daan — security grade SAFE, quality 56/100

Security audit verdict: SAFE · quality 56/100

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 pluveto · MCP Server · ★ 284

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

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

About daan

Dáàn A Lightweight Language Model Client English | 中文 Daan (答案, "Answer" in Chinese) is a concise and lightweight client for interacting with Large Language Models (LLMs), offering a smooth and efficient AI experience. It's compatible with OpenAI's GPT series and other OpenAI-compatible APIs. 正在支持使用 AI 在 Daan 内生成并运行 JS App 和 MCP服务,让 AI 工具化变得轻而易举,敬请期待! Try the Demo Key Features 🆕 Miniapp Functionality: Convert your frequently used features directly into a mini-app for use in a mini-window. 🆕 Miniapp and Character Market: Publish your presets to GitHub issues and install/reuse them in Daan with one click. 🆕 Miniapp as MCP Service: Miniapps also support running as MCP services, enabling low-threshold development of simple MCP servers. ✨ Minimalist Interface: Focus on the conversation, not clutter. 🔌 MCP (Model Context Protocol): Enhance AI responses with external tools and knowledge. 👤 Character Customization: Create and reuse chat personas with specific prompts and settings. 🔄 Flexible Model Selection: Easily switch between OpenAI models or add custom ones. 🔑 Custom API Endpoints: Use alternative OpenAI-compatible API services.

chatgptclientdeepseekllmmcpmcp-clientopenai

Quick Facts

Stars284
Forks14
LanguageTypeScript
CategoryMCP Server
LicenseAGPL-3.0
Quality Score56.2976853400977/100
Open Issues8
Last Updated2025-11-25
Created2025-04-18
Platformscli, mcp, node
Est. Tokens~446k

Compatible Skills

These tools work well together with daan for enhanced workflows:

  • mcp-chat — semantic(0.36)+same_lang+similar_pop+shared_platform (47%)

daan alternative? Top 6 similar tools

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

  • sre by SmythOS · ⭐ 1.3k

    The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular,

  • tuui by AI-QL · ⭐ 1.2k

    A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Mode

  • codexia by milisp · ⭐ 915

    Lightweight Agent Workstation for Codex CLI + Claude Code — with task scheduler, git worktree & remote control

  • 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

  • UnrealGenAISupport by prajwalshettydev · ⭐ 632

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

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is daan?

daan is ✨Lightweight LLM Client with MCP 🔌 & Characters 👤. It is categorized as a MCP Server with 284 GitHub stars.

What programming language is daan written in?

daan is primarily written in TypeScript. It covers topics such as chatgpt, client, deepseek.

How do I install or use daan?

You can find installation instructions and usage details in the daan GitHub repository at github.com/pluveto/daan. The project has 284 stars and 14 forks, indicating an active community.

What license does daan use?

daan is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to daan?

The top alternatives to daan on Agent Skills Hub include sre, tuui, codexia. 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