Htmltext is an HTTP JSON-RPC MCP server that exposes tools for converting HTML into readable plain text, extracting hyperlinks, and retrieving document metadata. It is intended for developers integrating HTML processing into AI agents, scraping pipelines, and automation workflows.
htmltext is an API design, testing & docs project. It focuses on cleaning HTML and extracting readable text, links, and metadata for automated workflows. It is built as a B2B product for developers building AI agents and web-data workflows. It runs on the web and API.
Pipeworx builds and maintains htmltext. Key capabilities include HTML to text, link extraction, and metadata extraction. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match