Summary
Search and scrape together is the pairing that matters, because a search result is a link and a link is not an answer.
Plenty of servers do one or the other, and the gap between them is where the work sits: finding the page, then getting its content in a form worth reading. Having both behind one key means the sequence is two calls rather than two integrations. Optional markdown on the scrape is the detail worth using — raw text loses the structure that tells a model what is a heading and what is a caption, and markdown preserves it at no extra cost.
What it is
A two-tool search and extraction client over the Serper API: web search returning rich results, and page scraping returning text with optional markdown.
What you get
- google_search performs the search and returns rich results rather than a bare link list.
- scrape fetches a page and returns its text, with markdown available as an option — markdown being the form a model reads best.
Requirements
SERPER_API_KEY.
Setup effort
One command plus a key — env SERPER_API_KEY=your_api_key_here npx -y serper-search-scrape-mcp-server, then supply credentials