What is google-scholar-mcp?

A search connection for Google Scholar, a service that indexes academic papers and researcher profiles. It can return paper details, citation links, author information, citation counts, and BibTeX records, but not full paper text.

Use it to find papers, compare research, identify authors and citations, look up profiles, and generate a BibTeX entry for a known paper.

It makes literature searches and citation work easier while keeping results tied to retrieved academic metadata instead of guesses.

google-scholar-mcp — Skill for Claude Code and Codex by LWaetzig

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add LWaetzig/google-scholar-search-mcp --skill google-scholar-mcp

Clone the repo

git clone --depth 1 https://github.com/LWaetzig/google-scholar-search-mcp

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/lwaetzig/google-scholar-search-mcp/google-scholar-mcp/github.svg)](https://agentmods.dev/skills/lwaetzig/google-scholar-search-mcp/google-scholar-mcp)

Your own site

<a href="https://agentmods.dev/skills/lwaetzig/google-scholar-search-mcp/google-scholar-mcp"><img src="https://agentmods.dev/badge/skills/lwaetzig/google-scholar-search-mcp/google-scholar-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/lwaetzig/google-scholar-search-mcp/google-scholar-mcp"><img src="https://agentmods.dev/badge/skills/lwaetzig/google-scholar-search-mcp/google-scholar-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 924 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00082	$0.00924
Opus 5.5	$0.00033	$0.00370
Sonnet 5.5	$0.00016	$0.00185
Haiku 4.5	$0.00008	$0.00092

Measured yesterday against content hash 63d6b1626254, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

google-scholar-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/google-scholar-mcp/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Google Scholar research with google-scholar-search-mcp

Seven tools, backed by the scholarly library scraping Google Scholar. If none are available, tell the user the Google Scholar MCP server is not connected instead of recalling paper details from memory. Never invent titles, authors, citation counts or BibTeX.

When to use it

"Find papers on X", literature reviews, related-work sections
Who wrote or cites a paper; citation counts; an author's h-index and works
A BibTeX entry for a known paper
Venues beyond arXiv (journals, conferences, patents)

Do not use it for general web questions, full-text reading (it returns metadata and abstracts/snippets only), or when an arXiv ID is already known and an arXiv tool is available.

Choosing a tool

Goal	Tool
Topic or keyword search	`search_papers`
Several topics at once	`bulk_search` (max 10 queries)
Full metadata of one known paper	`get_paper_details`
Who cites a paper	`get_citations`
Author profile and top works	`search_author`
Citation entry	`get_bibtex`

Typical flow: search_papers → get_paper_details for the candidates that matter → get_bibtex only for papers the user will cite.

Parameters

search_papers(query, max_results=10 [1-20], year_from, year_to, sort_by="relevance"|"date", include_patents=true). Set include_patents=false for academic literature.
search_author(name, max_publications=5 [1-20]): use the full name; names are ambiguous, so check affiliation and interests before trusting a match.
get_paper_details(title) / get_citations(title, max_results=10 [1-20]) / get_bibtex(title) take the title, not an ID. Use the exact title from a previous search result.
bulk_search(queries, max_results_per_query=5 [1-10], year_from, year_to) runs queries one after another and reports per-query errors without aborting.

Values outside the stated ranges are clamped, not rejected.

Rate limits: this is the important part

Read the full file on GitHub · 83 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 83 lines · 82 tokens per session scan A 63d6b1626254

Subscribe to this mod's changes

google-scholar-mcp is a skill published in the GitHub repository LWaetzig/google-scholar-search-mcp (2 stars, last pushed 2d ago), licensed MIT. It adds 82 tokens to every session and 924 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-10.

Research academic-research ai-tools mcp mcp-server

google-scholar-mcp next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
google-scholar-mcpLWaetzig/google-scholar-search-mcp	Skill	2	2d ago	MIT	A	82	Claude Code, Codex
pre-meeting-briefchrisblattman/claudeblattman	Skill	480	yesterday	MIT	A	23	Claude Code
schedule-querychrisblattman/claudeblattman	Skill	480	yesterday	MIT	A	17	Claude Code
announcement-digestchrisblattman/claudeblattman	Skill	480	yesterday	MIT	A	26	Claude Code, Codex
dr-synthesizechrisblattman/claudeblattman	Skill	480	yesterday	MIT	A	22	Claude Code, Codex
todo-addchrisblattman/claudeblattman	Skill	480	yesterday	MIT	A	18	Claude Code, Codex
b123d-modelingpzfreo/build123d-mcp	Skill	147	2d ago	Apache-2.0	A	0	Claude Code, Codex