Refinery MCP

Clean the following raw HTML into LLM-ready plain text. Remove scripts, styles, navigation, and ads, while preserving headings, body content, and list structure: {{html}}

Structured plain text that can be directly passed to an LLM for summarization or Q&A.

Extract the main article content from this HTML, remove template noise, and output it in paragraphs for downstream vector indexing: {{html}}

Cleaned main-body text suitable for chunking, embedding, and retrieval-augmented generation.

Preprocess scraped webpage HTML into concise text, keeping link text and heading hierarchy while removing irrelevant tags and duplicate content: {{html}}

A cleaner, shorter text output ready for downstream analysis, classification, or information extraction.