$ loading_
Clean raw HTML into LLM-ready text to save context and token costs.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "Refinery MCP" MCP server from askskill: Run: claude mcp add 'io-github-larelabs-refinery-mcp' -- npx -y @larelabs/refinery-mcp
Clean this raw webpage HTML into LLM-ready main text. Remove scripts, styles, navigation, footer, and ads, and keep only headings, paragraphs, and lists in the original structure.
A clean, well-structured main-text version of the page ready for summarization, QA, or analysis.
I’m about to ingest a batch of webpages into a knowledge base. First, clean each raw HTML page into a consistent plain-text format, preserve section hierarchy, and remove irrelevant template content.
Consistently cleaned text suitable for vectorization, indexing, and knowledge base ingestion.
Before the AI agent analyzes this webpage, clean the raw HTML and keep only text that helps understand the page, reducing token usage, then output the cleaned result.
A leaner page-text input that helps the agent process faster and lowers context overhead.
Automatically repairs and polishes prompts to create clearer, more effective AI inputs.
Convert any URL into clean, LAG-ready Markdown, text, or HTML.
Clean AI-generated Markdown and export shareable HTML, PDF, DOCX, or PNG documents.
Convert URLs into lean LLM-ready text with token and cost savings receipts.
Convert webpages into clean Markdown for archiving, extraction, and AI workflows.
Provides clean, spam-free web search results for AI agents.