Is Paper Fetcher safe to use?

Paper Fetcher has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments. Licensed under MIT.

How do I install Paper Fetcher?

Paper Fetcher can be installed by cloning its GitHub repository and following the setup instructions in the README.

What can Paper Fetcher do?

Paper Fetcher provides 3 tools: search_papers, fetch_paper, get_paper_metadata. See the full tools list on the server page for descriptions and parameters.

What AI clients work with Paper Fetcher?

Paper Fetcher is compatible with claude-desktop, cursor, claude-code. It uses stdio transport.

Is Paper Fetcher actively maintained?

Paper Fetcher is recently maintained — last commit was 66 days ago. It has 35 GitHub stars.

Paper Fetcher

Name: Paper Fetcher
Author: fermionoid

by fermionoid

Academic paper full-text fetcher - MCP server for Claude Code with Open Access, arXiv, and EZproxy support

35 3 tools GitHub

No known CVEs

MIT license

Maintained

Last commit 66d ago

Works with most clients

Transport: stdio

3 tools · ~255 tok

Grade A · 0.1% of 200K ctx

Edit this pageView history

Education Search

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "paper-fetcher": {
      "command": "<see-readme>",
      "args": []
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/paper-fetcher)](https://mcppedia.org/s/paper-fetcher)

Read me

What Paper Fetcher does

An MCP server and CLI tool for fetching academic paper full texts. Designed to work as a Claude Code MCP tool, enabling AI-assisted literature review and research workflows.

Test This Server

No automated test available for this server. Check the GitHub README for setup instructions.

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

70/100across 5 weighted dimensions

How we score →

0255075100

−30

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

No package registry to scan.

Inventory

Tools (3)

Click any tool to inspect its schema.

~255 tokens total

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is Paper Fetcher safe to use?: Paper Fetcher has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments. Licensed under MIT.
How do I install Paper Fetcher?: Paper Fetcher can be installed by cloning its GitHub repository and following the setup instructions in the README.
What can Paper Fetcher do?: Paper Fetcher provides 3 tools: search_papers, fetch_paper, get_paper_metadata. See the full tools list on the server page for descriptions and parameters.
What AI clients work with Paper Fetcher?: Paper Fetcher is compatible with claude-desktop, cursor, claude-code. It uses stdio transport.
Is Paper Fetcher actively maintained?: Paper Fetcher is recently maintained — last commit was 66 days ago. It has 35 GitHub stars.

Similar servers

Others in education / search

View all →

Brave Search MCP Server98

Web and local search using Brave Search API

86.4k 2

Tavily Mcp96

Production ready MCP server with real-time search, extract, map & crawl.

2.0k 4

Context795

Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

56.4k 2

Qmd95

mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local

25.8k 4

MCP Security Weekly

Get CVE alerts and security updates for Paper Fetcher and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

Edit this pageView history

Education Search

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "paper-fetcher": {
      "command": "<see-readme>",
      "args": []
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/paper-fetcher)](https://mcppedia.org/s/paper-fetcher)

Read me

What Paper Fetcher does

An MCP server and CLI tool for fetching academic paper full texts. Designed to work as a Claude Code MCP tool, enabling AI-assisted literature review and research workflows.

Test This Server

No automated test available for this server. Check the GitHub README for setup instructions.

README

paper-fetcher

An MCP server and CLI tool for fetching academic paper full texts. Designed to work as a Claude Code MCP tool, enabling AI-assisted literature review and research workflows.

How It Works

paper-fetcher uses a three-layer strategy to maximize access to full-text papers:

Layer 1: Open Access (Unpaywall + arXiv)     ← free, no login required
Layer 2: Institutional proxy (EZproxy)        ← requires university login
Layer 3: Metadata only (Semantic Scholar)     ← always available

For each paper request, it tries Open Access sources first. If the paper is paywalled, it falls back to your institution's EZproxy. Metadata and search are always available via Semantic Scholar.

Features

MCP Server - Integrate directly with Claude Code for AI-powered research
Three access layers - Open Access, institutional EZproxy, and metadata fallback
Multi-source search - Search papers via Semantic Scholar API
Full-text extraction - Extract text from HTML and PDF sources
Publisher adapters - Optimized extraction for Nature, ACS, Elsevier, Wiley, and more
Smart caching - Cache fetched papers locally to avoid redundant requests
Rate limiting - Built-in polite request delays
CLI interface - Standalone command-line tool for batch operations

Installation

# Clone the repository
git clone https://github.com/YOUR_USERNAME/paper-fetcher.git
cd paper-fetcher

# Install in development mode
pip install -e .

Setup with Claude Code

claude mcp add paper-fetcher -- paper-fetcher-mcp

After restarting Claude Code, you can ask Claude to search and fetch papers directly:

"Search for recent papers on perovskite solar cells" "Fetch the full text of DOI 10.1038/s41566-024-01234-5"

CLI Usage

Login to EZproxy (institutional access)

# Opens a browser for manual login. Cookies are saved for future use.
paper-fetcher login

# Force re-login even if session appears valid
paper-fetcher login --force

Search for papers

# Basic search
paper-fetcher search "organic photovoltaics stability"

# Limit results and filter by year
paper-fetcher search "perovskite solar cells" --limit 20 --year 2022-2025

# Search and fetch full texts
paper-fetcher search "silver nanowire transparent electrode" --fetch

Fetch a single paper

# By DOI
paper-fetcher fetch "10.1038/s41566-024-01234-5"

# By URL
paper-fetcher fetch "https://www.nature.com/articles/s41566-024-01234-5"

# Output as markdown
paper-fetcher fetch "10.1038/s41566-024-01234-5" --format markdown

Batch fetch

# Create a file with one DOI per line
paper-fetcher batch dois.txt --format markdown --output ./papers

Configuration

# View current config
paper-fetcher config-cmd

# Set email (required for Unpaywall OA detection)
paper-fetcher config-cmd --email your@email.com

# Set output directory
paper-fetcher config-cmd --output-dir ./my-papers

Configuration

Configuration is stored at ~/.paper-fetcher/config.json and includes:

Field	Description	Default
`proxy_base`	Your institution's EZproxy login URL	`http://eproxy.lib.hku.hk/login?url=`
`email`	Email for Unpaywall API (OA detection)	`""` (set via CLI)
`output_dir`	Directory for downloaded PDFs	`~/.paper-fetcher/papers`
`cache_dir`	Directory for cached results	`~/.paper-fetcher/cache`
`request_delay_min`	Minimum delay between requests (seconds)	`2.0`
`request_delay_max`	Maximum delay between requests (seconds)	`5.0`

To use with a different institution's EZproxy, edit ~/.paper-fetcher/config.json:

{
  "proxy_base": "http://your-institution-proxy.edu/login?url=",
  "email": "your@email.com"
}

MCP Tools

When used as an MCP server, paper-fetcher exposes three tool

... View full README on GitHub

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

70/100across 5 weighted dimensions

How we score →

0255075100

−30

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

No package registry to scan.

Inventory

Tools (3)

Click any tool to inspect its schema.

~255 tokens total

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is Paper Fetcher safe to use?: Paper Fetcher has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments. Licensed under MIT.
How do I install Paper Fetcher?: Paper Fetcher can be installed by cloning its GitHub repository and following the setup instructions in the README.
What can Paper Fetcher do?: Paper Fetcher provides 3 tools: search_papers, fetch_paper, get_paper_metadata. See the full tools list on the server page for descriptions and parameters.
What AI clients work with Paper Fetcher?: Paper Fetcher is compatible with claude-desktop, cursor, claude-code. It uses stdio transport.
Is Paper Fetcher actively maintained?: Paper Fetcher is recently maintained — last commit was 66 days ago. It has 35 GitHub stars.