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:
- 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.
- 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 axis | Research Rabbit | Scholar Feed |
|---|---|---|
| Form | Visual web app (citation maps, author graphs) | MCP server (your assistant queries it, no UI to learn) |
| Best at | Exploring a topic’s neighborhood visually | Querying + watching a narrow area from inside your editor |
| Per-paper signal | None on the node itself | LLM summary + 0–1 novelty score |
| Keep-up | Notifies on new related work in a collection | Daily watches on a saved filter (lab, technique, author, citation scope) |
| Coverage | All fields (Semantic Scholar data) | 600,000+ CS/AI/ML papers, indexed daily from arXiv |
| Full text | Links out | Extracts results/experiments from LaTeX source |
| Price | Free | Free anonymous (200/month), free key (500/month) |
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
- You want the visual citation map to explore how a field connects. That’s Research Rabbit’s whole strength, it’s free, and Scholar Feed doesn’t render graphs you pan around. Use Research Rabbit (or Connected Papers / Litmaps).
- You work outside CS/AI/ML. Research Rabbit covers all fields; Scholar Feed is a 600k CS/AI/ML corpus.
- You want a polished standalone app with no setup. Research Rabbit is a click-and-go website; Scholar Feed lives inside an MCP client you already use.
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 200 calls per month. A free API key raises the limit to 500 calls per month, and Pro raises it to 10,000. Install with npx scholar-feed-mcp init.
Try it
npx scholar-feed-mcp initFree anonymous access is 200 calls/month (no account); a free key raises it to 500/month. Open source (MIT): scholar-feed-mcp on GitHub.
More setup options on the developers page.