deepseek R1, Claude Opus/Sonnet, Gem

  • agnix by agent-sh · ⭐ 422

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

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is MiniAgent?

MiniAgent is 🚀「 5分钟手搓一个 AI Coding 助手 + 命令行版 Manus」 ⚡️Build an AI Coding Assistant + CLI-based Manus in 5 Minutes!. It is categorized as a MCP Server with 190 GitHub stars.

What programming language is MiniAgent written in?

MiniAgent is primarily written in Python. It covers topics such as agent, claude, claudecode.

How do I install or use MiniAgent?

You can find installation instructions and usage details in the MiniAgent GitHub repository at github.com/ZhuLinsen/MiniAgent. The project has 190 stars and 41 forks, indicating an active community.

What license does MiniAgent use?

MiniAgent 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 MiniAgent?

The top alternatives to MiniAgent on Agent Skills Hub include argo, wcgw, oreilly-ai-agents. 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