Kagi Ken
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.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-02.
Scan details: Circle-IR · 2026-09-02 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- security
- Source
- PulseMCP
- Repository
- github.com/czottmann/kagi-ken-mcp
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
Use via MCP
Resolve Kagi Ken from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.