Scholar Feed MCP Server

Search 600,000+ CS/AI/ML research papers with LLM-powered novelty analysis from Claude Code, Cursor, or any MCP client.

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"

Migrating from v1.x to v3.0.0

v3.0.0 is a hard cutover — there is no deprecation window. The previous v1.x tool surface was consolidated down to 8 focused tools. Existing agents using removed tools will need to update their calls before upgrading.

Breaking changes — full replacement table

The 8 v3 tools

New in v3.0.0 (reaching npm for the first time):

• find_author — merged discover_authors + get_author into a single tool with exactly-one-of (q or id) semantics.

• get_field_orientation — the cheap-retrieval half of the former field_guide, demoted from tool to skill in v3 but re-added as a lightweight tool (0.6 × citation score + 0.4 × cosine similarity; no DeepSeek, no Pro quota). Pairs with the /field-guide skill for deeper orientation.

• co_author_graph and embed_text — shipped in the local v2.1.0 build but never published to npm; v3.0.0 is the first public release of both.

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."

Manual Installation

Claude Code

# Without API key (anonymous, 100 calls/day)
claude mcp add scholar-feed -- npx -y scholar-feed-mcp

# With 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

Cursor (.cursor/mcp.json)

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

To add an API key, add "env": { "SF_API_KEY": "sf_your_key_here" } to the config.

Claude Desktop (claude_desktop_config.json)

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

Project-scoped (.mcp.json)

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

Windows note: Use "command": "cmd" and "args": ["/c", "npx", "-y", "scholar-feed-mcp"].

Available Tools (8)

Core Search & Discovery

Authors

Embeddings

Research

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.

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 — 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.

License

MIT