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.
Work with Kagi without API access (you'll need to be a customer, tho). Searches and summarizes. Uses Kagi session token for easy authentication.
Local-first, keyless web intelligence in one server: search, fetch, crawl, extract, cache, find-similar, and research. Multi-engine search with local ML reranking and a persistent SQLite cache, renders JS-heavy pages, and keeps everything on your machine. Install via npx wigolo init --non-interactive --agents=.
Quality signal
60/100 (Good)
59/100 (Good)
Install path
npx · high
npx · high
Engagement
3 0 0 41
1 0 0 4,410
Tools
kagi_search_fetchkagi_summarizer
Multi-engine web search with local machine learning rerankingPersistent SQLite cache storing all fetched data locallyJavaScript rendering for dynamic web pagesKeyless operation for search, fetch, crawl, extract, cache, and similarityOptional LLM integration for research and answer synthesisSupports multiple AI agents via MCP and REST endpoints