MCP App StoreMCP App Store
from academic-search75
Search and extract structured metadata for academic papers across arXiv, Semantic Scholar, PubMed, ACM/IEEE and more; supports citation analysis and PDF/BibTeX
Academic Search provides a focused workflow and scripts for discovering academic papers, extracting structured metadata (title, authors, year, venue, citations, PDF links), and performing citation analysis. It selects the best platform per task (arXiv, Semantic Scholar, PubMed, Papers with Code, ACM/IEEE) and includes guidance for using CDP/browser automation when platforms lack APIs (e.g., Google Scholar, CNKI).
Use this skill for literature reviews, finding papers by keyword/author/venue, gathering BibTeX or PDFs, and building citation lists or lightweight surveys. It triggers on signals like “search paper”, “find paper”, mentions of arXiv/Semantic Scholar/Google Scholar, or requests for citation counts and BibTeX exports.
Designed for agents that can run Node/Python helper scripts and, when needed, control a browser via CDP proxy. Useful for research assistants and agents performing automated literature reviews.
Academic-search is a comprehensive skill for searching and extracting structured metadata from academic papers across arXiv, Semantic Scholar, PubMed, and more. It includes a CDP proxy server for browser automation (Google Scholar, CNKI), an OA PDF downloader with manifest-based workflow, and discipline-specific routing profiles. The SKILL.md is exceptionally detailed with platform selection matrices, query expansion strategies, and PDF access fallback chains. Scripts are well-written but some test failures were environment-related (no Chrome, no rg, sandbox path issues) rather than code quality issues.
ripgrep (rg)Chrome with remote debuggingShell injection risk in CDP proxy /eval endpoint is acceptable since it's a localhost-only dev tool connecting to the user's own Chrome. The skill explicitly forbids Sci-Hub/LibGen/shadow libraries and paywall bypass — strong ethical boundary. OA PDF download properly validates content-type and %PDF- header before saving. Discipline routing and venue ranking references show thoughtful architecture for multi-domain academic search.
Retriever (Membrane CLI)
Integrate Retriever search and discovery via the Membrane CLI — manage connections and run queries across Retriever data sources.
arxiv2md
Convert arXiv papers into clean, LLM-ready Markdown via a REST API or CLI for fast reading, summarization, and downstream processing.
ClawPod / Massive Unblocker
Bypass anti-bot restrictions and fetch rendered HTML or structured search results via Massive's Unblocker API (handles CAPTCHAs, JS rendering, geo-restrictions)
Retriever (Membrane) Integration
Integrate with Retriever via the Membrane CLI to search, query, and proxy Retriever data (documents, snippets, queries) with built-in auth and pagination.
Scite Database (Smart Citations)
Query Scite.ai Smart Citations by DOI to report supporting, contrasting, and mentioning citation counts and help assess a paper's reliability.
AI News Daily
Generate a structured, bilingual daily briefing of the latest AI industry news, model updates, papers, and open-source tools with in-depth technical analysis an
Algolia Cost Tuning
Practical guide to reduce Algolia billing by auditing records/requests, switching to virtual replicas, multi-query usage, caching, and cleanup strategies.
Memory Search
Search past coding sessions and observations using natural-language queries to retrieve decisions, notes, and context.