Connection check
local install
scraper
Web scraping MCP — extract clean markdown, links, and metadata from any URL.
Tools
5
GitHub stars
5
Installs / wk
157
Licence
MIT
Transport
stdio
Last checked
never
Tools & capabilities
5 toolsRead from the published package source — this server runs locally, so there is no endpoint to query. Names are taken from the code, not observed at runtime, and descriptions are often absent.
extract_links
from source
Extract all links from a page with their href and anchor text. Resolves relative URLs. Skips anchors and javascript: links. Extract all links from a page with their href and anchor text. Resolves relative URLs. Skips anchors and javascript: links.
extract_metadata
from source
Extract page metadata: title, description, Open Graph tags (og:title, og:description, og:image), canonical URL, and favicon. Extract page metadata: title, description, Open Graph tags (og:title, og:description, og:image), canonical URL, and favicon.
scrape_multiple
from source
Batch scrape multiple URLs. Returns title and excerpt for each. Failures are reported per URL without failing the whole batch. Batch scrape multiple URLs. Returns title and excerpt for each. Failures are reported per URL without failing the whole batch.
scrape_url
from source
Extract clean, readable text content from a URL using Mozilla Readability. Returns title, excerpt, and main content. Best for articles, docs, and blog posts. Extract clean, readable text content from a URL using Mozilla Readability. Returns title, excerpt, and main content. Best for articles, docs, and blog posts.
search_page
from source