MCP Servers Kagi MCP Server

MCP server for Kagi Search API (beta) integration

Local serverstdioTypeScript

What is the MCP Servers Kagi MCP server?

If you want an AI assistant working directly with MCP Servers Kagi, the mcp servers kagi mcp server is the bridge. MCP server for Kagi Search API (beta) integration.

What MCP Servers Kagi does

This is a TypeScript-based MCP server that integrates the Kagi Search API. It demonstrates core MCP concepts by providing:

Tools it exposes

Once connected, the assistant can call these 5 tools directly:

  • kagi_search — Perform web searches using Kagi
  • kagi_summarize — Generate summaries of web pages or text
  • kagi_fastgpt — Get quick responses using Kagi's FastGPT
  • kagi_enrich — Fetch enriched news results on specific topics
  • Debugging — Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the [MCP

Installing the mcp servers kagi mcp server

The server is distributed via npm as @smithery/cli, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.

Configuration

Before the server will start you need to supply one environment variable: KAGI_API_KEY. Keep credentials in your client's env block or a secrets manager rather than committing them.

Where it fits

Developer-tool servers are usually the first ones people connect, because they turn "help me with this code" into an assistant that can actually read the repo and act on it. MCP Servers Kagi sits in that group, and the shape of its toolset — kagi_search, kagi_summarize, kagi_fastgpt among others — tells you what it is really for. Worth comparing against the other developer tools servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

  • This server runs locally, so it operates with whatever access your machine and its credentials already have. Scope that deliberately rather than by default.
  • It will not start until its required credentials are present, so set those before wondering why the tools never appear.
  • Maintained by ac3xx, written in TypeScript.
  • MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the mcp servers kagi mcp server actually does with your data.
  • Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.

Available tools

ToolWhat it does
kagi_searchPerform web searches using Kagi
kagi_summarizeGenerate summaries of web pages or text
kagi_fastgptGet quick responses using Kagi's FastGPT
kagi_enrichFetch enriched news results on specific topics
DebuggingSince MCP servers communicate over stdio, debugging can be challenging. We recommend using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector), which is available as a package script:

How to install the MCP Servers Kagi MCP server

{
  "mcpServers": {
    "servers-kagi": {
      "command": "npx",
      "args": ["-y", "@smithery/cli"],
      "env": {
        "KAGI_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
KAGI_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use MCP Servers Kagi to kagi search.
  • Use MCP Servers Kagi to kagi summarize.
  • Use MCP Servers Kagi to kagi fastgpt.

Frequently asked questions

It connects MCP Servers Kagi to MCP-compatible AI assistants such as Claude and Cursor, exposing 5 tools (kagi_search, kagi_summarize, kagi_fastgpt, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with MCP Servers Kagi directly.