Doc Scraper (Jina.ai)

Fetch

Convert web data into markdown format for in-depth analysis and examination.

GitMCP (GitHub to MCP)

Create a documentation center by converting your GitHub projects (repositories or GitHub pages), enabling accessibility to current documentation and code for AI applications such as Cursor, minimizing confusion.

Markdownify

Easily transform a variety of file formats and online content into Markdown style through dedicated utilities tailored for PDFs, photos, audio files, websites, and beyond.

DeepWiki Markdown Converter

Easily convert DeepWiki repositories into clear Markdown format, preserving page links and eliminating unwanted elements like headers, footers, and ads. Ideal for extracting clean and well-structured documentation.

Open Deep Research

Discover in-depth insights on various subjects through iterative investigation utilizing search engines, web scraping, and advanced language algorithms to produce detailed markdown summaries.

Fetch and Convert

Transform web data into Markdown format by leveraging the powerful capabilities of JSDOM and Turndown for seamless conversion.

Google Docs

Enhances the connection between Google Docs and artificial intelligence applications, enabling seamless interaction for analyzing, editing, and formatting text in documents.

Fetch (Web Content & YouTube Transcripts)

Discover web content and YouTube video transcriptions effortlessly with the Model Context Protocol (MCP). Easily convert HTML to Markdown format and pinpoint timestamps for convenient reference during discussions.

MarkItDown

Easily transform various file types into Markdown format with the MarkItDown tool. Streamline text-based processes for migrating, documenting, and analyzing content across different formats.

Puppeteer Vision Web Scraper

Enhances web data extraction by effectively managing cookie pop-ups, CAPTCHAs, and subscription barriers to retrieve high-quality markdown information from online sources.

Jina AI

Unlock the potential of Jina AI’s web services by seamlessly integrating with the Model Context Protocol (MCP). Gain advanced capabilities in web content extraction, search functionalities, and fact-checking using intuitive natural language interactions.

Ref

Access curated technical documentation seamlessly by leveraging the Ref.tools documentation search service through the Model Context Protocol (MCP). Benefit from web search fallback and easy URL-to-markdown conversion, enhancing developer reference efficiency while coding.

Scrapling Fetch

Empower AI systems to retrieve text data from websites safeguarded by bot detection technologies using three distinct security tiers (basic, stealth, max-stealth). This protocol allows for the extraction of entire web pages or targeted content layouts without the need for manual extraction.

Docling

Unlock powerful document processing features by connecting seamlessly with the Docling library. From converting files to markdown and extracting tables to handling images with OCR functionality, this model context protocol streamlines the analysis of diverse document types, organized or random.

Crawl4AI (Web Scraping & Crawling)

Employs advanced techniques for combining web scraping, crawling, content extraction, metadata acquisition, and Google search features. Ideal for tasks involving analysis of online content, gathering data, and conducting research on the web.