paper-fetch MCP — Сценарии использования, Установка & Живое демо

Зачем использовать

Ключевые функции

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

Живое демо

Как выглядит на практике

paper-fetch-skill.replay ▶ готово

0/0

Установка

Выберите клиент

~/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
    }
  }
}

Откройте Claude Desktop → Settings → Developer → Edit Config. Перезапустите после сохранения.

~/.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 использует ту же схему mcpServers, что и Claude Desktop. Конфиг проекта приоритетнее глобального.

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
    }
  }
}

Щёлкните значок MCP Servers на боковой панели Cline, затем "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
    }
  }
}

Тот же формат, что и Claude Desktop. Перезапустите Windsurf для применения.

~/.continue/config.json

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

Continue использует массив объектов серверов, а не 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"
        ]
      }
    }
  }
}

Добавьте в context_servers. Zed перезагружается автоматически.

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

Однострочная команда. Проверить: claude mcp list. Удалить: claude mcp remove.

Сценарии использования

Реальные сценарии: paper-fetch

Pull all PDFs for a literature review reading list

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

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

Предварительные требования

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

Поток

Hand over the list

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

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

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

→ Status per miss
Index the results

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

→ Browsable index

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

Подводные камни

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

Сочетать с: filesystem

Chase citations one hop at a time

👤 Deep researchers following reference chains ⏱ ~20 min intermediate

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

Поток

Start with the seed

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

→ Paper downloaded; referenced DOIs listed
Fetch the next ring

Download those 10 too.✓ Скопировано

→ Batch download

Итог: A mini research trail in your file system.

Сочетать с: arxiv

Комбинации

Сочетайте с другими MCP — эффект x10

paper-fetch-skill + arxiv

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

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

paper-fetch-skill + filesystem

Organized local library

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

paper-fetch-skill + infinite-gratitude-skill

Multi-agent research with real PDFs

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

Инструменты

Что предоставляет этот MCP

Инструмент	Входные данные	Когда вызывать	Стоимость
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

Стоимость и лимиты

Во что обходится

Квота API: Unpaywall 100k/day (with email); arXiv and PMC are generous
Токенов на вызов: Low
Деньги: Free
Совет: Batch DOIs; respect rate limits to avoid being blocked.

Безопасность

Права, секреты, радиус поражения

Хранение учётных данных: Unpaywall email (not a secret) in env var

Исходящий трафик: Unpaywall, arXiv, PMC, bioRxiv APIs only

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

Устранение неполадок

Частые ошибки и исправления

PDF not found for a DOI you know is OA

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

Проверить: 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

Альтернативы

paper-fetch в сравнении

Альтернатива	Когда использовать	Компромисс
arxiv MCP	You only need arXiv, nothing else	Narrower scope
Manual browser + Zotero	Small reading lists	Tedious at scale

Ещё

Ресурсы

📖 Читать официальный README на GitHub

🐙 Открытые задачи

🔍 Все 400+ MCP-серверов и Skills