mcp-servers-kagi
by ac3xx·★ 44·Score 36
A TypeScript MCP server that integrates with Kagi's Search API to provide web search capabilities.
Overview
The kagi-server is a Model Context Protocol implementation that bridges AI assistants with Kagi's search capabilities. It provides tools for performing web searches through Kagi's API, though many planned features like summarization and FastGPT are not yet implemented. The server demonstrates proper MCP structure with environment setup for API keys, build processes, and integration instructions for Claude Desktop.
Try asking AI
After installing, here are 5 things you can ask your AI assistant:
When to choose this
Choose this server if you need web search capabilities integrated into your AI workflow and are already using or planning to use Kagi's API.
When NOT to choose this
Don't choose this if you need alternative search engines, as it's specifically tied to Kagi's API which is currently in private beta.
Tools this server exposes
1 tool extracted from the READMEkagi_searchPerform web searches using Kagi's API
Comparable tools
Installation
Installation
Via Smithery
npx @smithery/cli install kagi-server --client claudeManual Installation
- Install dependencies:
``bash npm install ``
- Build the server:
``bash npm run build ``
- Add to Claude Desktop configuration:
{
"mcpServers": {
"kagi-server": {
"command": "/path/to/kagi-server/build/index.js",
"env": {
"KAGI_API_KEY": "your_api_key_here"
}
}
}
}FAQ
- What tools are currently available?
- Currently only the `kagi_search` tool is implemented. Planned tools like `kagi_summarize`, `kagi_fastgpt`, and `kagi_enrich` are not yet available.
- How do I get a Kagi API key?
- You need to obtain a Kagi API key from your Kagi account settings. The Kagi Search API is currently in private beta.
Compare mcp-servers-kagi with
Last updated · Auto-generated from public README + GitHub signals.