google-scholar-search — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited google-scholar-search (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Search Google Scholar academic papers via the scholarly library (modified version with CAPTCHA handling).
# 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"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.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://..."
}google-scholar bibtex "<query>" [--num-results N]Output: BibTeX entry strings printed to stdout.
When Google Scholar detects automated access, a CAPTCHA popup appears. The modified scholarly library:
If a CAPTCHA is encountered, inform the user: "Google Scholar requires CAPTCHA verification. A browser window should have appeared — please complete the verification manually, then I'll retry the search."
--no-fill for quick result counts without detailed metadatacitedby_url from search results~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.