Scholar Feed

io.github.YGao2005Published by GitHub account YGao2005v3.20.0Updated Oct 24, 2026

Rank CS/AI/ML papers by citations, forecast impact, or code adoption; trace 23.2M citation edges.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingKnowledge & MemoryData & Analytics

Overview

AI-generated overview

Scholar Feed lets an assistant search and rank CS/AI/ML papers from arXiv, trace citation graphs, read full text, and manage a saved research library.

What you can do
Search and discover papers by keyword, semantic similarity, category, novelty score, trending status, or citation scope, and look up paper details or BibTeX in batches. Trace citation graphs forward and backward, and read full text by section for one or several papers. Get field orientations, foundational lineage for a paper's niche, and drift checks on whether a method has been superseded. Save, like, annotate and organize papers into collections, and run saved-search watches with previews and new-match checks. Ask cited questions over your saved library and find gaps in a collection or topic.
When to use it
Useful for literature reviews, technology scouting, trend monitoring, author discovery, and orienting yourself in an unfamiliar research area without leaving the chat client. Worth adding if you regularly work with arXiv papers and want ranked, summarized results plus citation context.
Requirements
Runs as a remote endpoint or as a local npm package via npx, which needs Node.js 18 or newer. No key is required for anonymous use; an optional SF_API_KEY from a free account raises the monthly quota and unlocks library features. Network access to the Scholar Feed API is needed.
Before you install
Anonymous use is capped at 200 calls per month per IP; a free key gives 500 and Pro 10,000, and some tools (embeddings, gap analysis) are Pro-only. Library tools write to your account: saving, liking, annotating, creating collections and watches, and deleting watches. SF_API_KEY is a secret and should be supplied through the environment, not committed to shared config. Queries and paper requests go to a third-party service.

Installation

In SourceWeft

  1. Open Scholar Feed in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.YGao2005%2Fscholar-feed-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "scholar-feed": {
      "type": "http",
      "url": "https://mcp.scholarfeed.org/mcp?src=mcp-registry"
    }
  }
}

README

[Scholar Feed]

Scholar Feed MCP Server

[CI] [npm version] [Node] [License: MIT] [smithery badge]

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

bash
npx scholar-feed-mcp@latest init

This interactive wizard will:

  1. Optionally ask for an API key (or skip for anonymous access)
  2. Detect your MCP client (Claude Code, Cursor, or Claude Desktop)
  3. 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"

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:

bash
# 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@latest

Every other client takes this standard JSON block:

json
{  "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:

ClientConfig fileNotes
Cursor.cursor/mcp.json (project) or ~/.cursor/mcp.json (global)Restart Cursor.
Claude DesktopmacOS: ~/Library/Application Support/Claude/claude_desktop_config.json; Windows: %APPDATA%\Claude\claude_desktop_config.jsonSettings → Developer → Edit Config, then restart.
Windsurf~/.codeium/windsurf/mcp_config.jsonCascade → MCP icon → Configure, then refresh.
Cline / Roo Codecline_mcp_settings.jsonMCP Servers sidebar icon → Configure. Cline and Roo Code share this format.
Gemini CLI~/.gemini/settings.json (or project .gemini/settings.json)
LM Studio~/.lmstudio/mcp.jsonProgram tab → Install → Edit mcp.json. Follows Cursor's notation.
JetBrains (PyCharm / IntelliJ)AI Assistant → MCP → Add → As JSONRequires AI Assistant 2025.1+.

A few clients need a different wrapper key or file format:

OpenAI Codex, VS Code (GitHub Copilot), Zed, Continue, and project-scoped configs

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.

toml
[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.

json
{  "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).

json
{  "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).

yaml
mcpServers:  - name: scholar-feed    type: stdio    command: npx    args:      - "-y"      - scholar-feed-mcp@latest

Project-scoped (.mcp.json), to share the server across a repo:

json
{  "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

ToolDescriptionKey Parameters
search_papersSemantic + keyword search with filters. Also does similar-paper discovery, citation-scoped search, and trending.q, category, novelty_min, days, sort, anchor_paper_id, scope_to_citations_of, mode, method_category, task, dataset, contribution_type, task_category, cursor, limit
get_paperGet full paper details by arXiv ID. Also handles batch lookup and BibTeX export.arxiv_ids, format, fields, verbose
get_citationsCitation graph (outgoing refs or incoming citations)arxiv_id, direction, limit, fields
fetch_fulltextRead 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 paper that cannot be extracted comes back as a failed entry, not a failed call.arxiv_id, arxiv_ids, sections

Authors

ToolDescriptionKey Parameters
find_authorFind researchers by topic/name query, or retrieve a profile by ID.q, id, field, limit
co_author_graphCo-authorship neighborhood for an authorauthor_ids, window_years

Embeddings

ToolDescriptionKey Parameters
embed_textGet a 768-dim Gemini embedding for text (for HyDE and custom similarity). Pro-only, so anonymous/free callers get a 403 pro_required.text, task_type

Research

ToolDescriptionKey Parameters
get_field_orientationCheap retrieval orientation for a research area: top papers, subfields, open problems. No Pro quota.topic, limit
get_foundational_lineageFoundational work for a paper's niche via the citation graph (consensus-then-lift): niche_roots → field_level → discipline, with cited_by_in_niche evidence. Surfaces canonical anchors semantic search misses. No Pro quota.anchor_paper_id, scope, generality_ceiling, limit
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.family, method, limit

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.

ToolDescriptionKey Parameters
save_paperBookmark a paper to your library (idempotent; feeds personalization).arxiv_id
unsave_paperRemove a paper from your library (idempotent).arxiv_id
like_paper"More like this" calibration signal for the For You feed (insert-only).arxiv_id
list_libraryList your saved papers, newest first (includes your notes).limit, page
annotate_paperRecord 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 instead of re-deriving.arxiv_id, note_text, action
list_collectionsList collections with paper counts.(none)
create_collectionCreate a named collection (get-or-create; no error on duplicate).name
add_to_collectionAdd a paper to a collection by name or id (also auto-saves).arxiv_id, collection_name, collection_id
remove_from_collectionRemove a paper from a collection (stays saved).arxiv_id, collection_name, collection_id
create_watchStanding daily-evaluated saved search; get-or-create by name. Define it with a structured criteria filter (recommended) or a single seed selector.name, novelty_min, criteria, recency_days, q, collection_name, collection_id, anchor_paper_id, scope_to_citations_of, author_id, category
list_watchesList watches with summary, last_evaluated_at, and pending_hits.(none)
check_watchesPull new matches since the last digest (read-only, idempotent).watch_name, watch_id, limit
update_watchEdit a watch in place: rename, change novelty_min, or retarget its structured criteria (clears pending hits). Address by name or id.name, watch_id, new_name, novelty_min, criteria, recency_days
preview_watchDry-run a structured criteria filter over recent papers without creating a watch; returns match_count and a sample to tune before saving. Read-only.criteria, recency_days
delete_watchDelete a watch by name or id (idempotent).name, watch_id
find_gaps"What am I missing?" for a collection or topic: foundational + frontier work you haven't saved (read-only, Pro).collection_name, collection_id, topic, scope, limit
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. Free 20/month, then Pro 200/day.question, collection_name, collection_id, limit

Novelty Score

Every paper has an llm_novelty_score from 0.0 to 1.0:

RangeMeaningExample
0.7+Paradigm shift or broad SOTANew architecture that changes the field
0.5-0.7Novel method with strong resultsNew training technique with clear gains
0.3-0.5Incremental improvementApplying known method to new domain
<0.3Survey, dataset, or minor extensionLiterature review, benchmark release

Use novelty_min: 0.5 in search_papers to filter for genuinely novel work.

Rate Limits

EndpointLimit
search_papers30/min
get_paper30/min
get_citations30/min
fetch_fulltext (single paper)10/min
fetch_fulltext (batch, 2-8 papers)6/min
find_author20/min
co_author_graph20/min
embed_text30/min
get_field_orientation20/min
get_foundational_lineage20/min
find_gaps20/min
ask_library10/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:

json
{  "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

VariableRequiredDefaultDescription
SF_API_KEYNo(none)Your Scholar Feed API key (starts with sf_). Without it, runs in anonymous mode (200 calls/month).
SF_API_BASE_URLNoProduction URLOverride API base URL

Development

bash
npm installnpm run build      # Build to build/npm run dev        # Watch modenpm run typecheck  # Type check without emittingnpm test           # Run tests

Contributing

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:

bash
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.

Privacy

See our privacy policy.

License

MIT

Source: README.md at commit 5ca5ede

Tools

0
SourceWeft has not read this server's tools yet.

Version history

1
  1. v3.20.0LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts