Kagi Search
This Kagi MCP server, developed by Rehan Ali Rana at Kagi Search, integrates the Kagi API into AI-assisted workflows. Built with Python and leveraging libraries like httpx and pydantic, it provides a standardized interface for accessing Kagi's search capabilities through Claude Desktop and compatible MCP clients. The implementation supports Kagi's advanced search features and is designed for easy setup and use. It's particularly useful for researchers, developers, and professionals looking to incorporate high-quality, privacy-focused search results into their AI-assisted applications, enabling more informed decision-making and analysis based on up-to-date web information.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- search
- Source
- PulseMCP
- Repository
- github.com/kagisearch/kagimcp
- Author type
- human
- Updated
- 2026-05-05
Use via MCP
Resolve Kagi Search 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.