# openags/paper-search-mcp

MCP, CLI, Skills for searching and downloading academic papers from multiple sources like arXiv, PubMed, bioRxiv, etc.

Repository: https://github.com/openags/paper-search-mcp
Canonical: https://ross.abutalabs.com/products/paper-search-mcp
Language: Python
License: MIT
License Family: permissive
Topics: ai-scientist, arxiv-papers, mcp-server, paper-search
Last push: 2026-08-17T05:39:02+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 35, longevity 36
- inputs: {"age_days": 514, "days_push": 16, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2499, forks 250 (observed 2026-08-28T04:06:56.752541+00:00)

## What it is
A Python-based MCP server, CLI, and Claude Code skill for searching and downloading academic papers from open sources like arXiv, PubMed, and bioRxiv. It provides unified multi-source search with deduplication, PDF download with open-access fallbacks, and text extraction for LLM-driven research workflows.

## Use cases
- search academic papers across arxiv and pubmed
- download open-access pdfs of research papers
- give claude access to a paper search mcp server
- extract text from academic paper pdfs for llm workflows
- find papers for an ai scientist pipeline
- literature review search from the command line

## When to choose
- you need a free-first, multi-source academic paper search tool for MCP clients like Claude Desktop
- you want standardized, deduplicated search results and PDF downloads for AI research agents
- you prefer open-access sources with optional API keys for better coverage

## When to avoid
- you need paid or subscription-based database access like Scopus or Web of Science as a core feature
- you need a full graphical reference manager rather than a search/download tool
- you require guaranteed full-text retrieval from every source, since coverage varies by publisher

## Facets
- artifact type: service
- maturity: active
- function: mcp, search-engine, http-client, pdf, cli
- domain: artificial-intelligence, education, developer-tools
- platform: python, cli, self-hosted, cross-platform
- tags: mcp-server, academic-papers, arxiv, pubmed, literature-search, pdf-download, claude, ai-research, search, natural-language-processing, docker

## Member repositories
- openags/paper-search-mcp (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:56.752541+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:27:00.209445+00:00, confidence not recorded.
  - readme: https://github.com/openags/paper-search-mcp (fetched 2026-08-28T04:06:56.752541+00:00, sha 0542dae12b85)
  - registry_pypi: https://pypi.org/pypi/paper-search-mcp/json (fetched 2026-08-29T10:09:27.179980+00:00, sha 81d5a8f5aa34)
- Data as of 2026-08-30T08:39:29.467469+00:00.