yarxiv_mcp

MCP.Pizza Chef: IlyaGusev

This server connects your AI assistant to powerful tools for scientific research. You can search and download papers from arXiv and ACL Anthology, explore datasets on Hugging Face, get citation info from Semantic Scholar, and perform academic web searches. It also supports compiling LaTeX documents and reading PDFs. Designed for use with Claude Desktop and other MCP clients, it requires Python 3.12+ and developer setup steps like Docker or command-line installation.

Files/PDF
Other
Web/Research

Use This MCP server To

Search for scientific papers on arXiv by topic Download and read full scientific papers as PDFs or text Find citations and references for a research paper Search datasets on Hugging Face for machine learning projects Perform web searches related to academic topics Compile LaTeX documents into PDFs Ask questions about scientific documents using AI tools

README

Academia MCP

PyPI CI License smithery badge Verified on MseeP

MCP server with tools to search, fetch, analyze, and report on scientific papers and datasets.

Features

  • ArXiv search and download
  • ACL Anthology search
  • Hugging Face datasets search
  • Semantic Scholar citations and references
  • Web search via Exa, Brave, or Tavily
  • Web page crawler, LaTeX compilation, PDF reading
  • Optional LLM-powered tools for document QA and research proposal workflows

Requirements

  • Python 3.12+

Install

  • Using pip (end users):
pip3 install academia-mcp
  • For development (uv + Makefile):
uv venv .venv
make install

Quickstart

  • Run over HTTP (default transport):
python -m academia_mcp --transport streamable-http
# OR
uv run -m academia_mcp --transport streamable-http
  • Run over stdio (for local MCP clients like Claude Desktop):

yarxiv_mcp FAQ

Can I use this to search and download scientific papers from arXiv?
Yes — it lets you search arXiv and download papers directly within Claude Desktop or other MCP clients.
Can I analyze and get citations for scientific papers?
Yes — it provides tools to fetch citations and references from Semantic Scholar and analyze papers.
Do I need an API key or account to use this?
Some features like web search and LLM-powered tools require API keys, but basic paper search and download do not.
Which apps work with this server?
It works with Claude Desktop and any MCP client that supports server connections via stdio or HTTP.
How hard is it to set up?
Setup requires developer skills like installing Python 3.12+, running commands, or using Docker.
Can I compile LaTeX documents or extract text from PDFs?
Yes — with proper setup and workspace directory configured, you can compile LaTeX and read PDFs.
Is authentication required?
Authentication is optional and disabled by default; you can enable token-based access if needed.