open-science — security grade SAFE, quality 63/100

Security audit verdict: SAFE · quality 63/100

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 ai4s-research · MCP Server · ★ 1.7k

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

🔒 Is open-science safe to install? View the security audit →

About open-science

Open Science An open AI workbench for scientists. Your research partner for rigorous science. An open-source, local-first, model-agnostic, reproducible AI research workbench — an open alternative to Claude Science and similar AI-for-science products. Not a chat box: a workbench that ties literature, code, figures, reports, and review into one auditable, reproducible workflow. English · 中文 Contents ✨ Why it is different 🎬 See it in action [🧭 How it works](#-how-it-w

ai-agentai-for-scienceai-scientistai4sclaude-scienceclaude-science-alternativeclaude-science-desktop-alternativedesktop-applinuxlocal-first

Quick Facts

Stars1,664
Forks202
LanguageTypeScript
CategoryMCP Server
Quality Score62.6042546033721/100
Open Issues22
Last Updated2026-09-18
Created2026-07-03
Platformsclaude-code, mcp, node
Est. Tokens~17k

open-science alternative? Top 6 similar tools

Looking for a open-science alternative? If you're comparing open-science 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.

  • open-science by aipoch · ⭐ 4.8k

    AIPOCH Open-Science: an open-source AI research workbench for scientific agent workflows and reproducible scie

  • wisp-science by xuzhougeng · ⭐ 1.2k

    Open-source, local-first desktop AI research workbench for scientific computing with Python/R, MCP bioinformat

  • ScienceClaw by beita6969 · ⭐ 874

    🔬🦞 A self-evolving AI research colleague for scientists. 285 skills, zero hallucination, persistent memory.

  • mcp-client-for-ollama by jonigl · ⭐ 823

    Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools,

  • CoWork-OS by CoWork-OS · ⭐ 457

    Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and ar

  • CSSwitch by SuperJJ007 · ⭐ 432

    让 Claude Science 的推理走自选的第三方 API(DeepSeek / 通义千问 / 任意 OpenAI 兼容端点),保留工具调用·Skill·MCP·代码执行,含本地虚拟登录跳过。macOS 菜单栏 ap

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is open-science?

open-science is Open Science Desktop — local-first, model-agnostic AI research workbench for macOS, Windows & Linux. Open-source Claude Science desktop alternative built on Tauri + MCP + agent skills.. It is categorized as a MCP Server with 1.7k GitHub stars.

What programming language is open-science written in?

open-science is primarily written in TypeScript. It covers topics such as ai-agent, ai-for-science, ai-scientist.

How do I install or use open-science?

You can find installation instructions and usage details in the open-science GitHub repository at github.com/ai4s-research/open-science. The project has 1.7k stars and 202 forks, indicating an active community.

What are the best alternatives to open-science?

The top alternatives to open-science on Agent Skills Hub include open-science, wisp-science, ScienceClaw. 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