/ Diretório / Playground / paper-fetch
← Todos os servidores ↗ GitHub
● Comunidade Agents365-ai ⚡ Instantâneo

paper-fetch

por Agents365-ai · Agents365-ai/paper-fetch

Download open-access PDFs by DOI — pulls from Unpaywall, arXiv, PMC, bioRxiv. Legal, multi-source, built for research workflows.

Give it a DOI or citation; it finds a legally free version (preprint, PMC, institutional open access) and downloads the PDF. Falls back across Unpaywall, arXiv, PMC, and bioRxiv. No paywall bypass, no piracy — just making existing open-access options easier.

▶ Ver demo 📦 Instalar 💡 Casos de uso

Por que usar

Principais recursos

Demo ao vivo

Como fica na prática

paper-fetch-skill.replay ▶ pronto
0/0

Instalação

Repositório do autor · Documentação oficial de Skills do Claude

Casos de uso

Usos do mundo real: paper-fetch

Pull all PDFs for a literature review reading list

👤 Researchers, grad students, science writers ⏱ ~15 min beginner

Quando usar: You have 40 DOIs from a literature search and want to skim them without 40 browser clicks.

Fluxo
  1. Hand over the list
    Use paper-fetch. Here are 40 DOIs. Download the OA version of each to ~/papers/lit-review/.✓ Copiado
    → Progress per DOI; summary of found/unfound
  2. Handle misses
    For ones not found, tell me what's available (abstract-only? preprint missing?).✓ Copiado
    → Status per miss
  3. Index the results
    Make an index.md with title, year, and file path per downloaded paper.✓ Copiado
    → Browsable index

Resultado: A local folder of PDFs you can actually search.

Armadilhas
  • Some papers aren't legally OA anywhere — Skill reports the gap; request via your library's ILL for those
Combine com: filesystem

Chase citations one hop at a time

👤 Deep researchers following reference chains ⏱ ~20 min intermediate

Quando usar: You found a good paper and want the most-cited works it references.

Fluxo
  1. Start with the seed
    Use paper-fetch. Download this paper [DOI] and list its top-10 most-cited references.✓ Copiado
    → Paper downloaded; referenced DOIs listed
  2. Fetch the next ring
    Download those 10 too.✓ Copiado
    → Batch download

Resultado: A mini research trail in your file system.

Combine com: arxiv

Combinações

Combine com outros MCPs para 10× de alavancagem

paper-fetch-skill + arxiv

Prefer arXiv for preprints, fall back to Unpaywall for journal OA

Prefer arXiv preprints when present; otherwise use Unpaywall.✓ Copiado
paper-fetch-skill + filesystem

Organized local library

Save to ~/papers/<year>/<first-author>/✓ Copiado
paper-fetch-skill + infinite-gratitude-skill

Multi-agent research with real PDFs

Dojo explorer uses paper-fetch to ground claims in actual papers.✓ Copiado

Ferramentas

O que este MCP expõe

FerramentaEntradasQuando chamarCusto
fetch_by_doi DOI Per paper 1-3 API lookups
batch_fetch DOI list Lit reviews N * lookups
resolve_citation free-text citation Starting from citation text Crossref + Unpaywall

Custo e limites

O que custa rodar

Cota de API
Unpaywall 100k/day (with email); arXiv and PMC are generous
Tokens por chamada
Low
Monetário
Free
Dica
Batch DOIs; respect rate limits to avoid being blocked.

Segurança

Permissões, segredos, alcance

Armazenamento de credenciais: Unpaywall email (not a secret) in env var
Saída de dados: Unpaywall, arXiv, PMC, bioRxiv APIs only

Solução de problemas

Erros comuns e correções

PDF not found for a DOI you know is OA

Unpaywall occasionally lags; check oadoi.org directly or wait a day

Verificar: curl https://api.unpaywall.org/v2/<DOI>[email protected]
Rate limited

Space batches out; use the skill's rate-limit-aware batch mode

Wrong PDF downloaded (supplementary instead of main)

Some sources return supplements; rerun with prefer-main flag

Alternativas

paper-fetch vs. outros

AlternativaQuando usarTroca
arxiv MCPYou only need arXiv, nothing elseNarrower scope
Manual browser + ZoteroSmall reading listsTedious at scale

Mais

Recursos

📖 Leia o README oficial no GitHub

🐙 Ver issues abertas

🔍 Ver todos os 400+ servidores MCP e Skills