</>MCP Agents Market
MCP Server

scansci-pdf

by Rimagination879PythonUpdated 2026-09-10

Claude CodeClaude DesktopCodexZCodeCursorWindsurfClineCherry Studio

ScanSci PDF is an MCP server that enables AI agents to download academic papers by DOI, arXiv ID, or reference lists from over 20 parallel data sources including open access repositories, preprint servers, publisher APIs, and institutional access channels. It automatically routes around paywalls using WebVPN, CARSI federation authentication, EZProxy, or Elsevier API fast lanes (1-2 seconds per paper), with intelligent tier-based racing that tries OA direct links, gray sources, and institutional proxies in sequence. The server exposes 17 MCP tools covering single downloads, batch processing, literature search, citation export, and automated institutional login with session persistence.

Key Features

Downloads papers from 20+ sources (OA links, arXiv, PMC, EuropePMC, CORE, OpenAIRE, Unpaywall, LibGen, Sci-Hub) with parallel tier-based racing
Institutional access via 100+ university WebVPN channels, CARSI federated auth, EZProxy, and Elsevier API integration (1-2 sec/paper)
Batch processing with intelligent queue classification (OA / gray / institutional) and four-lane scheduling with automatic failover
Automatic Cloudflare/CAPTCHA handling, IP block detection with auto-stop, and session auto-healing (re-login on expiry)
Supplementary materials download, PDF-to-Markdown conversion for AI reading, and auto-renaming (Author_Year_Title.pdf)
17 MCP tools for single/batch downloads, search, citation export (BibTeX/RIS/EndNote), Zotero push, and diagnostics
Browser-based institutional login (credentials never touch the tool), proxy pool rotation, and Tor support for restricted sources
Docker deployment, HTTP remote mode, Web UI, and native plugins for Codex, ZCode, and Claude Code

Use Cases

  • 01Download a single paper by DOI or arXiv ID with automatic source selection and institutional access routing
  • 02Batch-download 1000+ papers from an Excel/CSV reference list with OA classification and multi-lane parallel processing
  • 03Search for recent high-impact papers on a topic and automatically download the full-text PDFs
  • 04Access paywalled Elsevier/Springer/Wiley papers via university WebVPN or CARSI federation without manual proxy setup
  • 05Export citation metadata (BibTeX, RIS, EndNote) and push downloaded papers to Zotero library
  • 06Download supplementary materials and convert PDFs to Markdown for AI-assisted reading and analysis

Related MCP Servers

View more

markitdown

Python tool for converting files and office documents to Markdown.

MCP Server187.8k

firecrawl

The context API to search, scrape, and interact with the web at scale. 🔥

MCP Server187.2k

prompts.chat

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

MCP Server171.7k

langflow

Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

MCP Server155.4k

scansci-pdf — FAQ

What is ScanSci PDF?+

ScanSci PDF is an MCP server (17 tools) that enables AI agents to download academic papers from 20+ parallel data sources, automatically routing through open access repositories, preprint servers, and institutional access channels (WebVPN, CARSI, EZProxy, Elsevier API) to bypass paywalls.

How do I install ScanSci PDF in Claude Code or Codex?+

For Claude Code or Codex, simply tell the agent: 'Install or update this plugin: https://github.com/Rimagination/scansci-pdf'. The agent will clone the repo, install dependencies, and register the MCP server. For manual installation: pip install scansci-pdf, then add the MCP server config to your client's settings.

Which AI clients work with ScanSci PDF?+

ScanSci PDF works with any MCP-compatible client including Claude Desktop, Cursor, Windsurf, Cline, Cherry Studio, Codex, ZCode, and Claude Code. It can also run in HTTP mode for remote deployment or as a standalone Web UI.

Do I need API keys or institutional access?+

No API keys are required for open access sources. For paywalled papers, you can optionally configure: (1) a free Elsevier API key for fast ScienceDirect downloads, or (2) institutional access via your university's WebVPN, CARSI, or EZProxy (100+ Chinese universities supported). Browser-based login keeps credentials local.

Is ScanSci PDF free to use?+

Yes, the tool itself is free and open-source (Apache 2.0 license). You only need institutional subscriptions or Elsevier API access if downloading paywalled papers; open access and preprint sources are always free.

How does it handle Cloudflare blocks and IP bans?+

ScanSci PDF uses cloakbrowser (Chromium 151 stealth engine) and FlareSolverr to bypass Cloudflare and CAPTCHAs. It auto-detects IP blocks from publishers and stops batch jobs after 3 consecutive failures. You can configure proxy pools, adjust concurrency/delays, or enable Tor for restricted sources.

How do I install scansci-pdf?+

Open the source repository on GitHub and follow its README. scansci-pdf is a mcp server — MCP Agents Market links you directly to the official repo.

Is scansci-pdf free?+

scansci-pdf is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.

Related searches

Research MCP ServersProductivity & Workflow MCP ServersDeveloper Tools MCP ServersBest SkillsBest PluginsBest AgentsTop rated listingsClaude Code toolsBrowse all categories