search-papers
Enables agents to search, analyze, and explore arXiv academic papers with advanced multi-field search, author lookup, category browsing, citation extraction, and bibliography export.
README
Agents 🤝 arXiv Papers
Empower your agents to search, analyse, and explore academic papers from arXiv autonomouly.
Table of Contents
To Do
- [x] Publish to the MCP registry
- [ ] Try Cloudflare's experimental Code Mode
Key Features
- Advanced multi-field search with date ranges and sorting options
- Author-specific searches with affiliation tracking
- Category browsing for all ArXiv subject areas
- Version tracking to see how papers evolved
- Citation extraction from abstracts and metadata
- Related paper discovery based on content similarity
- Bibliography export in BibTeX and JSON formats
Getting Started
Cursor
{
"search-papers": {
"command": "npx",
"args": ["mcp-remote", "https://search-papers.com/sse"]
}
}
Claude Code
claude mcp add --transport sse cloudflare-docs -s project https://search-papers.com/sse
{
"search-papers": {
"type": "sse",
"url": "https://search-papers.com/sse"
}
}
Codex
[mcp_servers.search-papers]
command = "npx"
args = ["https://search-papers.com/sse"]
Architecture
Search Papers MCP Features
Search & Discovery Tools:
advanced_search- Multi-field search with date ranges and sortingsearch_by_author- Find all papers by specific authorssearch_by_category- Browse papers in ArXiv categoriessearch_by_date_range- Find papers within time periods
Paper Analysis Tools:
get_paper_by_id- Retrieve complete paper informationget_paper_versions- Track all versions of a paperget_citations- Extract ArXiv citations from papersget_related_papers- Discover similar papers
Export & Bibliography:
export_bibliography- Export in BibTeX or JSON format
AI-Powered Prompts:
literature_review- Generate comprehensive literature reviewsresearch_gaps- Identify research gaps and opportunitiespaper_comparison- Compare multiple paperstrend_analysis- Analyze research trends over time
Resources:
categories://list- Browse all ArXiv categoriestrending://{category}/{days}- Get trending papers
Usage Examples
Advanced Searches
"Find papers on transformer architectures by Vaswani published after 2023"
"Search for quantum computing papers in the last month"
"Show me all papers by Geoffrey Hinton with their affiliations"
Paper Analysis
"Get all versions of paper 2401.12345 and show how it evolved"
"Extract citations from paper 2401.12345"
"Find papers related to arXiv:2301.00001"
Research Insights
"Generate a literature review on vision transformers focusing on architecture innovations"
"Identify research gaps in federated learning over the last 2 years"
"Compare papers 2401.12345, 2401.67890, and 2401.11111 on methodology"
"Analyze trends in large language models research over 5 years"
Export & Resources
"Export these 5 papers in BibTeX format for my thesis"
"Show trending AI papers from the last week"
"List all computer science categories in ArXiv"
Additional Resources
- Model Context Protocol Documentation
- ArXiv API Documentation
- Cloudflare Workers Guide
- MCP TypeScript SDK
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
This repository is licensed under the Apache-2.0 License
Acknowledgments
Built with ❤️ by Ibrahim Saidi and AI agents.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。