paper-fetch MCP — 사용 사례, 설치 & 라이브 데모

왜 쓰나요

핵심 기능

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

라이브 데모

실제 사용 모습

paper-fetch-skill.replay ▶ 준비됨

0/0

설치

클라이언트 선택

~/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
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config 열기. 저장 후 앱 재시작.

~/.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
    }
  }
}

Cursor는 Claude Desktop과 동일한 mcpServers 스키마 사용. 프로젝트 설정이 전역보다 우선.

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
    }
  }
}

Cline 사이드바의 MCP Servers 아이콘 클릭 후 "Edit Configuration" 선택.

~/.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
    }
  }
}

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

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

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.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"
        ]
      }
    }
  }
}

context_servers에 추가. 저장 시 Zed가 핫 리로드.

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

한 줄 명령. claude mcp list로 확인, claude mcp remove로 제거.

사용 사례

실전 활용법: paper-fetch

Pull all PDFs for a literature review reading list

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

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

사전 조건

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

흐름

Hand over the list

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

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

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

→ Status per miss
Index the results

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

→ Browsable index

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

함정

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

함께 쓰기: filesystem

Chase citations one hop at a time

👤 Deep researchers following reference chains ⏱ ~20 min intermediate

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

흐름

Start with the seed

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

→ Paper downloaded; referenced DOIs listed
Fetch the next ring

Download those 10 too.✓ 복사됨

→ Batch download

결과: A mini research trail in your file system.

함께 쓰기: arxiv

조합

다른 MCP와 조합해 10배 효율

paper-fetch-skill + arxiv

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

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

paper-fetch-skill + filesystem

Organized local library

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

paper-fetch-skill + infinite-gratitude-skill

Multi-agent research with real PDFs

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

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
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

비용 및 제한

운영 비용

API 쿼터: Unpaywall 100k/day (with email); arXiv and PMC are generous
호출당 토큰: Low
금액: Free
팁: Batch DOIs; respect rate limits to avoid being blocked.

보안

권한, 시크릿, 파급범위

자격 증명 저장: Unpaywall email (not a secret) in env var

데이터 외부 송신: Unpaywall, arXiv, PMC, bioRxiv APIs only

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

문제 해결

자주 발생하는 오류와 해결

PDF not found for a DOI you know is OA

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

확인: 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

대안

paper-fetch 다른 것과 비교

대안	언제 쓰나	단점/장점
arxiv MCP	You only need arXiv, nothing else	Narrower scope
Manual browser + Zotero	Small reading lists	Tedious at scale

paper-fetch