paper-fetch MCP — Anwendungsfälle, Installieren & Live-Demo

Warum nutzen

Hauptfunktionen

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

Live-Demo

In der Praxis

paper-fetch-skill.replay ▶ bereit

0/0

Installieren

Wählen Sie Ihren 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
    }
  }
}

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.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 nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die 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
    }
  }
}

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "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
    }
  }
}

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.continue/config.json

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

Continue nutzt ein Array von Serverobjekten statt einer 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"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

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

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: paper-fetch

Pull all PDFs for a literature review reading list

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

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

Voraussetzungen

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

Ablauf

Hand over the list

Use paper-fetch. Here are 40 DOIs. Download the OA version of each to ~/papers/lit-review/.✓ Kopiert

→ Progress per DOI; summary of found/unfound
Handle misses

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

→ Status per miss
Index the results

Make an index.md with title, year, and file path per downloaded paper.✓ Kopiert

→ Browsable index

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

Fallstricke

Some papers aren't legally OA anywhere — Skill reports the gap; request via your library's ILL for those

Kombinieren mit: filesystem

Chase citations one hop at a time

👤 Deep researchers following reference chains ⏱ ~20 min intermediate

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

Ablauf

Start with the seed

Use paper-fetch. Download this paper [DOI] and list its top-10 most-cited references.✓ Kopiert

→ Paper downloaded; referenced DOIs listed
Fetch the next ring

Download those 10 too.✓ Kopiert

→ Batch download

Ergebnis: A mini research trail in your file system.

Kombinieren mit: arxiv

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

paper-fetch-skill + arxiv

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

Prefer arXiv preprints when present; otherwise use Unpaywall.✓ Kopiert

paper-fetch-skill + filesystem

Organized local library

Save to ~/papers/<year>/<first-author>/✓ Kopiert

paper-fetch-skill + infinite-gratitude-skill

Multi-agent research with real PDFs

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

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen	Kosten
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

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: Unpaywall 100k/day (with email); arXiv and PMC are generous
Tokens pro Aufruf: Low
Kosten in €: Free
Tipp: Batch DOIs; respect rate limits to avoid being blocked.

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: Unpaywall email (not a secret) in env var

Datenabfluss: Unpaywall, arXiv, PMC, bioRxiv APIs only

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

Fehlerbehebung

Häufige Fehler und Lösungen

PDF not found for a DOI you know is OA

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

Prüfen: 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

Alternativen

paper-fetch vs. andere

Alternative	Wann stattdessen	Kompromiss
arxiv MCP	You only need arXiv, nothing else	Narrower scope
Manual browser + Zotero	Small reading lists	Tedious at scale

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen