/ Annuaire / Playground / paper-fetch
← Tous les serveurs ↗ GitHub
● Communauté Agents365-ai ⚡ Instantané

paper-fetch

par 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.

▶ Voir la démo 📦 Installer 💡 Cas d'usage

Pourquoi l'utiliser

Fonctionnalités clés

Démo en direct

Aperçu en pratique

paper-fetch-skill.replay ▶ prêt
0/0

Installation

Dépôt de l’auteur · Documentation officielle des Skills Claude

Cas d'usage

Usages concrets : paper-fetch

Pull all PDFs for a literature review reading list

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

Quand l'utiliser : You have 40 DOIs from a literature search and want to skim them without 40 browser clicks.

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

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

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

Chase citations one hop at a time

👤 Deep researchers following reference chains ⏱ ~20 min intermediate

Quand l'utiliser : You found a good paper and want the most-cited works it references.

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

Résultat : A mini research trail in your file system.

Combiner avec : arxiv

Combinaisons

Associez-le à d'autres MCPs pour un effet X10

paper-fetch-skill + arxiv

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

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

Organized local library

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

Multi-agent research with real PDFs

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

Outils

Ce que ce MCP expose

OutilEntréesQuand appelerCoût
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

Coût et limites

Coût d'exécution

Quota d'API
Unpaywall 100k/day (with email); arXiv and PMC are generous
Tokens par appel
Low
Monétaire
Free
Astuce
Batch DOIs; respect rate limits to avoid being blocked.

Sécurité

Permissions, secrets, portée

Stockage des identifiants : Unpaywall email (not a secret) in env var
Sortie de données : Unpaywall, arXiv, PMC, bioRxiv APIs only

Dépannage

Erreurs courantes et correctifs

PDF not found for a DOI you know is OA

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

Vérifier : 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

Alternatives

paper-fetch vs autres

AlternativeQuand l'utiliserCompromis
arxiv MCPYou only need arXiv, nothing elseNarrower scope
Manual browser + ZoteroSmall reading listsTedious at scale

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills