ScienceClaw — security grade SAFE, quality 60/100

Security audit verdict: SAFE · quality 60/100

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 AgentTeam-TaichuAI · MCP Server · ★ 635

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

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

About ScienceClaw

 ScienceClaw English | 中文 ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new architecture beyond OpenClaw. It offers stronger security, better transparency, and a more user-friendly experience. 1,900+ built-in scientific tools · Multi-format content generation · Fully local & privacy-first Why ScienceClaw · Architecture · News · Quick Start · [Demo](#de

ai-agentbioinformaticsdata-analysisdockerdrug-discoveryfastapifeishulangchainlanggraphllm

Quick Facts

Stars635
Forks69
LanguagePython
CategoryMCP Server
Quality Score60.4257205616881/100
Open Issues13
Last Updated2026-05-09
Created2026-03-13
Platformsdocker, mcp, python
Est. Tokens~143k

Compatible Skills

These tools work well together with ScienceClaw for enhanced workflows:

ScienceClaw alternative? Top 6 similar tools

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

  • ScienceClaw by beita6969 · ⭐ 874

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

  • full-stack-ai-agent-template by vstorm-co · ⭐ 1.9k

    Full-stack AI app generator — FastAPI + Next.js with agents, RAG, streaming, auth, and 20+ integrations out of

  • k-dense-byok by K-Dense-AI · ⭐ 1.2k

    An AI co-scientist running on your desktop. Claude Science but better.

  • flock by Onelevenvy · ⭐ 1.1k

    Flock is a workflow-based low-code platform for rapidly building chatbots, RAG, and coordinating multi-agent t

  • oreilly-ai-agents by sinanuozdemir · ⭐ 299

    An introduction to the world of AI Agents

  • awesome-bio-agent-skills by BioTender-max · ⭐ 140

    A curated collection of AI agent skills for biomedical research, covering genomics, proteomics, single-cell an

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is ScienceClaw?

ScienceClaw is ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new architecture beyond OpenClaw. It offers stronger security, better. It is categorized as a MCP Server with 635 GitHub stars.

What programming language is ScienceClaw written in?

ScienceClaw is primarily written in Python. It covers topics such as ai-agent, bioinformatics, data-analysis.

How do I install or use ScienceClaw?

You can find installation instructions and usage details in the ScienceClaw GitHub repository at github.com/AgentTeam-TaichuAI/ScienceClaw. The project has 635 stars and 69 forks, indicating an active community.

What are the best alternatives to ScienceClaw?

The top alternatives to ScienceClaw on Agent Skills Hub include ScienceClaw, full-stack-ai-agent-template, k-dense-byok. 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