google-scholar-search

Google Scholar Search

Search Google Scholar academic papers via the scholarly library (modified version with CAPTCHA handling).

Quick Start

# Basic keyword search (returns JSON)
google-scholar search "attention is all you need" --num-results 3

# Search with author filter
google-scholar search "deep learning" --author "Yann LeCun"

# Search with year range
google-scholar search "transformer" --year-low 2020 --year-high 2024 --num-results 5

# Get BibTeX citation
google-scholar bibtex "attention is all you need"

Prerequisites

Install the google-scholar-mcp package (provides the google-scholar CLI):

# Via uv (recommended — fast, no proxy issues)
uv tool install google_scholar_mcp

# Or install from GitHub
uv tool install git+https://github.com/arrogant-R/google_scholar_mcp.git

⚠️ Avoid pip install — pip is slow and may fail behind proxies. Use uv instead.

Commands

search

google-scholar search "<query>" [options]

Option	Type	Default	Description
query	str	required	Search keywords (title, topic, or terms)
--author	str	None	Filter by author name
--year-low	int	None	Start year (inclusive)
--year-high	int	None	End year (inclusive)
--num-results	int	5	Number of results to return
--no-fill	flag	off	Skip detailed info (faster, less data)

Output: JSON array. Each item contains:

{
  "bib": { "title": "...", "author": "...", "pub_year": "...", "venue": "...", "abstract": "..." },
  "abstract": "Full abstract text",
  "pub_url": "https://...",
  "num_citations": 12345,
  "citedby_url": "https://...",
  "eprint_url": "https://..."
}

bibtex

google-scholar bibtex "<query>" [--num-results N]

Output: BibTeX entry strings printed to stdout.

CAPTCHA Handling

When Google Scholar detects automated access, a CAPTCHA popup appears. The modified scholarly library: