Scholar Feed MCP Server

Search 600,000+ CS/AI/ML research papers with LLM-generated novelty analysis, without leaving Claude Code, Cursor, or any MCP client. Built for researchers running a literature review where they already work: search, trace citations, pull full text, and export BibTeX in the same session.

Scholar Feed indexes arXiv papers daily and ranks them using a multi-signal scoring system (recency, citation velocity, institutional reputation, code availability). Each paper has an LLM-generated summary and novelty score.

Quick Start

npx scholar-feed-mcp 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 100 calls/day, enough for a typical research session. For higher limits (1,000/day per account), 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 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); only the config-file location and the wrapper key differ.

Claude Code takes a one-line command:

# Anonymous (100 calls/day)
claude mcp add scholar-feed -- npx -y scholar-feed-mcp

# With an API key (1,000 calls/day per account)
claude mcp add scholar-feed -e SF_API_KEY=sf_your_key_here -- npx -y scholar-feed-mcp

Every other client takes this standard JSON block:

{
  "mcpServers": {
    "scholar-feed": {
      "command": "npx",
      "args": ["-y", "scholar-feed-mcp"]
    }
  }
}

To raise limits to 1,000 calls/day, 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:

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

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"]
    }
  }
}

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"]
    }
  }
}

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

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

{
  "mcpServers": {
    "scholar-feed": {
      "command": "npx",
      "args": ["-y", "scholar-feed-mcp"],
      "env": { "SF_API_KEY": "${SF_API_KEY}" }
    }
  }
}

Windows: for any JSON config above, use "command": "cmd" and "args": ["/c", "npx", "-y", "scholar-feed-mcp"].

Scholar Feed is a standard stdio MCP server, so any other MCP-compatible client works with the standard block too.

Available Tools (25)

Core Search & Discovery

Authors

Embeddings

Research

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.

Novelty Score

Every paper has an llm_novelty_score from 0.0 to 1.0:

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

Rate Limits

Responses include X-RateLimit-Limit, X-RateLimit-Remaining, and X-RateLimit-Reset headers.

Daily volume quota (separate from the per-minute limits above, counted per account across all your keys): 100 calls/day anonymous, 1,000/day with a free key, 10,000/day on Pro. The AI synthesis tools have their own limits: ask_library is 1/month free, then 200/day on Pro; find_gaps and embed_text are Pro-only (a 403 pro_required otherwise).

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

Development

npm install
npm run build      # Build to build/
npm run dev        # Watch mode
npm run typecheck  # Type check without emitting
npm 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 100 calls/day. Get a free API key at scholarfeed.org/settings for 1,000 calls/day per account.

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
If you're stuck on an old version after an update: npx --yes scholar-feed-mcp@latest

Windows: "command not found"
Use "command": "cmd" with "args": ["/c", "npx", "-y", "scholar-feed-mcp"] in your MCP config.

Migrating from v1.x

v3.0.0 was a hard cutover with no deprecation window: the v1.x surface was consolidated into a smaller set of focused tools. If an agent still calls a removed v1.x tool, update it per this table. Full version history is in CHANGELOG.md.

License

MIT