Kagi Search
This Kagi MCP server, developed by Aleksey Pridachin, integrates the Kagi search API into the Model Context Protocol ecosystem. Built with Python using libraries like httpx and mcp, it provides tools for web search, news retrieval, and fast GPT-powered question answering. The server implements environment-based configuration for API key management and offers a streamlined interface to Kagi's advanced search capabilities. By abstracting Kagi API operations into a standardized MCP format, it enables AI systems to easily access high-quality web search results and enriched content. This implementation is particularly valuable for applications requiring up-to-date information retrieval, facilitating use cases such as research assistance, fact-checking, and content enrichment across various domains.
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 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- search
- Source
- PulseMCP
- Repository
- github.com/apridachin/kagi-search-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
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.