Research Rabbit alternative

Scholar Feed: a Research Rabbit alternative for people who live in their editor

Scholar Feed is an alternative to Research Rabbit for CS/AI/ML researchers who would rather query papers inside their AI assistant than explore a visual web app. Research Rabbit is the better pick if you want free, interactive citation maps to explore a topic’s neighborhood. Scholar Feed trades the visual map for in-editor MCP access, an LLM novelty score on every paper, and daily "watches", over a 600,000+ CS/AI/ML corpus. Install with npx scholar-feed-mcp init.

Why people search "Research Rabbit alternative"

Research Rabbit is a genuinely good, free discovery tool — you start from a seed paper and it maps similar work, earlier and later work, and author networks. Two reasons people look for something different:

  1. It’s a separate web app you browse. If your actual work happens in Claude Code or Cursor, you want discovery in that workflow, not in another tab.
  2. It’s built for exploring a neighborhood once, visually. It’s less suited to "keep telling me what’s new in this narrow area every day," and it doesn’t put a novelty signal on each paper to help you skip incremental work.

How Scholar Feed compares

Comparison axisResearch RabbitScholar Feed
FormVisual web app (citation maps, author graphs)MCP server (your assistant queries it, no UI to learn)
Best atExploring a topic’s neighborhood visuallyQuerying + watching a narrow area from inside your editor
Per-paper signalNone on the node itselfLLM summary + 0–1 novelty score
Keep-upNotifies on new related work in a collectionDaily watches on a saved filter (lab, technique, author, citation scope)
CoverageAll fields (Semantic Scholar data)600,000+ CS/AI/ML papers, indexed daily from arXiv
Full textLinks outExtracts results/experiments from LaTeX source
PriceFreeFree anonymous (100/day), free key (1,000/day)

What you actually do with it

Instead of opening a map and panning around, you ask your assistant "what’s new and high-novelty on retrieval-augmented generation this month?" and get ranked CS/ML papers with summaries, in the window you’re already in. Then "watch new sparse-attention work above 0.5 novelty" and it surfaces matches daily. It’s the keep-an-eye-on-this-area job, done as a tool your agent calls, rather than a canvas you explore.

When NOT to use Scholar Feed

Frequently asked questions

Is Scholar Feed a good Research Rabbit alternative?

It depends on what you want. If you want to query and monitor a narrow CS/AI/ML area from inside Claude Code or Cursor, with an LLM novelty score on each paper and daily watches, Scholar Feed fits. If you want free, interactive citation maps to explore a topic’s neighborhood visually, Research Rabbit is the better tool — Scholar Feed does not render graphs you pan around.

Does Scholar Feed show citation maps like Research Rabbit?

No. Scholar Feed traces citations as data — incoming citations and outgoing references in both directions — but it does not render an interactive visual graph. For visual neighborhood maps, use Research Rabbit, Connected Papers, or Litmaps.

Do I need an account or API key to try it?

No. The search and read tools work anonymously at 100 calls per day. A free API key raises the limit to 1,000 calls per day, and Pro raises it to 10,000. Install with npx scholar-feed-mcp init.

Try it

npx scholar-feed-mcp init

Free anonymous access is 100 calls/day (no account); a free key raises it to 1,000/day. Open source (MIT): scholar-feed-mcp on GitHub.

More setup options on the developers page.

Related comparisons