> For the complete documentation index, see [llms.txt](https://doc.thordata.com/doc/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://doc.thordata.com/doc/faq/product-problem/scraping/serp-api/can-serp-data-feed-a-rag-pipeline-directly.md).

# Can SERP data feed a RAG pipeline directly?

Yes — that is one of its main uses. The [SERP API](https://www.thordata.com/products/serp-api/mcp-server?op=cianna\&from=mcp) returns clean structured JSON (rank, title, URL, snippet), so you can chunk and embed it or use it as a retrieval layer without cleaning DOM first. Suited to answers and monitoring that need current rankings and fresh sources; not suited to bulk-fetching full articles from those result links, which crosses copyright and platform-terms boundaries.
