MCP Agentic Data Transformer

GitHub Trending Scraper

automation-lab/github-trending-scraper

Scrape GitHub Trending repositories by language and time range: today, this week, or this month. Extracts repo names, star counts, forks, star gains, and top contributors. Great for dev trend tracking, tech newsletters, and investment research. Export to JSON, CSV, or Excel.

Google AI Overview API

johnvc/Google-AI-Overview-API

Fetch Google AI Overviews for any query - get the AI-generated answer and its cited sources as structured JSON. Send one or many queries, target a country and language, and handle Google's deferred (page-token) generation automatically. Pay per retrieval. MCP-ready for Claude and AI agents.

Image Similarity API | Compare Images, Find Duplicates

johnvc/image-similarity-api

Compare images by visual similarity with a CLIP vision model plus perceptual hashing. Score a source image against up to 500 targets, catch exact and near-duplicates, and get one clean row per comparison. URLs, base64, or file upload. Pay per result, MCP ready for AI agents.

Google Scholar | Research Papers, Citations & Author Profiles

johnvc/google-scholar-api

Scrape Google Scholar at scale. Search research papers, get citation formats (MLA, APA, Chicago, BibTeX), author profiles with h-index and i10-index, list an author's publications, view per-article citation history, & map co-author networks. Six modes in one for lit reviews, bibliometrics, & agents.

Google Scholar Lite - Cheap Bulk Academic Papers API

johnvc/google-scholar-lite-api

Search Google Scholar for academic papers in bulk and export clean JSON: title, authors, journal, year, citation count, and PDF links. Fast bibliometric search for literature reviews, citation discovery, and research datasets. Pay per paper from $1.50 per 1,000, with no setup or per-run fee.

News Intelligence Scraper — AI Agent Real-Time News API

logiover/news-intelligence-scraper

Multi-source real-time news aggregator for AI agents: Google News, Bing News and DuckDuckGo News merged, deduplicated, source-ranked and sentiment-scored. One topic or company to clean structured news feed. No API key, no browser.

Lever Jobs Scraper

humble-echidna/lever-jobs

Type company names or paste Lever job-board URLs (US and EU) and get every open job from those companies' Lever career pages: full descriptions, salary where published, one clean format. Filter by keyword, place, department, salary or date; get only new, changed or closed jobs since your last run.

Hugging Face Scraper - Models, Datasets, Spaces & Leads

scrapesage/hugging-face-scraper

Scrape the Hugging Face Hub via its official API: models, datasets and Spaces with downloads, likes, trending score, license, tags, parameters, eval results and linked Spaces — plus author/org profiles with a creator-lead wedge and a new-release monitor. Keyless, no browser.

arXiv Scraper: Preprints, Authors & Categories

arman-bd/arxiv-papers-scraper

Scrape arXiv: title, authors, abstract, categories, DOI, journal reference, and PDF links. Search by query, category, author or date. The primary source for AI/ML preprints.

arXiv Scraper - Papers, Authors, Abstracts & PDFs

scrapesage/arxiv-scraper

Scrape arXiv papers by search query or ID from the official API: title, abstract, authors, categories, publication date, DOI, journal reference and PDF link. No key, no browser, cents per paper. Independent tool, not affiliated with arXiv.

arXiv Papers Scraper — Search Research Papers by Topic & Author

yadroo/arxiv-papers

Search arXiv for research papers by keywords, author, category and date; returns title, authors, abstract, categories, published/updated dates, PDF and abstract URLs, DOI. Sort by relevance or date. Built for research agents. No API key.