Enterprise DNA
M MCP Servers Developer low

YGao2005/scholar-feed-mcp

by Various

MCP server for searching 600,000+ CS/AI research papers with citation graphs, full text, embeddings, and BibTeX. Works with Claude Code, Cursor, and any MCP client. No signup requi

Y

MCP

YGao2005/scholar-feed-mcp

Added 7 June 2026

#ai #arxiv #bibtex #citations #claude #claude-code #cursor #literature-review

Overview

An MCP server that lets you search over 600,000 computer science and AI research papers. It provides citation graphs, full text, embeddings, and BibTeX exports and works with Claude Code, Cursor, and any MCP client without requiring signup.

Best for

Best for
Researchers and developers needing a lightweight offline-capable MCP server for CS/AI paper discovery

Use cases

  • Retrieve full text and metadata for CS/AI papers via MCP clients
  • Generate citation graphs and BibTeX references for literature reviews
  • Explore paper embeddings for similarity search and clustering

Notes

An MCP server that lets you search over 600,000 computer science and AI research papers. It provides citation graphs, full text, embeddings, and BibTeX exports and works with Claude Code, Cursor, and any MCP client without requiring signup.

7 stars on GitHub. Last updated 2026-06-07. Licensed MIT.

Use cases

  • Retrieve full text and metadata for CS/AI papers via MCP clients
  • Generate citation graphs and BibTeX references for literature reviews
  • Explore paper embeddings for similarity search and clustering

Pros

  • No signup or API key required to use
  • Works with popular MCP clients like Claude Code and Cursor
  • Includes citation graphs and embeddings for deeper analysis

Cons

  • Limited to 600,000 papers, much smaller than full academic indexes
  • Covers only computer science and AI, not other disciplines
  • Low community adoption (7 stars) suggests limited updates or support

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.

Pros

  • No signup or API key required to use
  • Works with popular MCP clients like Claude Code and Cursor
  • Includes citation graphs and embeddings for deeper analysis

Cons

  • Limited to 600,000 papers, much smaller than full academic indexes
  • Covers only computer science and AI, not other disciplines
  • Low community adoption (7 stars) suggests limited updates or support

Pairs with

Other entries in the index that connect to this one. Click through to see the chain.