Happy slice of mcp pizzaMCP.pizza

paper-search-mcp

MCP.Pizza Chef: openags

Finding a paper usually means visiting arXiv, then PubMed, then somewhere else, and comparing results by hand. Here your assistant checks many sources in one go, removes duplicates, downloads the ones that are freely available, and pulls out the text so you can ask questions about it. Covered sources include arXiv, PubMed, bioRxiv, medRxiv, Semantic Scholar, Crossref, OpenAlex, and Zenodo. Most work without any sign-up; a free key improves a few of them. It installs in Claude Desktop with one command.

Files/PDF
Web/Research

Use This MCP server To

Find recent papers on a topic across several archives Download the full text of an open-access paper Summarize a paper I just found without opening it Check whether a study has a freely readable version Pull the key findings from five papers at once

README

Paper Search MCP

A Model Context Protocol (MCP) server for searching and downloading academic papers from multiple sources. The project follows a free-first strategy: prioritize open and public data sources, support optional API keys when they improve stability or coverage, and keep source-specific connectors extensible for advanced users.

PyPI License Python smithery badge

Table of Contents

Overview

paper-search-mcp is a Python-based tool for searching and downloading academic papers from various platforms. It provides tools for searching papers, downloading PDFs, and extracting text, making it ideal for researchers and AI-driven workflows. It can be used as an MCP server (for Claude Desktop and other MCP clients) or as a Claude Code skill with a CLI interface.

Project Principles

paper-search-mcp FAQ

Do I need paid journal subscriptions?
No — it favours free and open sources, and only downloads full text where it is legally available.
Can I use this to gather papers for a literature review?
Yes — give it a topic and it searches many archives at once and removes repeats.
Does it need a key?
Not for most sources; an optional free key for Semantic Scholar or CORE raises the limits.
Which apps does it work in?
Claude Desktop is the documented setup, and it also runs as a Claude Code skill with a command-line version.
How hard is it to install?
A single Smithery command sets it up for Claude Desktop; other routes use uvx, pip, or Docker.
Can it read the paper, not just find it?
For open-access papers, yes — it downloads the file and pulls out the text for your assistant.