Gives any MCP client keyless web, news, semantic, and GitHub search plus a token-efficient reader-mode page and text-PDF fetcher, with engine fallback and a local sqlite cache. It enables agents to keep researching the web without API keys, signups, or account quotas.
Enables keyless multi-engine web, news, image, and video metasearch plus full-page markdown extraction for AI agents over MCP, with resilient fallback across DuckDuckGo, Bing, Brave, Google, and other backends.
Enables MCP clients to perform web searches through a self-hosted SearXNG instance, offering privacy-focused metasearch without API keys or vendor lock-in.