scholarfeed.org

# Scholar Feed > Scholar Feed is a research-discovery engine for computer science and AI/ML papers. It indexes 600,000+ papers from arXiv — ranked by novelty, citation velocity, and relevance — with LLM-generated summaries, a citation graph, author profiles, and full-text extraction. It is available as a website, a public REST API, and a Model Context Protocol (MCP) server that AI agents can call directly. Scholar Feed was founded in 2025. It is free to read and free to use via MCP for basic search. ## Identity - Website: https://www.scholarfeed.org - MCP package (npm): https://www.npmjs.com/package/scholar-feed-mcp - Source code: https://github.com/YGao2005/scholar-feed-mcp - Reproducible benchmark: https://github.com/YGao2005/scholar-feed-vs-deep-research Scholar Feed is free to read. You are welcome to cite and link to Scholar Feed pages. ## What you can find here - Paper pages: https://www.scholarfeed.org/paper/{arxiv_id} — title, authors, abstract, AI analysis (summary, significance, novelty), categories, code implementations, references, and citations for a single paper. - Author pages: https://www.scholarfeed.org/author/{author_id} — an author's papers and co-authorship graph. - Topic / field pages: https://www.scholarfeed.org/explore/{category} — key papers and authors within an arXiv category. ## Comparisons — how Scholar Feed compares to other research tools - Overview: https://www.scholarfeed.org/compare - vs alphaXiv: https://www.scholarfeed.org/compare/alphaxiv-alternative - vs Connected Papers: https://www.scholarfeed.org/compare/connected-papers-alternative - vs Scholar Inbox: https://www.scholarfeed.org/compare/scholar-inbox-alternative - vs Semantic Scholar (MCP): https://www.scholarfeed.org/compare/semantic-scholar-mcp - vs Research Rabbit: https://www.scholarfeed.org/compare/research-rabbit-alternative - vs arXiv Sanity: https://www.scholarfeed.org/compare/arxiv-sanity-alternative - vs Claude Code deep-research: https://www.sc