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.
npx skills add aryankeluskar/bibtex-mcp --skill google-scholar-bibtex-mcpgit clone --depth 1 https://github.com/aryankeluskar/bibtex-mcpWrote 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.
[](https://agentmods.dev/skills/aryankeluskar/bibtex-mcp/google-scholar-bibtex-mcp)<a href="https://agentmods.dev/skills/aryankeluskar/bibtex-mcp/google-scholar-bibtex-mcp"><img src="https://agentmods.dev/badge/skills/aryankeluskar/bibtex-mcp/google-scholar-bibtex-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.
<a href="https://agentmods.dev/skills/aryankeluskar/bibtex-mcp/google-scholar-bibtex-mcp"><img src="https://agentmods.dev/badge/skills/aryankeluskar/bibtex-mcp/google-scholar-bibtex-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00083 | $0.00669 |
| Opus 5 | $0.00042 | $0.00334 |
| Sonnet 5 | $0.00017 | $0.00134 |
| Haiku 4.5 | $0.00008 | $0.00067 |
Grade A, and why
google-scholar-bibtex-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 12d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Scholar BibTeX MCP
Use this skill when a task needs BibTeX records from Google Scholar rather than model-generated citations.
Install The MCP
If this repository is checked out locally:
npm install
npm run build
npx add-mcp "node /absolute/path/to/bibtex-mcp/dist/mcp.js" --name scholar-bibtex -a codex -y
For a published npm package:
npx add-mcp bibtex-mcp --name scholar-bibtex -a codex -y
If direct package-name installation is not suitable, use the explicit command form:
npx add-mcp "npx -y bibtex-mcp" --name scholar-bibtex -a codex -y
You can also install from the public GitHub repo:
npx add-mcp "npx -y github:aryankeluskar/bibtex-mcp" --name scholar-bibtex -a codex -y
Adjust -a codex for the target client. add-mcp supports agents such as codex, claude-code, cursor, vscode, and opencode. Use --all only when the user explicitly wants broad installation.
Use The MCP Tool
Call:
google_scholar_bibtex
Input:
{
"query": "Attention Is All You Need",
"maxResults": 10,
"exactTitle": false
}
Guidelines:
- Request multiple results by default. Do not force
maxResults: 1unless the user explicitly asks for a single record. - Prefer returned options with
sourceType: "archival"oversourceType: "preprint"when the title matches. - Treat
origin: "versions"as useful: the MCP follows ScholarAll versionsclusters so archival conference/journal records can beat top-level arXiv/preprint rows. - Use
exactTitle: truewhen the user gives a precise paper title and similarly named papers are likely. - Inspect
title,authorsLine,url,sourceType, andarchivalReasonbefore selecting the final BibTeX. - Keep alternatives visible when the citation is for a paper, thesis, preprint, workshop version, conference version, or journal extension that could have multiple legitimate records.
Failure Handling
If Google Scholar returns an anti-automation or CAPTCHA interstitial, report that clearly. Do not bypass CAPTCHA, rate limits, paywalls, or access controls. Ask the user to retry later or use the browser-visible Scholar flow manually.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 76 lines · 83 tokens per session scan A 204c3cfa52c6
google-scholar-bibtex-mcp is a skill published in the GitHub repository aryankeluskar/bibtex-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 83 tokens to every session and 669 once invoked, about $0.0004 per session on Opus 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 2026-08-31.
Other skills, from other repositories
idea-bib-review
A writing workflow for drafting a literature review from a research idea and BibTeX files, which are structured records of academic sources. It preserves citation keys and checks whether claims are supported by the supplied evidence.
scholar-sidekick
This skill should be used when the user mentions a scholarly identifier (DOI, PMID, PMCID, ISBN, arXiv, ISSN, NASA ADS bibcode, WHO IRIS URL) and wants structured metadata, a formatted citation, a bibliography export file, a retraction check, an open-access check, or verification that a claimed citation is real (not…
science-agent
Verify what AI writes about science — catch confabulated citations, drifted notebook numbers, and stale figure captions before they ship. Use when adding or reviewing academic citations, BibTeX entries, DOIs, or empirical claims in .md/.tex/.bib/.ipynb files; when writing a literature review; or when the user says…
google-scholar-labs-ajg-mcp
Search Google Scholar Labs via CloakBrowser with persistent browser profile and filter candidate papers strictly against the AJG 2024 (Academic Journal Guide / ABS) rankings (default ABS2+: 2, 3, 4, 4). Returns qualified papers and detailed exclusion records, with human handoff for sign-in or anti-bot interruptions.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
scientific-writing
Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting…