Side-by-side comparison of two Model Context Protocol servers — install paths, tools, quality signals, and directory engagement so you can pick the right one for Claude, Cursor, and other MCP clients.
Crawl websites into clean Markdown, search pages, and extract structured data with LLMs. Built-in MCP server for web research and RAG pipelines.
Official MCP server for managing Searchcraft clusters, creating a search index, generating an index dynamically given a data file and for easily importing data into a search index given a feed or local json file.
Quality signal
44/100 (Fair)
51/100 (Fair)
Install path
npx · high
npx · high
Engagement
5 0 1 3
0 0 0 9
Tools
Crawls single pages or full websites with URL filteringOutputs clean Markdown files with citations and timestampsGenerates structured JSONL index per pageIncludes local embedding model with zero API key requirementSupports downloading referenced PDFs and DOCX files with filtersImplements HTTP retry with exponential backoff honoring Retry-After headers
Index management: create, update, delete, patch, list indexesDocument management: add, delete by ID, field, or query, retrieve documentsFederation management: create, update, delete, list federationsAuthentication key management: create, update, delete, list keysStopwords management: add and delete custom stopwordsSupports plain English prompts for administrative actions