Scholar Feed MCP Server

Search 512,000+ 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. Ask for your API key (get one at scholarfeed.org/settings)
2. Detect your MCP client (Claude Code, Cursor, or Claude Desktop)
3. Write the config and verify the connection

That's it. 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."

Deep dives — "Run a deep research session on 'reasoning in large language models'"

Manual Installation

Claude Code

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"],
      "env": { "SF_API_KEY": "sf_your_key_here" }
    }
  }
}

Claude Desktop (claude_desktop_config.json)

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

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 (12)

| Tool | Description | Key Parameters | |------|-------------|----------------| | check_connection | Verify API key, show plan and usage | — | | search_papers | Search by keyword with filters | q, category, novelty_min, days, cursor, limit | | get_paper | Get paper details by arXiv ID | arxiv_id | | find_similar | Find similar papers | arxiv_id, limit, days | | get_citations | Get citation graph | arxiv_id, direction, limit | | whats_trending | Today's trending papers | category, limit | | fetch_fulltext | Extract results/experiments from LaTeX | arxiv_id | | batch_lookup | Look up multiple papers at once | arxiv_ids (max 50) | | fetch_repo | Get GitHub repo README + file tree | arxiv_id | | export_bibtex | Export BibTeX for arXiv papers | arxiv_ids (max 50) | | deep_research | Multi-round research synthesis | topic, depth | | refine_research | Follow-up question on a completed research report | report_id, question, cluster_label, date_from, date_to |

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 | |----------|-------| | check_connection | 60/min | | search_papers | 30/min | | get_paper | 60/min | | find_similar | 20/min | | get_citations | 30/min | | whats_trending | 30/min | | fetch_fulltext | 10/min | | batch_lookup | 20/min | | fetch_repo | 10/min | | export_bibtex | 20/min | | deep_research | 5/min | | refine_research | 5/min |

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).

Verify Installation

After setup, ask your AI assistant to run check_connection. You should see:

{
  "status": "ok",
  "plan": "free",
  "key_name": "my-key",
  "usage_today": 0
}

Environment Variables

| Variable | Required | Default | Description | |----------|----------|---------|-------------| | SF_API_KEY | Yes | — | Your Scholar Feed API key (starts with sf_) | | SF_API_BASE_URL | No | Production URL | Override API base URL |

Troubleshooting

"SF_API_KEY environment variable is required" Your MCP client isn't passing the env var. Double-check the env block in your config matches the examples above.

"Authentication failed: your SF_API_KEY is invalid" The key may have been revoked. Generate a new one at scholarfeed.org/settings.

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