Parse any file or URL into structured text. Extract text from PDF, DOCX, YouTube, web pages, images, and 25+ formats via one API. Tools: parse_url, parse_file, get_youtube_transcript.
Converts any URL into clean, LLM-ready Markdown, text, or HTML with production-grade features like SSRF protection, rate limiting, retries, caching, and structured error handling.
Enables web scraping and document processing with JavaScript execution, anti-detection measures, batch processing, and structured data extraction. Supports multiple formats including markdown, HTML, screenshots, and handles PDFs with OCR capabilities.
A powerful tool for fetching and extracting text content from web pages and APIs, supporting web scraping, REST API requests, and Google Custom Search integration.
MCP server that extracts clean text, tables, and structured data from documents, images, code, and audio files, supporting 97 formats with OCR, transcription, and code intelligence.
Enables AI agents to extract clean, structured web content (articles, tables, links, visual layouts) optimized for LLM token efficiency, with fast response times and optional JavaScript support.