Kagi Ken

JavaScript-based Kagi search and summarization server that provides web search and document summarization capabilities through the kagi-ken package with concurrent query processing and flexible authentication options.

Kagi MCP server implementation by Carlo Zottmann that provides search and summarization capabilities through the kagi-ken package, offering an alternative to the official Python-based Kagi MCP server. The implementation features concurrent multi-query search processing with timeout handling, comprehensive token resolution supporting both environment variables and file-based authentication (~/.kagi_session_token), and output formatting that precisely matches the official Kagi MCP interface for seamless tool compatibility. Built with Node.js and designed for developers who prefer JavaScript-based tooling, it enables AI assistants to perform web searches and document summarization through Kagi's APIs while maintaining the same interface standards as the official implementation.