Kagi Search MCP server

Integrates Kagi search API to provide web search, news retrieval, and fast GPT-powered question answering for up-to-date information access and content enrichment.
Back to servers
Setup instructions
Provider
Aleksey Pridachin
Release date
Dec 27, 2024
Language
Python
Stats
2 stars

The Kagi MCP server connects your AI assistants to Kagi's web search capabilities, enabling them to search the internet, find answers, and enrich context with relevant web content or news articles through Kagi's API.

Installation

Installing via Smithery

The easiest way to install the Kagi MCP server for Claude Desktop is to use Smithery:

npx -y @smithery/cli install kagi-mcp --client claude

Manual Installation for Claude Desktop

For MacOS, you'll need to modify the Claude Desktop configuration file located at: ~/Library/Application\ Support/Claude/claude_desktop_config.json

Add the following to the configuration file:

"mcpServers": {
  "kagi-mcp": {
    "command": "uv",
    "args": [
      "--directory",
      "path_to_project",
      "run",
      "kagi-mcp"
    ],
    "env": {
      "KAGI_API_KEY": "YOUR API KEY"
    }
  }
}

Important: Replace "YOUR API KEY" with your actual Kagi API key and "path_to_project" with the path to the project directory.

Usage

The Kagi MCP server provides several tools that allow you to leverage Kagi's search capabilities:

Available Tools

  • ask_fastgpt: Search the web and find an answer using Kagi's FastGPT
  • enrich_web: Enrich your model's context with web content
  • enrich_news: Enrich your model's context with the latest news

API Methods

The server implements the following Kagi API methods:

  • fastgpt: Get quick answers from the web
  • enrich/web: Add relevant web content to your context
  • enrich/news: Add recent news to your context

Configuration

To use the Kagi MCP server, you need a valid Kagi API key which should be set in the environment variables as shown in the installation section. Make sure to keep your API key secure and never share it publicly.

When using the tools in your prompts, you can specify search queries and parameters according to the Kagi API documentation for the best results.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "kagi-mcp" '{"command":"uv","args":["run","kagi-mcp"],"env":{"KAGI_API_KEY":"YOUR API KEY"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "kagi-mcp": {
            "command": "uv",
            "args": [
                "run",
                "kagi-mcp"
            ],
            "env": {
                "KAGI_API_KEY": "YOUR API KEY"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "kagi-mcp": {
            "command": "uv",
            "args": [
                "run",
                "kagi-mcp"
            ],
            "env": {
                "KAGI_API_KEY": "YOUR API KEY"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later