nature-academic-search — 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 wp-a · MCP Server · ★ 250

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

🔒 Is nature-academic-search safe to install? View the security audit →

About nature-academic-search

Academic Paper Search 给 Codex、Claude Code 和 DeepSeek Harness 使用的文献检索与引用核验工具。 用中文描述研究问题,跨学术数据库找论文、去重、核对引用,导出文献管理器可用的文件。 快速开始 · 中文场景 · 工具与命令 · 批量工作流 · 数据源 · 常见问题 可选配套服务:WPIRONMAN AI 中转 提供可选模型入口,不是论文来源。学术源检索、元数据核验和引用下载不需要配置中转。 这是什么 本项目帮助科研用户完成可复现的文献检索、核验与引用导出。核心流程是 检索 → 去重 → 核验 → 导出;需要扩展阅读时,可以从种子论文追踪参考文献和后续引用。 安装标识仍为 ,展示名称为 Academic Paper Search。 名称中的 不限制检索范围,也不表示与 Nature Portfolio 有官方关联。 默认论文源为 CrossRef

academic-searchagent-skillsarxivchinesecitation-graphcitation-managementcitation-verificationclaude-codeclinicaltrials-govcodex

Quick Facts

Stars250
Forks11
LanguagePython
CategoryMCP Server
LicenseMIT
Quality Score63.00005371638/100
Open Issues2
Last Updated2026-09-16
Created2026-06-11
Platformsclaude-code, cli, codex, mcp, python
Est. Tokens~17k

Compatible Skills

These tools work well together with nature-academic-search for enhanced workflows:

  • auto-paper-collecter — semantic(0.42)+complementary+rare_topics+same_lang+similar_pop+shared_platform (78%)
  • OneCite — semantic(0.39)+complementary+rare_topics+same_lang+similar_pop+shared_platform (77%)
  • paper-fetch — semantic(0.34)+complementary+rare_topics+same_lang+similar_pop+shared_platform (71%)

nature-academic-search alternative? Top 6 similar tools

Looking for a nature-academic-search alternative? If you're comparing nature-academic-search 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.

  • de-anthropocentric-research-engine by yogsoth-ai · ⭐ 504

    A 267-skill research graph in pure markdown — 51 research operations built from 216 single-purpose steps, comp

  • medsci-skills by Aperivue · ⭐ 325

    Agent Skills for medical research — literature search, reporting-guideline & citation checks, statistics, publ

  • De-Anthropocentric-Research-Engine by Pthahnix · ⭐ 229

    De-Anthropocentric Research Engine — AI-powered academic research automation with deep literature survey, gap

  • paper-fetch by Agents365-ai · ⭐ 174

    DOI → PDF resolver with 7-source fallback (Unpaywall, S2, arXiv, PMC, bioRxiv, publisher, Sci-Hub). Multi-agen

  • paper-search-pro by O0000-code · ⭐ 172

    Academic literature discovery as a Skill — Claude Code · Codex · any agent that loads SKILL.md. Five sources ·

  • OneCite by HzaCode · ⭐ 66

    📚 Only Cite what you can verify

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is nature-academic-search?

nature-academic-search is Academic Paper Search:中文科研用户的 Codex / Claude Code / DeepSeek Harness Skill + MCP;跨 CrossRef、PubMed、arXiv、OpenAlex、Europe PMC 检索去重,支持 MeSH、引用核验、引文图谱、试验检索与审计导出。. It is categorized as a MCP Server with 250 GitHub stars.

What programming language is nature-academic-search written in?

nature-academic-search is primarily written in Python. It covers topics such as academic-search, agent-skills, arxiv.

How do I install or use nature-academic-search?

You can find installation instructions and usage details in the nature-academic-search GitHub repository at github.com/wp-a/nature-academic-search. The project has 250 stars and 11 forks, indicating an active community.

What license does nature-academic-search use?

nature-academic-search is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to nature-academic-search?

The top alternatives to nature-academic-search on Agent Skills Hub include de-anthropocentric-research-engine, medsci-skills, De-Anthropocentric-Research-Engine. 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