by ai4s-research · MCP Server · ★ 2.1k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/ai4s-research/open-scienceTaken from the project's README on GitHub. Check the security audit before running it.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 2,076 |
| Forks | 229 |
| Language | TypeScript |
| Category | MCP Server |
| Quality Score | 63/100 |
| Open Issues | 26 |
| Last Updated | 2026-11-05 |
| Created | 2026-07-03 |
| Platforms | claude-code, mcp, node |
| Est. Tokens | ~17k |
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.
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.
The open-source AI research workbench for scientific research and agent workflows. Local-first, model-agnostic
Open-source, local-first desktop AI research workbench for scientific computing with Python/R, MCP bioinformat
Verifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay
Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools,
Rent the model. Own everything else. Free, open-source AI app for real work.
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
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: