About BetterWebSearch MCP
BetterWebSearch MCP is an MCP server in the RAG category: keyless-first MCP for better web research — DuckDuckGo out of the box, Brave/Tavily optional, 3-tier extraction (HTTP → hydration → Playwright).
Install
git clone https://github.com/PhantomPixelDev/BetterWebSearch-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 (6)
deep_searchAlias for `web_research`
Parameters not published.
web_extractExtracts clean content from any URL, using the best method available
Parameters not published.
web_findSearch scoped to a single website
Parameters not published.
web_newsRecent news with timeline and diversity filtering
Parameters not published.
web_researchDeep research. Rewrites your question, searches in parallel, extracts top results with citations
Parameters not published.
web_searchAggregated search across providers, deduplicated and reranked
Parameters not published.
Ask AI
Ask AI about BetterWebSearch MCP
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.