600,000+ CS/AI/ML papers in your AI assistant: search, novelty scores, citations, daily watches.
600,000+ CS/AI/ML papers in your AI assistant: search, novelty scores, citations, daily watches.
Scholar Feed is a research-discovery engine for computer science and AI/ML papers, founded in 2025. 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. This package (scholar-feed-mcp) is the open-source MCP server.
name — scholar-feedscholar-feed — mcp@latestsave_paper — Bookmark a paper to your library (idempotent; feeds personalization).unsave_paper — Remove a paper from your library (idempotent).like_paper — "More like this" calibration signal for the For You feed (insert-only).list_library — List your saved papers, newest first.list_collections — List collections with paper counts.create_collection — Create a named collection (get-or-create; no error on duplicate).add_to_collection — Add a paper to a collection by name or id (also auto-saves).remove_from_collection — Remove a paper from a collection (stays saved).create_watch — Standing daily-evaluated saved search; get-or-create by name. Define it with a structured criteria filter (recommended) or a single seed selector.Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| search_papers | Semantic + keyword search with filters. Also does similar-paper discovery, citation-scoped search, and trending. |
| get_paper | Get full paper details by arXiv ID. Also handles batch lookup and BibTeX export. |
| get_citations | Citation graph (outgoing refs or incoming citations) |
| fetch_fulltext | Read a paper's text by section (abstract, introduction, related_work, method, results, conclusion, or all). Pass arxiv_ids to read up to 8 papers in one call; a |
| find_author | Find researchers by topic/name query, or retrieve a profile by ID. |
| co_author_graph | Co-authorship neighborhood for an author |
| embed_text | Get a 768-dim Gemini embedding for text (for HyDE and custom similarity). Pro-only, so anonymous/free callers get a 403 pro_required. |
| get_field_orientation | Cheap retrieval orientation for a research area: top papers, subfields, open problems. No Pro quota. |
| get_foundational_lineage | Foundational work for a paper's niche via the citation graph (consensus-then-lift): niche_roots → field_level → discipline, with cited_by_in_niche evidence. Sur |
| check_drift | "Is the method I use superseded — and by what?" Critique receipts + benchmark-dominance edges over ~10 LLM builder-problem families. No Pro quota. |
| save_paper | Bookmark a paper to your library (idempotent; feeds personalization). |
| unsave_paper | Remove a paper from your library (idempotent). |
| like_paper | "More like this" calibration signal for the For You feed (insert-only). |
| list_library | List your saved papers, newest first (includes your notes). |
| annotate_paper | Record your verdict on a paper — why it matters, when to use it, why you ruled it out. Upserted; returned by list_library, so it is what a later session reads i |
| list_collections | List collections with paper counts. |
| create_collection | Create a named collection (get-or-create; no error on duplicate). |
| add_to_collection | Add a paper to a collection by name or id (also auto-saves). |
| remove_from_collection | Remove a paper from a collection (stays saved). |
| create_watch | Standing daily-evaluated saved search; get-or-create by name. Define it with a structured criteria filter (recommended) or a single seed selector. |
| list_watches | List watches with summary, last_evaluated_at, and pending_hits. |
| check_watches | Pull new matches since the last digest (read-only, idempotent). |
| update_watch | Edit a watch in place: rename, change novelty_min, or retarget its structured criteria (clears pending hits). Address by name or id. |
| preview_watch | Dry-run a structured criteria filter over recent papers without creating a watch; returns match_count and a sample to tune before saving. Read-only. |
| delete_watch | Delete a watch by name or id (idempotent). |
| find_gaps | "What am I missing?" for a collection or topic: foundational + frontier work you haven't saved (read-only, Pro). |
| ask_library | "Answer from my saved set": a cited synthesis over your library or one collection, grounded only in papers you've saved (read-only). The inverse of find_gaps. F |
{
"mcpServers": {
"scholar-feed": {
"command": "npx",
"args": [
"-y",
"scholar-feed-mcp@latest"
]
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
ComfyUI MCP server: knowledge base, workflow builder, real-time execution, models, plugins.
Comments pinned on a website, as a queue your coding agent takes, fixes and resolves.
A model context protocol server to chat with iRacing data.
A powerful MCP (Model Control Protocol) server that provides tools for performing web searches and finding similar content. This server is designed