# Scholar Feed

Scholar Feed searches CS, AI, and ML papers, maps citations, and supports literature reviews inside an MCP client.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · 7974 installs
- Author: yangg40
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://smithery.ai/server/yangg40/scholar-feed
- Updated: 2026-06-06
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/yangg40-scholar-feed

## What it does

Scholar Feed gives an agent access to a corpus of 600,000+ CS, AI, and ML papers. `search_papers` uses semantic matching by default, while `keyword` mode looks for an exact string. The server can return paper details, citation links, arXiv full text, and BibTeX entries. It also covers author lookup, co-author networks, and novelty analysis.

You can save papers, organise them into collections, and tune the feed with likes. Watches track newly indexed papers and can be checked for fresh matches; other tools help explore gaps and ask questions about a saved library. `SF_API_KEY` is required for saving papers and working with the personal library.

## Requirements
- Remote server: `https://scholar-feed--yangg40.run.tools`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http scholar-feed https://scholar-feed--yangg40.run.tools
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add yangg40-scholar-feed --url https://scholar-feed--yangg40.run.tools
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "yangg40-scholar-feed": {
            "url": "https://scholar-feed--yangg40.run.tools"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "yangg40-scholar-feed": {
            "type": "http",
            "url": "https://scholar-feed--yangg40.run.tools"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http yangg40-scholar-feed https://scholar-feed--yangg40.run.tools
```

## When to use it
- find papers related by meaning rather than wording
- inspect a paper’s citation graph
- extract sections from an arXiv paper
- export a publication as BibTeX
- track new papers with saved watches

## Example prompts
- Find papers about retrieval for LLMs and compare the closest results.
- Show the citations for this paper, extract its results section, and return a BibTeX entry.
- Save the relevant papers to my library and create a watch for new work on this topic.

## Similar
- [semantic-scholar](https://affpapa.org/en/nevibecode/skills/semantic-scholar.md) — skill · 705 installs
- [deep-research](https://affpapa.org/en/nevibecode/skills/lingzhi227-deep-research.md) — skill · 2000 installs
- [arxiv](https://affpapa.org/en/nevibecode/skills/arxiv.md) — skill · 748 installs
- [ArXiv Scout](https://affpapa.org/en/nevibecode/mcp/arxiv-scout.md) — MCP server · 3426 installs
- [arxiv-viewer](https://affpapa.org/en/nevibecode/skills/arxiv-viewer.md) — skill · 133 installs
- [onecite](https://affpapa.org/en/nevibecode/mcp/onecite.md) — MCP server · ★ 68 repo stars

## Other versions with the same name
- [Scholar Feed · ygao2005](https://affpapa.org/en/nevibecode/mcp/scholar-feed.md) — ★ 14 repo stars

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
