Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free
Reach 47,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here

Works with

Claude CodeClaude DesktopCursorVS CodeClineCodex CLIOpenClaw+ any MCP client

Install to Claude Code

This server doesn't publish a one-line install command. Follow the setup in the source repository.

Summary

An MCP server that enables Claude to access paywalled scientific papers through your institutional login (Shibboleth/SAML SSO, EZProxy).

README.md

Claude Research Gateway 🔬

An MCP (Model Context Protocol) server that enables Claude to access paywalled scientific papers through your institutional login (Shibboleth/SAML SSO, EZProxy).

How it works: When you ask Claude to find or read a paper, this tool authenticates to journal portals using your university credentials (via a browser popup), then fetches the full text of papers you have institutional access to.

Supported Portals

| Portal | Key | Publisher | |--------|-----|-----------| | ACS Publications | acs | American Chemical Society | | SciFinder-n | scifinder | CAS | | ScienceDirect | elsevier | Elsevier | | Springer / Nature | springer | Springer Nature | | Wiley Online Library | wiley | Wiley | | IEEE Xplore | ieee | IEEE | | JSTOR | jstor | JSTOR | | PubMed Central | pmc | NIH / NLM |

Prerequisites

  • Python 3.10+
  • uv (Python package manager): pip install uv
  • A valid institutional login (university SSO credentials)

Quick Setup

1. Install Dependencies

cd claude-tool-research
uv sync

2. Install Playwright Browsers

uv run playwright install chromium

3. Add to Claude Desktop

Edit your Claude Desktop config file:

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

Add this MCP server entry:

{
  "mcpServers": {
    "research-gateway": {
      "command": "uv",
      "args": [
        "--directory",
        "C:\\Users\\abdir\\Documents\\projects-code\\claude-tool-research",
        "run",
        "server.py"
      ]
    }
  }
}

4. Restart Claude Desktop

Close and reopen Claude Desktop. You should see the research tools appear in the tools menu (🔨 icon).

Usage Examples

First-Time Setup

You: "Configure my institution — I'm at MIT"
Claude: [Calls configure_institution with name="MIT", wayf_name="Massachusetts Institute of Technology"]

You: "Log me into ACS Publications"  
Claude: [Calls authenticate_portal("acs")]
→ A browser window opens → You complete your university SSO login → Session is saved

Searching Papers

You: "Search ACS for papers about lithium-ion battery cathodes published recently"
Claude: [Calls search_papers("acs", "lithium-ion battery cathode materials")]
→ Returns formatted search results with titles, authors, DOIs

Reading a Paper

You: "Fetch the full text of DOI 10.1021/jacs.3c12345"
Claude: [Calls fetch_paper("acs", doi="10.1021/jacs.3c12345")]
→ Downloads and extracts the full paper text for Claude to read and discuss

Checking Session

You: "Is my ACS session still active?"
Claude: [Calls check_session("acs")]
→ Reports session status and age

Available Tools

| Tool | Description | |------|-------------| | list_portals | Shows all portals and your login status for each | | authenticate_portal | Opens browser for institutional SSO login | | check_session | Verifies if a session is still valid | | search_papers | Searches for papers by keywords, title, etc. | | fetch_paper | Downloads and extracts full paper text (via DOI or URL) | | configure_institution | Sets up your institution name, EZProxy URL, WAYF name |

How Authentication Works

┌─────────────┐    ┌──────────────┐    ┌────────────────┐    ┌──────────────┐
│   Claude     │───▶│  MCP Server  │───▶│  Playwright    │───▶│  Publisher   │
│  (asks for   │    │  (manages    │    │  Browser       │    │  Login Page  │
│   a paper)   │    │   sessions)  │    │  (visible)     │    │  (SSO/SAML)  │
└─────────────┘    └──────────────┘    └────────────────┘    └──────────────┘
                                              │                       │
                                              │    ┌──────────────┐   │
                                              └───▶│  Your Univ.  │◀──┘
                                                   │  IdP (SSO)   │
                                                   └──────────────┘
                                                          │
                                                   You enter your
                                                   credentials here
  1. Claude calls authenticate_portal → a real browser window opens
  2. The browser navigates to the publisher's institutional login
  3. You're redirected to your university's SSO page (Shibboleth/SAML)
  4. You enter your credentials in the browser
  5. After successful login, the tool captures the session cookies
  6. Cookies are encrypted and stored locally in ~/.claude-research/sessions/
  7. Subsequent requests use these cookies — no browser needed until they expire

Security Notes

  • No credentials stored: Only session cookies are saved, never your password
  • Encrypted storage: Cookies are encrypted with a machine-local key (Fernet)
  • Session expiry: Sessions follow your institution's expiry policy (typically 8–24h)
  • Local only: All data stays on your machine in ~/.claude-research/

Configuration

Optional: create ~/.claude-research/config.json:

{
  "institution": {
    "name": "MIT",
    "ezproxy_url": "https://ezproxy.library.mit.edu/login",
    "wayf_institution_name": "Massachusetts Institute of Technology"
  },
  "rate_limit_seconds": 1.0,
  "max_content_length": 100000,
  "browser_timeout_seconds": 300
}

Troubleshooting

| Issue | Solution | |-------|----------| | Browser doesn't open | Run uv run playwright install chromium | | Login times out | Increase browser_timeout_seconds in config | | Session expired quickly | Your institution may have short session limits; re-authenticate | | Paper text is empty | Some publishers serve content via JavaScript — try the PDF version | | "Access denied" error | Re-authenticate with authenticate_portal |

License

MIT

See related servers & alternatives →

Related MCP servers

Browse all →

Related guides

Hand-picked reading to help you choose and use Search servers.