paper-fetch MCP — Cas d'usage, Installer & Démo en direct

Pourquoi l'utiliser

Fonctionnalités clés

DOI → PDF resolution across 4+ legal sources
Unpaywall integration for OA detection
arXiv / bioRxiv / PMC direct fetching
Multi-platform (Claude Code, generic Agent Skill)
Clear licensing respect — no sci-hub, no pirated content

Démo en direct

Aperçu en pratique

paper-fetch-skill.replay ▶ prêt

0/0

Installer

Choisissez votre client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "paper-fetch-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/Agents365-ai/paper-fetch",
        "~/.claude/skills/paper-fetch"
      ],
      "_inferred": true
    }
  }
}

Ouvrez Claude Desktop → Settings → Developer → Edit Config. Redémarrez après avoir enregistré.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "paper-fetch-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/Agents365-ai/paper-fetch",
        "~/.claude/skills/paper-fetch"
      ],
      "_inferred": true
    }
  }
}

Cursor utilise le même schéma mcpServers que Claude Desktop. La config projet l'emporte sur la globale.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "paper-fetch-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/Agents365-ai/paper-fetch",
        "~/.claude/skills/paper-fetch"
      ],
      "_inferred": true
    }
  }
}

Cliquez sur l'icône MCP Servers dans la barre latérale Cline, puis "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "paper-fetch-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/Agents365-ai/paper-fetch",
        "~/.claude/skills/paper-fetch"
      ],
      "_inferred": true
    }
  }
}

Même format que Claude Desktop. Redémarrez Windsurf pour appliquer.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "paper-fetch-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/Agents365-ai/paper-fetch",
        "~/.claude/skills/paper-fetch"
      ]
    }
  ]
}

Continue utilise un tableau d'objets serveur plutôt qu'une map.

~/.config/zed/settings.json

{
  "context_servers": {
    "paper-fetch-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/Agents365-ai/paper-fetch",
          "~/.claude/skills/paper-fetch"
        ]
      }
    }
  }
}

Ajoutez dans context_servers. Zed recharge à chaud à la sauvegarde.

claude mcp add paper-fetch-skill -- git clone https://github.com/Agents365-ai/paper-fetch ~/.claude/skills/paper-fetch

Une seule ligne. Vérifiez avec claude mcp list. Supprimez avec claude mcp remove.

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.

Prérequis

Skill installed — git clone https://github.com/Agents365-ai/paper-fetch ~/.claude/skills/paper-fetch
Unpaywall email for API access — Free; email is the API key: https://unpaywall.org/products/api

Déroulement

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
Handle misses

For ones not found, tell me what's available (abstract-only? preprint missing?).✓ Copié

→ Status per miss
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

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
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

Outil	Entrées	Quand appeler	Coût
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

This skill only retrieves legally open-access content. Do not modify it to bypass paywalls; respect publisher licensing.

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

Alternative	Quand l'utiliser	Compromis
arxiv MCP	You only need arXiv, nothing else	Narrower scope
Manual browser + Zotero	Small reading lists	Tedious at scale

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills