Scholar Feed MCP Server
The Scholar Feed MCP Server enables search and analysis of 560,000+ CS/AI/ML research papers with LLM-powered summaries, novelty scoring, and deep research synthesis.
Search & Discovery — Full-text or semantic search with filters for category, novelty, recency, method, task, dataset, and contribution type; trending papers ranked by recency, citation velocity, and institutional reputation; batch lookup of up to 50 papers at once.
Paper Details & Content — Retrieve metadata, LLM-generated summaries, novelty scores, and structured extraction (methods, tasks, baselines); extract results/experiments from LaTeX source; fetch GitHub repo READMEs and file trees; export BibTeX for up to 50 papers.
Citation & Similarity — Explore citation graphs (incoming/outgoing) and discover related papers via embedding similarity and bibliographic coupling.
Benchmarks & Methods — Search 20k+ benchmarks, view SOTA leaderboards, analyze score distributions and timelines, search by method name (e.g., LoRA, DPO), compare 2–10 models side-by-side, and extract structured quantitative results from specific papers.
Authors — Discover researchers by topic or name; view detailed profiles (h-index, citations, global rank, top papers); retrieve paginated paper lists by author.
Research Synthesis — Run deep research sessions (60–300s) producing structured reports with clusters, gap analysis, and evidence chains; refine reports with follow-up questions.
Landscape Analysis — Aggregated topic stats: methods used, benchmarks evaluated, active authors, publication velocity, and novelty distribution.
Utility — Verify API connection, subscription plan, and daily usage limits.
Provides tools for searching and analyzing arXiv research papers, including full-text search, paper details retrieval, citation analysis, and trending paper discovery with LLM-powered novelty scoring.
Enables access to GitHub repositories associated with research papers, including fetching repository READMEs and file trees for code availability analysis.
Provides tools for extracting content from LaTeX source files of research papers, including results and experiments sections for detailed analysis.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Scholar Feed MCP Server find recent papers on efficient LLM inference with high novelty scores"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Scholar Feed MCP Server
Research paper search with ranking and citation tracking, for LLM engineering and academic research, without leaving Claude Code, Cursor, or any MCP client.
Most paper tools hand back a flat list. Scholar Feed ranks it: sort by relevance, by proven citation count, or by rising impact, then trace any paper's citation lineage forward and backward across 22M+ edges. 600k+ CS/AI/ML papers, updated daily, each with an LLM-generated summary and novelty score.
Scholar Feed indexes arXiv papers daily and ranks them on recency, citation velocity, institutional reputation, and code availability.
Quick Start
npx scholar-feed-mcp@latest initThis interactive wizard will:
Optionally ask for an API key (or skip for anonymous access)
Detect your MCP client (Claude Code, Cursor, or Claude Desktop)
Write the config and verify the connection
No API key required. Anonymous access gives you 200 calls/month, enough for a typical research session. For a higher quota (500/month per account) plus your library — collections, saved papers and watches — get a free key at scholarfeed.org/settings.
Try asking: "Search for recent papers on test-time compute scaling"
Related MCP server: Research MCP
What You Can Do
Technology scouting: "What novel research on retrieval-augmented generation was published this month?"
Literature review: "Find papers similar to 2401.04088 and export their BibTeX"
Trend monitoring: "What's trending in cs.CV this week? Summarize the top 3."
Author discovery: "Who are the top researchers working on efficient LLM inference?"
Field orientation: "Give me an orientation report on sparse mixture-of-experts architectures."
Installation
The fastest path is npx scholar-feed-mcp@latest init, which auto-detects your client and writes the config. To set it up by hand, every client launches the same stdio server (npx -y scholar-feed-mcp@latest); only the config-file location and the wrapper key differ.
Claude Desktop (one-click) installs without editing any config: download the .mcpb bundle from the latest release and open it (or drag it into Settings > Extensions). The installer shows one optional field for a Scholar Feed API key (sf_...): leave it blank for anonymous mode (200 calls/month), or paste a free key from scholarfeed.org/settings for 500/month.
Claude Code takes a one-line command:
# Anonymous (200 calls/month)
claude mcp add scholar-feed -- npx -y scholar-feed-mcp@latest
# With an API key (500 calls/month per account)
claude mcp add scholar-feed -e SF_API_KEY=sf_your_key_here -- npx -y scholar-feed-mcp@latestEvery other client takes this standard JSON block:
{
"mcpServers": {
"scholar-feed": {
"command": "npx",
"args": ["-y", "scholar-feed-mcp@latest"]
}
}
}To raise the quota to 500 calls/month, add "env": { "SF_API_KEY": "sf_your_key_here" } to the server entry. Get a free key at scholarfeed.org/settings.
Drop that block into the right config file:
Client | Config file | Notes |
Cursor |
| Restart Cursor. |
Claude Desktop | macOS: | Settings → Developer → Edit Config, then restart. |
Windsurf |
| Cascade → MCP icon → Configure, then refresh. |
Cline / Roo Code |
| MCP Servers sidebar icon → Configure. Cline and Roo Code share this format. |
Gemini CLI |
| |
LM Studio |
| Program tab → Install → Edit |
JetBrains (PyCharm / IntelliJ) | AI Assistant → MCP → Add → As JSON | Requires AI Assistant 2025.1+. |
A few clients need a different wrapper key or file format:
OpenAI Codex (~/.codex/config.toml, or $CODEX_HOME/config.toml if you set that) uses TOML, not JSON — the block above will not work. One file serves both the Codex CLI and the IDE extension.
[mcp_servers.scholar-feed]
command = "npx"
args = ["-y", "scholar-feed-mcp@latest"]
env = { SF_API_KEY = "sf_your_key_here" }Drop the env line to run keyless at 200 calls/month. On Windows, if Codex cannot launch the server, use command = "cmd" with args = ["/c", "npx", "-y", "scholar-feed-mcp@latest"].
VS Code: GitHub Copilot (.vscode/mcp.json) uses a servers key and an explicit type, and needs Copilot agent mode. You can also run MCP: Add Server from the Command Palette.
{
"servers": {
"scholar-feed": {
"type": "stdio",
"command": "npx",
"args": ["-y", "scholar-feed-mcp@latest"]
}
}
}Zed (settings.json) uses a context_servers key, and the "source": "custom" line is required (without it, Zed silently skips the entry).
{
"context_servers": {
"scholar-feed": {
"source": "custom",
"command": "npx",
"args": ["-y", "scholar-feed-mcp@latest"]
}
}
}Continue uses YAML, with mcpServers as a list, in ~/.continue/config.yaml (global) or .continue/config.yaml (workspace).
mcpServers:
- name: scholar-feed
type: stdio
command: npx
args:
- "-y"
- scholar-feed-mcp@latestProject-scoped (.mcp.json), to share the server across a repo:
{
"mcpServers": {
"scholar-feed": {
"command": "npx",
"args": ["-y", "scholar-feed-mcp@latest"],
"env": { "SF_API_KEY": "${SF_API_KEY}" }
}
}
}Windows: for any JSON config above, use "command": "cmd" and "args": ["/c", "npx", "-y", "scholar-feed-mcp@latest"].
Scholar Feed is a standard stdio MCP server, so any other MCP-compatible client works with the standard block too.
Available Tools (27)
Core Search & Discovery
Tool | Description | Key Parameters |
| Semantic + keyword search with filters. Also does similar-paper discovery, citation-scoped search, and trending. |
|
| Get full paper details by arXiv ID. Also handles batch lookup and BibTeX export. |
|
| Citation graph (outgoing refs or incoming citations) |
|
| Read a paper's text by section (abstract, introduction, related_work, method, results, conclusion, or |
|
Authors
Tool | Description | Key Parameters |
| Find researchers by topic/name query, or retrieve a profile by ID. |
|
| Co-authorship neighborhood for an author |
|
Embeddings
Tool | Description | Key Parameters |
| Get a 768-dim Gemini embedding for text (for HyDE and custom similarity). Pro-only, so anonymous/free callers get a 403 |
|
Research
Tool | Description | Key Parameters |
| Cheap retrieval orientation for a research area: top papers, subfields, open problems. No Pro quota. |
|
| Foundational work for a paper's niche via the citation graph (consensus-then-lift): niche_roots → field_level → discipline, with |
|
| "Is the method I use superseded — and by what?" Critique receipts + benchmark-dominance edges over ~10 LLM builder-problem families. No Pro quota. |
|
Library, Collections, Watches & Gap Analysis (require SF_API_KEY)
These MUTATE or read the authenticated user's account. The core read/search tools above work anonymously; these need a key.
Tool | Description | Key Parameters |
| Bookmark a paper to your library (idempotent; feeds personalization). |
|
| Remove a paper from your library (idempotent). |
|
| "More like this" calibration signal for the For You feed (insert-only). |
|
| List your saved papers, newest first (includes your notes). |
|
| Record your verdict on a paper — why it matters, when to use it, why you ruled it out. Upserted; returned by |
|
| List collections with paper counts. | (none) |
| Create a named collection (get-or-create; no error on duplicate). |
|
| Add a paper to a collection by name or id (also auto-saves). |
|
| Remove a paper from a collection (stays saved). |
|
| Standing daily-evaluated saved search; get-or-create by name. Define it with a structured |
|
| List watches with summary, | (none) |
| Pull new matches since the last digest (read-only, idempotent). |
|
| Edit a watch in place: rename, change |
|
| Dry-run a structured |
|
| Delete a watch by name or id (idempotent). |
|
| "What am I missing?" for a collection or topic: foundational + frontier work you haven't saved (read-only, Pro). |
|
| "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 |
|
Novelty Score
Every paper has an llm_novelty_score from 0.0 to 1.0:
Range | Meaning | Example |
0.7+ | Paradigm shift or broad SOTA | New architecture that changes the field |
0.5-0.7 | Novel method with strong results | New training technique with clear gains |
0.3-0.5 | Incremental improvement | Applying known method to new domain |
<0.3 | Survey, dataset, or minor extension | Literature review, benchmark release |
Use novelty_min: 0.5 in search_papers to filter for genuinely novel work.
Rate Limits
Endpoint | Limit |
| 30/min |
| 30/min |
| 30/min |
| 10/min |
| 6/min |
| 20/min |
| 20/min |
| 30/min |
| 20/min |
| 20/min |
| 20/min |
| 10/min |
Responses include X-RateLimit-Limit, X-RateLimit-Remaining, and X-RateLimit-Reset headers.
Monthly volume quota (separate from the per-minute limits above, counted per account across all your keys): 200 calls/month anonymous (per IP), 500/month with a free key, 10,000/month on Pro. A smaller daily cap (100 / 200 / 2,000) sits underneath it as a burst guardrail so a runaway loop cannot spend a month in an hour; hitting it returns a 429 with scope: "burst" and leaves your monthly quota untouched. Read your remaining month from GET /v1/health (monthly_limit / usage_this_month) before a batch.
The AI synthesis tools have their own limits: ask_library is 20/month free, then 200/day on Pro; find_gaps is Pro-only (a 403 pro_required otherwise). embed_text needs an account of any tier — anonymous callers get a 403 account_required.
Example Response
search_papers with q: "attention mechanism" returns:
{
"papers": [
{
"arxiv_id": "2401.04088",
"title": "Attention Is All You Need (But Not All You Get)",
"authors": ["A. Researcher", "B. Scientist"],
"year": 2024,
"categories": ["cs.LG", "cs.AI"],
"primary_category": "cs.LG",
"arxiv_url": "https://arxiv.org/abs/2401.04088",
"has_code": true,
"github_url": "https://github.com/example/repo",
"citation_count": 42,
"rank_score": 0.73,
"llm_summary": "Proposes a sparse attention variant that reduces compute by 60% while matching dense attention accuracy on 5 benchmarks.",
"llm_novelty_score": 0.55
}
],
"total": 1847,
"page": 1,
"limit": 20,
"next_cursor": "eyJzIjogMC43MywgImlkIjogIjI0MDEuMDQwODgifQ=="
}Pass next_cursor back to get the next page (keyset pagination, which is more stable than page numbers for large result sets).
Environment Variables
Variable | Required | Default | Description |
| No | (none) | Your Scholar Feed API key (starts with |
| No | Production URL | Override API base URL |
Development
npm install
npm run build # Build to build/
npm run dev # Watch mode
npm run typecheck # Type check without emitting
npm test # Run testsContributing
See CONTRIBUTING.md for guidelines.
Troubleshooting
"Authentication failed: your SF_API_KEY is invalid" The key may have been revoked. Generate a new one at scholarfeed.org/settings. Or remove the key to use anonymous mode.
"Rate limit exceeded" or "Anonymous daily limit exceeded" Anonymous mode allows 200 calls/month. Get a free API key at scholarfeed.org/settings for 500 calls/month per account, plus your library.
Server shows as "failed" with no error — especially right after an update
The first launch (and the first launch after each new release) makes npx download the package. The published bin is a single self-contained file with no dependency tree to resolve, so this is fast — but on a slow link it can still outrun your client's start-up timeout, and the server then shows as "failed" with no detail. Fixes: (1) warm the cache by running it once in a terminal — npx -y scholar-feed-mcp@latest --version — then restart your client; (2) raise the MCP start-up timeout if your client supports it (Claude Code: MCP_TIMEOUT=60000). For the fastest, offline-capable launches, install once globally and point the config at it instead of npx:
npm install -g scholar-feed-mcp
# then in your MCP config: "command": "scholar-feed-mcp", "args": []Tool calls time out or fail silently
Ensure Node.js 18+ is installed (node --version). Older versions lack the native fetch API.
Stale npx cache
The config blocks above pin scholar-feed-mcp@latest, which re-resolves the newest version each launch. If you previously used an unpinned scholar-feed-mcp and are stuck on an old build: npx --yes scholar-feed-mcp@latest.
Windows: "command not found"
Use "command": "cmd" with "args": ["/c", "npx", "-y", "scholar-feed-mcp@latest"] in your MCP config.
About Scholar Feed
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.
Website: https://www.scholarfeed.org
REST API: https://api.scholarfeed.org/v1
Privacy
See our privacy policy.
License
Available Tools
25 toolsadd_to_collectionAdd to CollectionAInspect
Add a paper to a collection, addressed by collection_id OR collection_name (get-or-create by name — no need to look up an id first). Nest with "/": collection_name "AgentOPA/Formal" files the paper under an "AgentOPA" folder. MUTATES: also auto-saves the paper to the library. Idempotent (adding a paper already in the collection is a no-op). Requires SF_API_KEY.
Inputs: arxiv_id (required), collection_name, collection_id. Returns: ok, message, action, arxiv_id, +2 more
ask_libraryAsk LibraryARead-onlyInspect
Answer a question using ONLY the papers you've saved — a synthesis over your library (or one collection) with inline [arXiv-ID] citations. The inverse of find_gaps (which finds important work you're MISSING): ask_library reasons over what you HAVE. Optionally scope to one collection (collection_name OR collection_id); omit both to use your whole library. Read-only. Requires SF_API_KEY (it reads your saved set). Free accounts get 1 question/month; Pro raises this to 200/day.
Inputs: question (required), collection_name, collection_id, limit. Returns: answer, citations, papers, ok, +1 more
check_watchesCheck WatchesARead-onlyInspect
Pull new matching papers since the last digest delivery, in the same shape as search_papers results. Optionally scope to one watch by watch_name OR watch_id; omit both for all watches. Read-only and idempotent — does NOT advance any watermark (only digest delivery does), so it is safe to call repeatedly (no mark-on-read). This is the in-session 'anything new on my watches?' pull. Requires SF_API_KEY.
Inputs: watch_name, watch_id, limit. Returns: papers, total, page, limit, +8 more
co_author_graphCo-Author GraphARead-onlyInspect
Find the co-authorship neighborhood of one or more authors. Given a list of author_ids, returns edges {from, to, papers_count, last_collab_year} where 'from' is one of the input authors and 'to' is any co-author appearing on a shared paper within the window. Use for AC reviewer triage (find conflicts), disambiguating researchers (who do they actually work with?), or expanding an author seed into a research community. window_years defaults to 10. Result is capped at 500 edges, sorted by papers_count DESC.
Inputs: author_ids (required), window_years. Returns: queried_author_ids, window_years, edge_count, edges
create_collectionCreate CollectionAInspect
Create a new named collection. MUTATES. If a collection with that name already exists, returns the existing one (get-or-create — never errors on duplicate). Use "/" to nest under a folder, e.g. "AgentOPA/Formal" — the folder is derived from the name, so there is no parent to create first. Requires SF_API_KEY.
Inputs: name (required). Returns: ok, message, action, arxiv_id, +2 more
create_watchCreate WatchAInspect
Create a standing watch — evaluated daily against newly-indexed papers, surfacing new matches via the email digest and via check_watches. MUTATES. Get-or-create by name (re-creating with an existing name returns it unchanged — never errors on duplicate). TWO forms: (1) the v2 STRUCTURED filter via criteria (collections/authors/categories/text/has_code/min_novelty/similar, AND-composed) — the composable, agent-tunable form, recommended; tune it with preview_watch first, and edit later with update_watch. Structured watches rank by 'rising' (forecasted breakout impact) by default, and tighten with min_impact_pct for an anti-noise watch that surfaces only the breakout papers in your niche. (2) a single legacy seed selector (q OR collection_name OR collection_id OR anchor_paper_id); if criteria is given it takes precedence. Requires SF_API_KEY.
Inputs: name (required), novelty_min, q, collection_name, +7 more. Returns: ok, message, action, arxiv_id, +2 more
delete_watchDelete WatchADestructiveInspect
Delete a watch, addressed by watch_id OR name. MUTATES. Idempotent: deleting a non-existent watch is a no-op (no error). To change a watch in place (rename / novelty_min / retarget criteria) use update_watch instead of delete-and-recreate. Requires SF_API_KEY.
Inputs: name, watch_id. Returns: ok, message, action, arxiv_id, +2 more
embed_textEmbed TextARead-onlyInspect
Embed a text string into a 768-dim Gemini Flash vector. Use for HyDE-style retrieval: (1) write a hypothetical short paper that would perfectly answer the user's query, (2) embed it with task_type='RETRIEVAL_DOCUMENT' (default — matches the corpus embedding side), (3) pass the resulting embedding back through search-style tools to find real papers nearest to the hypothetical. task_type='RETRIEVAL_QUERY' matches the query side and is useful for direct user-query embedding without HyDE. Pro-only — requires an SF_API_KEY on a Pro account; anonymous and free callers get a 403 pro_required. Cost: ~$0.0001/call; rate-limited at 30/minute per API key.
Inputs: text (required), task_type. Returns: embedding, model, task_type, dimensions, +1 more
fetch_fulltextFetch Full TextARead-onlyInspect
Extract paper content from an arXiv paper's LaTeX source. Two modes: 'results' (default) returns 800 chars of results/experiments + 3 table captions. 'all' returns full paper sections (abstract, introduction, related work, method, results, conclusion) at up to 3000 chars each + 5 table captions. ~62% of arXiv papers have LaTeX source. May take a few seconds.
Inputs: arxiv_id (required), sections. Returns: source, arxiv_id, results_text, sections, +1 more
find_authorFind AuthorARead-onlyInspect
Two-mode author tool — replaces discover_authors and get_author. Provide exactly one of q or id. Q-MODE (q=...): search for researchers by topic or name — uses embedding similarity for topics ('efficient LLM inference'), fuzzy matching for names ('Yann LeCun'). Returns a list of matching authors with author_id, name, h_index, total_papers, primary_field, research_topics. ID-MODE (id=...): look up a single author profile by author_id (obtained from a previous q-mode call or from co_author_graph results). Returns h-index, total citations, global rank, primary field, novelty score distribution, research topics, code/venue scores, years active, and their top 10 papers by rank score.
Inputs: q, id, field, limit. Returns: query, search_type, total, authors, +9 more
find_gapsFind Research GapsARead-onlyInspect
Find important work you HAVEN'T saved, for a collection or topic — a 'what am I missing?' analysis. Returns two buckets: foundational_gaps (canonical citation-graph anchors in the niche, not in your library) and frontier_gaps (recent high-novelty work in the niche, not yet saved). Provide exactly one seed: collection_name OR collection_id OR topic. The backend derives the niche, runs lineage + recent-novelty search, and subtracts your saved set. Read-only. Requires SF_API_KEY (it needs your library to subtract) and is a Pro feature — free accounts receive an upgrade prompt.
Inputs: collection_name, collection_id, topic, scope, +1 more. Returns: foundational_gaps, frontier_gaps, ok, message
get_citationsGet CitationsARead-onlyInspect
Get the citation graph for a paper, sorted by citing-paper rank_score (highest-impact first). 'citing' = outgoing references this paper cites; 'cited_by' = incoming citations from other papers. Default response is a lean 12-field shape per paper — pass verbose=true for the full 28-field shape.
Inputs: arxiv_id (required), direction, limit, fields, +2 more. Returns: papers, total, page, limit, +8 more
get_field_orientationGet Field OrientationARead-onlyInspect
Returns CANDIDATE FOUNDATIONAL PAPERS for a research topic — cheap retrieval only, no synthesis. Ranks papers by a blend of citation count (0.6 weight, captures importance) and semantic similarity to your topic (0.4 weight). Use this to bootstrap a literature survey or get a fast sense of the landscape. For a synthesized orientation report (key concepts, open problems, reading order), use the /field-guide skill which calls this tool internally. Does not require a Pro API key — no LLM calls are made.
Inputs: topic (required), limit. Returns: papers, total, page, limit, +8 more
get_foundational_lineageGet Foundational LineageARead-onlyInspect
Returns the FOUNDATIONAL WORK FOR A PAPER'S NICHE via the citation graph — the relative question ('what is foundational for THIS paper's specific sub-field', often itself only modestly cited) rather than the obvious global landmarks. Anchors on the paper, takes its embedding neighbourhood as the niche, and ranks what the niche cites into three tiers: niche_roots (the niche-specific foundations, ranked by how specifically the neighbourhood builds on them — surfaces canonical anchors that semantic search misses), field_level (broader secondary foundations), and discipline (universal landmarks like Attention Is All You Need, collapsed out of the way). Each paper carries cited_by_in_niche evidence so the claim is grounded, not asserted. Use this to trace prior art / lineage for a paper, or to find the canonical methods a niche is built on. Complements get_field_orientation (which is topic-anchored and retrieval-only). No Pro key and no LLM calls required.
Inputs: anchor_paper_id (required), scope, generality_ceiling, limit. Returns: anchor, scope, niche_size, tiers, +4 more
get_paperGet PaperARead-onlyInspect
Get full details for one or more papers by arXiv ID. Pass a single-element array for one paper; pass multiple IDs to batch-fetch up to 50 papers in one call (replaces the removed batch_lookup tool). Pass format='bibtex' to get a .bib citation entry (replaces the removed export_bibtex tool — bibtex is single-paper only; for multi-paper bibtex, call repeatedly). Default returns a lean 14-field shape (arxiv_id, title, authors, year, categories, has_code, github_url, citation_count, venue_name, llm_summary, llm_significance, llm_novelty_score, impact_pct, impact_tier — where impact_pct is the ML-forecast per-category impact percentile 0-100 and impact_tier its A+/A/B/C/D grade; both NULL on older papers outside the recent scoring window). Pass verbose=true for the full shape with structured extraction (method_name, contribution_type, task_category, datasets, baselines) and institution_tags. Use fields='arxiv_id,title,abstract' to select an exact subset, or fetch_fulltext with sections='all' for the full paper.
Inputs: arxiv_ids (required), format, fields, verbose. Returns: papers, total, page, limit, +13 more
like_paperLike PaperAInspect
Like a paper — a 'more like this' calibration signal that tunes the user's For You feed toward similar work. INSERT-only and idempotent (liking twice is a no-op, never un-likes). Distinct from save_paper: like expresses taste for ranking; save bookmarks for later reading. Requires SF_API_KEY.
Inputs: arxiv_id (required). Returns: ok, message, action, arxiv_id, +2 more
list_collectionsList CollectionsARead-onlyInspect
List the authenticated user's collections (named groups of saved papers) with paper counts. Read-only. Use before add_to_collection to see existing collections. Requires SF_API_KEY.
Inputs: no named parameters. Returns: collections, ok, message
list_libraryList LibraryARead-onlyInspect
List the authenticated user's saved papers (their library), newest first. Read-only. Use this to review a reading list or to see what's already saved before saving more. Requires SF_API_KEY.
Inputs: limit, page. Returns: papers, total, page, limit, +8 more
list_watchesList WatchesARead-onlyInspect
List the authenticated user's watches with name, a one-line definition summary, last_evaluated_at, and pending_hits (count of new matches since the last digest delivery). Read-only. Use before create_watch to see what's already tracked. Requires SF_API_KEY.
Inputs: no named parameters. Returns: watches, ok, message
preview_watchPreview WatchARead-onlyInspect
Dry-run a structured filter over recent papers WITHOUT creating a watch — the tuning loop. Returns {window_days, needs_similarity, match_count, sample} so you can iterate (add a category, raise min_novelty, switch the collection relation) before saving with create_watch. Structured watches rank by 'rising' (forecasted breakout impact) by default, and tighten with min_impact_pct for an anti-noise watch that surfaces only the breakout papers in your niche. NOTE: for a similarity filter, match_count is capped at 200 (the cosine fetch window) and so saturates at 200 on broad/hot topics — tune by the sample scores and narrow with categories/min_novelty (or a higher similar floor) rather than relying on match_count alone. Read-only. Requires SF_API_KEY.
Inputs: criteria (required), recency_days. Returns: window_days, needs_similarity, match_count, sample, +2 more
remove_from_collectionRemove from CollectionADestructiveInspect
Remove a paper from a collection, addressed by collection_id OR collection_name. MUTATES (the paper stays in your library; it's only removed from this collection). Idempotent. Requires SF_API_KEY.
Inputs: arxiv_id (required), collection_name, collection_id. Returns: ok, message, action, arxiv_id, +2 more
save_paperSave PaperAInspect
Save a paper to the authenticated user's Scholar Feed library (bookmark). MUTATES the library and feeds the user's personalization — saved papers are the strongest signal in the For You feed and the email digest. Idempotent: calling it again on an already-saved paper leaves it saved. Requires SF_API_KEY. To file it into a named collection in one step, use add_to_collection (that also saves).
Inputs: arxiv_id (required). Returns: ok, message, action, arxiv_id, +2 more
search_papersSearch PapersARead-onlyInspect
Search Scholar Feed's 600k+ CS/AI/ML paper corpus. Defaults to semantic (embedding) search — finds conceptually related papers even when the user's wording doesn't match the paper's title/abstract. Pass mode='keyword' for exact-string full-text search. CAVEAT: semantic search often misses old high-citation CANONICAL papers (e.g. foundational anchors like H2O for KV eviction, GRIT for unified embedding+generation) because the ranker prefers recent stylistically-matched papers. If you're hunting the canonical anchor for an area, parse the top-5 result abstracts for baseline mentions ('we compare against X, Y, Z'), then look the most-mentioned name up directly. Returns papers with LLM-generated summaries, novelty scores, and structured extraction data. Default response is a lean 14-field shape (arxiv_id, title, authors, year, categories, has_code, github_url, citation_count, venue_name, llm_summary, llm_significance, llm_novelty_score, impact_pct, impact_tier) — pass verbose=true or fields=... for the full shape with method/task/dataset extraction. RANKING BY IMPACT — two different notions, don't confuse them: (1) PROVEN impact = citations. For 'the important/seminal papers on topic X', pass sort='impactful' (most-cited among the relevant) or sort='balanced' (relevant AND well-cited). This is the right tool for established/foundational work. (2) FORECAST impact = impact_pct (0-100), an ML per-category percentile of PREDICTED citations, only computed for the last ~90 days; impact_tier is its A+/A/B/C/D grade. For 'what's rising/new in X' pass sort='trending' or filter impact_min=N — but NOTE impact_pct is NULL on everything older than ~90 days, so impact_min DROPS all established/canonical papers (it is NOT a way to find the influential papers in a niche — use sort='impactful' for that). Both impact notions are distinct from llm_novelty_score (new-idea-ness, an orthogonal filter). (3) ADOPTION impact = GitHub traction. Pass sort='community' to rank by real-world engineering adoption (stars + star-velocity) — the papers practitioners are actually running/building on, independent of citations or recency. Filter on it with min_stars=N (minimum GitHub stars) and has_code=true (only papers with a code release); has_code/min_stars surface RUNNABLE/ADOPTED work, the engineering counterpart to citations. github_url_exists=true is the stricter has_code (requires a linked repo). Supports filtering by category, novelty, recency, method, task, dataset, and contribution type — plus min_citations (minimum PROVEN citations, keeps established papers unlike the ~90-day impact_min) and an explicit date window via published_after / published_before ('YYYY-MM-DD', vs days' rolling lookback). v3 ABSORPTIONS: pass sort='trending' to rank by rising/forecast impact (impact_pct); pass anchor_paper_id to replicate find_similar (q is ignored in anchor mode, results carry similarity_score); pass scope_to_citations_of to restrict search to a paper's citation graph (replaces find_citations_about).
Inputs: q, sort, anchor_paper_id, scope_to_citations_of, +23 more. Returns: papers, total, page, limit, +8 more
unsave_paperUnsave PaperADestructiveInspect
Remove a paper from the authenticated user's Scholar Feed library. MUTATES the library. Idempotent: removing a paper that isn't saved leaves it unsaved. Note: the saved library is a superset of all collections, so un-saving a paper ALSO removes it from every collection it was in. To keep it filed in a collection, use remove_from_collection instead (that leaves the paper saved). Requires SF_API_KEY.
Inputs: arxiv_id (required). Returns: ok, message, action, arxiv_id, +2 more
update_watchUpdate WatchAInspect
Update an existing watch in place — rename, change novelty_min, or RETARGET its structured filter criteria. MUTATES. Address by watch_id OR name. Changing criteria replaces the definition and clears the watch's pending hits (so stale matches don't deliver); the next daily eval repopulates. Structured watches rank by 'rising' (forecasted breakout impact) by default, and tighten with min_impact_pct for an anti-noise watch that surfaces only the breakout papers in your niche. Tune the new criteria with preview_watch first. Requires SF_API_KEY.
Inputs: name, watch_id, new_name, novelty_min, +2 more. Returns: ok, message, action, arxiv_id, +2 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 25 tools
Most tools have clearly distinct purposes, but some overlap exists between search and discovery tools like ask_library, find_gaps, get_field_orientation, and get_foundational_lineage. However, detailed descriptions help differentiate them.
All tool names follow a consistent verb_noun pattern with underscores. Even compound names like get_foundational_lineage adhere to this pattern, making it predictable and easy for agents to understand.
25 tools is slightly above the typical 3-15 range, but the server covers a broad domain (library management, search, analysis, watches, collections, author discovery, etc.), justifying the count. It is not excessive.
The tool set provides comprehensive coverage: CRUD operations for libraries, collections, watches, and full analysis capabilities (citation graphs, gap analysis, author discovery, embedding). No obvious gaps exist for the intended purpose.
Maintenance
Related MCP Connectors
Search 340M+ academic papers — citation graphs, semantic similarity, and AI literature reviews.
Paper search (free), literature review packs, hallucinated-citation checks, arXiv digests, citations
Research intelligence for AI coding agents. 2M+ CS papers with evidence and tradeoffs.
Search arXiv/Semantic Scholar/OpenAlex + medical evidence (PubMed/Europe PMC) + LaTeX/PDF tools.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI-powered academic paper discovery, search, and analysis from arXiv with advanced features like semantic search, citation network analysis, and multi-format exports (BibTeX, RIS, JSON, CSV). Provides intelligent research assistance through specialized AI prompts for summarization, trend tracking, and literature review automation.17MIT
- AlicenseNot gradedqualityDmaintenanceEnables LLMs to search, analyze, and summarize academic research papers in real-time from arXiv, Semantic Scholar, and PubMed. Provides automatic deduplication, citation analysis, and BibTeX generation across multiple research databases.22 npmMIT
- AlicenseBqualityDmaintenanceEnables real-time tracking of AI/LLM research progress by searching and aggregating content from arXiv, GitHub, Hugging Face, and Papers with Code. Supports intelligent search, automated daily/weekly research summaries, and covers 15+ AI research areas with smart caching.8MIT
- FlicenseNot gradedqualityBmaintenanceEnables researchers to search ArXiv papers, extract key insights (problems, methods, results) from abstracts, and perform ML-powered analysis including topic modeling, trend visualization, and author collaboration networks.-