The Kagi MCP server enables interaction with the Kagi API for web search and context enrichment:
Ask FastGPT: Search the web and retrieve answers with references
Enrich Web: Add general, non-commercial web content using concise queries (1-3 words recommended)
Enrich News: Add latest news and discussions using concise queries (1-3 words recommended)
Allows to search web using Kagi API, providing tools for web search (fastgpt), web content enrichment, and news enrichment
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Kagi MCP Serversearch for recent advancements in quantum computing"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Kagi MCP server
MCP server that allows to search web using Kagi API
Components
Resources
The server implements calls of API methods:
fastgpt
enrich/web
enrich/news
Prompts
The server provides doesn't provide any prompts:
Tools
The server implements several tools:
ask_fastgpt to search web and find an answer
enrich_web to enrich model context with web content
enrich_news to enrich model context with latest news
Related MCP server: MCP JinaAI Search Server
Configuration
Quickstart
Install
Installing via Smithery
To install the Kagi MCP server for Claude Desktop automatically via Smithery:
Claude Desktop
On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
Development
Building and Publishing
To prepare the package for distribution:
Sync dependencies and update lockfile:
Build package distributions:
This will create source and wheel distributions in the dist/ directory.
Publish to PyPI:
Note: You'll need to set PyPI credentials via environment variables or command flags:
Token:
--tokenorUV_PUBLISH_TOKENOr username/password:
--username/UV_PUBLISH_USERNAMEand--password/UV_PUBLISH_PASSWORD