MCP server that extracts content from web pages for LLMs
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"mcp-web-extractor-sadasiba","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# MCP Web Extractor (by sadasiba) `mcp-web-extractor-sadasiba` is an MCP (Model Context Protocol) server that extracts clean text content from web pages for use by LLMs such as Claude. It fetches HTML from a given URL, parses it with **BeautifulSoup**, and returns only the readable text. --- ## Features - 🌐 Extracts readable text from any web page - 🧹 Strips away HTML tags, scripts, and styling - ⚡ Simple command-line interface - 🤝 Works seamlessly with Claude's MCP integration --- ## Installation You can install directly from [PyPI](https://pypi.org/project/mcp-web-extractor-sadasiba/): ```bash pip install mcp-web-extractor-sadasiba
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.