About scrapedatshi-mcp
scrapedatshi-mcp is an MCP server published by scrapedatshi in the RAG category: enables Claude to scrape, crawl, extract data, and sync to vector databases using scrapedatshi's RAG pipeline, with support for multiple embedding and vector DB providers.
Recent commit activity is the strongest signal that reported issues will get attention.
Install
git clone https://github.com/scrapedatshi/scrapedatshi-mcpThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (18)
autoragFull pipeline: crawl entire site → chunk → embed → inject into your vector DB (large sites auto-batched)
Parameters not published.
chunk_fileUpload a local file (PDF, MD, TXT, CSV, XLSX, DOCX, IPYNB, HTML, XML, code files, etc.) and chunk it into RAG-ready segments
Parameters not published.
chunk_urlScrape & chunk a single URL into RAG-ready text segments
Parameters not published.
crawl_siteCrawl an entire site (sitemap or spider mode) and return all chunks
Parameters not published.
extract_crawlMulti-page schema extraction via site crawl
Parameters not published.
extract_dataExtract structured schema fields from a URL using your LLM
Parameters not published.
get_usage_guideReturns the guided wizard flow and tool selection reference
Parameters not published.
ingest_fileFull pipeline: upload local file → embed → inject into your vector DB
Parameters not published.
ingest_scrapedFull pipeline: bulk-ingest a folder of pre-scraped files → embed → inject into your vector DB
Parameters not published.
inspect_vectordbRead vector DB metadata: dimension, vector count, suggested embedding models (free)
Parameters not published.
Show all 18 tools
list_embedding_providersDiscover supported embedding providers + model notes
Parameters not published.
list_vector_db_providersDiscover supported vector DBs + required config fields
Parameters not published.
pdf_extractExtract text or tables from a PDF (URL or local file) — no chunking, no embedding needed
Parameters not published.
query_vectordbSemantic search: embed a query and retrieve the most relevant chunks from your vector DB. Supports `hybrid_search=true` (vector + BM25 + RRF) and optional `query_rewrite` (LLM-powered query rewriting before embedding)
Parameters not published.
rag_chatRAG Chat: retrieve top-N chunks from your vector DB and generate a grounded LLM answer. Supports `hybrid_search=true`, `query_rewrite=true` (uses the same LLM — no extra keys), and `conversation_history` for pronoun resolution
Parameters not published.
scrape_urlScrape a URL and return clean Markdown — no chunking, just the raw text
Parameters not published.
sync_to_vectordbFull pipeline: scrape URL → embed → inject into your vector DB
Parameters not published.
verify_provider_keyVerify an LLM or embedding API key + get live model list
Parameters not published.
Ask AI
Ask AI about scrapedatshi-mcp
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.